Proceedings of Machine Learning ResearchProceedings of the 38th International Conference on Machine Learning
Held in Virtual on 18-24 July 2021
Published as Volume 139 by the Proceedings of Machine Learning Research on 01 July 2021.
Volume Edited by:
Marina Meila
Tong Zhang
Series Editors:
Neil D. Lawrence
http://proceedings.mlr.press/v139/
Wed, 21 Jul 2021 06:43:53 +0000Wed, 21 Jul 2021 06:43:53 +0000Jekyll v3.9.0A Functional Perspective on Learning Symmetric Functions with Neural NetworksSymmetric functions, which take as input an unordered, fixed-size set, are known to be universally representable by neural networks that enforce permutation invariance. These architectures only give guarantees for fixed input sizes, yet in many practical applications, including point clouds and particle physics, a relevant notion of generalization should include varying the input size. In this work we treat symmetric functions (of any size) as functions over probability measures, and study the learning and representation of neural networks defined on measures. By focusing on shallow architectures, we establish approximation and generalization bounds under different choices of regularization (such as RKHS and variation norms), that capture a hierarchy of functional spaces with increasing degree of non-linear learning. The resulting models can be learned efficiently and enjoy generalization guarantees that extend across input sizes, as we verify empirically.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/zweig21a.html
http://proceedings.mlr.press/v139/zweig21a.htmlOn the Convergence of Hamiltonian Monte Carlo with Stochastic GradientsHamiltonian Monte Carlo (HMC), built based on the Hamilton’s equation, has been witnessed great success in sampling from high-dimensional posterior distributions. However, it also suffers from computational inefficiency, especially for large training datasets. One common idea to overcome this computational bottleneck is using stochastic gradients, which only queries a mini-batch of training data in each iteration. However, unlike the extensive studies on the convergence analysis of HMC using full gradients, few works focus on establishing the convergence guarantees of stochastic gradient HMC algorithms. In this paper, we propose a general framework for proving the convergence rate of HMC with stochastic gradient estimators, for sampling from strongly log-concave and log-smooth target distributions. We show that the convergence to the target distribution in $2$-Wasserstein distance can be guaranteed as long as the stochastic gradient estimator is unbiased and its variance is upper bounded along the algorithm trajectory. We further apply the proposed framework to analyze the convergence rates of HMC with four standard stochastic gradient estimators: mini-batch stochastic gradient (SG), stochastic variance reduced gradient (SVRG), stochastic average gradient (SAGA), and control variate gradient (CVG). Theoretical results explain the inefficiency of mini-batch SG, and suggest that SVRG and SAGA perform better in the tasks with high-precision requirements, while CVG performs better for large dataset. Experiment results verify our theoretical findings.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/zou21b.html
http://proceedings.mlr.press/v139/zou21b.htmlProvable Robustness of Adversarial Training for Learning Halfspaces with NoiseWe analyze the properties of adversarial training for learning adversarially robust halfspaces in the presence of agnostic label noise. Denoting $\mathsf{OPT}_{p,r}$ as the best classification error achieved by a halfspace that is robust to perturbations of $\ell^{p}$ balls of radius $r$, we show that adversarial training on the standard binary cross-entropy loss yields adversarially robust halfspaces up to classification error $\tilde O(\sqrt{\mathsf{OPT}_{2,r}})$ for $p=2$, and $\tilde O(d^{1/4} \sqrt{\mathsf{OPT}_{\infty, r}})$ when $p=\infty$. Our results hold for distributions satisfying anti-concentration properties enjoyed by log-concave isotropic distributions among others. We additionally show that if one instead uses a non-convex sigmoidal loss, adversarial training yields halfspaces with an improved robust classification error of $O(\mathsf{OPT}_{2,r})$ for $p=2$, and $O(d^{1/4} \mathsf{OPT}_{\infty, r})$ when $p=\infty$. To the best of our knowledge, this is the first work showing that adversarial training provably yields robust classifiers in the presence of noise.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/zou21a.html
http://proceedings.mlr.press/v139/zou21a.htmlExploration in Approximate Hyper-State Space for Meta Reinforcement LearningTo rapidly learn a new task, it is often essential for agents to explore efficiently - especially when performance matters from the first timestep. One way to learn such behaviour is via meta-learning. Many existing methods however rely on dense rewards for meta-training, and can fail catastrophically if the rewards are sparse. Without a suitable reward signal, the need for exploration during meta-training is exacerbated. To address this, we propose HyperX, which uses novel reward bonuses for meta-training to explore in approximate hyper-state space (where hyper-states represent the environment state and the agent’s task belief). We show empirically that HyperX meta-learns better task-exploration and adapts more successfully to new tasks than existing methods.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/zintgraf21a.html
http://proceedings.mlr.press/v139/zintgraf21a.htmlContrastive Learning Inverts the Data Generating ProcessContrastive learning has recently seen tremendous success in self-supervised learning. So far, however, it is largely unclear why the learned representations generalize so effectively to a large variety of downstream tasks. We here prove that feedforward models trained with objectives belonging to the commonly used InfoNCE family learn to implicitly invert the underlying generative model of the observed data. While the proofs make certain statistical assumptions about the generative model, we observe empirically that our findings hold even if these assumptions are severely violated. Our theory highlights a fundamental connection between contrastive learning, generative modeling, and nonlinear independent component analysis, thereby furthering our understanding of the learned representations as well as providing a theoretical foundation to derive more effective contrastive losses.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/zimmermann21a.html
http://proceedings.mlr.press/v139/zimmermann21a.htmlLearning Fair Policies in Decentralized Cooperative Multi-Agent Reinforcement LearningWe consider the problem of learning fair policies in (deep) cooperative multi-agent reinforcement learning (MARL). We formalize it in a principled way as the problem of optimizing a welfare function that explicitly encodes two important aspects of fairness: efficiency and equity. We provide a theoretical analysis of the convergence of policy gradient for this problem. As a solution method, we propose a novel neural network architecture, which is composed of two sub-networks specifically designed for taking into account these two aspects of fairness. In experiments, we demonstrate the importance of the two sub-networks for fair optimization. Our overall approach is general as it can accommodate any (sub)differentiable welfare function. Therefore, it is compatible with various notions of fairness that have been proposed in the literature (e.g., lexicographic maximin, generalized Gini social welfare function, proportional fairness). Our method is generic and can be implemented in various MARL settings: centralized training and decentralized execution, or fully decentralized. Finally, we experimentally validate our approach in various domains and show that it can perform much better than previous methods, both in terms of efficiency and equity.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/zimmer21a.html
http://proceedings.mlr.press/v139/zimmer21a.htmlRecovering AES Keys with a Deep Cold Boot AttackCold boot attacks inspect the corrupted random access memory soon after the power has been shut down. While most of the bits have been corrupted, many bits, at random locations, have not. Since the keys in many encryption schemes are being expanded in memory into longer keys with fixed redundancies, the keys can often be restored. In this work we combine a deep error correcting code technique together with a modified SAT solver scheme in order to apply the attack to AES keys. Even though AES consists Rijndael SBOX elements, that are specifically designed to be resistant to linear and differential cryptanalysis, our method provides a novel formalization of the AES key scheduling as a computational graph, which is implemented by neural message passing network. Our results show that our methods outperform the state of the art attack methods by a very large gap.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/zimerman21a.html
http://proceedings.mlr.press/v139/zimerman21a.htmlDemystifying Inductive Biases for (Beta-)VAE Based ArchitecturesThe performance of Beta-Variational-Autoencoders and their variants on learning semantically meaningful, disentangled representations is unparalleled. On the other hand, there are theoretical arguments suggesting the impossibility of unsupervised disentanglement. In this work, we shed light on the inductive bias responsible for the success of VAE-based architectures. We show that in classical datasets the structure of variance, induced by the generating factors, is conveniently aligned with the latent directions fostered by the VAE objective. This builds the pivotal bias on which the disentangling abilities of VAEs rely. By small, elaborate perturbations of existing datasets, we hide the convenient correlation structure that is easily exploited by a variety of architectures. To demonstrate this, we construct modified versions of standard datasets in which (i) the generative factors are perfectly preserved; (ii) each image undergoes a mild transformation causing a small change of variance; (iii) the leading VAE-based disentanglement architectures fail to produce disentangled representations whilst the performance of a non-variational method remains unchanged.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/zietlow21a.html
http://proceedings.mlr.press/v139/zietlow21a.htmlAccumulated Decoupled Learning with Gradient Staleness Mitigation for Convolutional Neural NetworksGradient staleness is a major side effect in decoupled learning when training convolutional neural networks asynchronously. Existing methods that ignore this effect might result in reduced generalization and even divergence. In this paper, we propose an accumulated decoupled learning (ADL), which includes a module-wise gradient accumulation in order to mitigate the gradient staleness. Unlike prior arts ignoring the gradient staleness, we quantify the staleness in such a way that its mitigation can be quantitatively visualized. As a new learning scheme, the proposed ADL is theoretically shown to converge to critical points in spite of its asynchronism. Extensive experiments on CIFAR-10 and ImageNet datasets are conducted, demonstrating that ADL gives promising generalization results while the state-of-the-art methods experience reduced generalization and divergence. In addition, our ADL is shown to have the fastest training speed among the compared methods.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/zhuang21a.html
http://proceedings.mlr.press/v139/zhuang21a.htmlCommutative Lie Group VAE for Disentanglement LearningWe view disentanglement learning as discovering an underlying structure that equivariantly reflects the factorized variations shown in data. Traditionally, such a structure is fixed to be a vector space with data variations represented by translations along individual latent dimensions. We argue this simple structure is suboptimal since it requires the model to learn to discard the properties (e.g. different scales of changes, different levels of abstractness) of data variations, which is an extra work than equivariance learning. Instead, we propose to encode the data variations with groups, a structure not only can equivariantly represent variations, but can also be adaptively optimized to preserve the properties of data variations. Considering it is hard to conduct training on group structures, we focus on Lie groups and adopt a parameterization using Lie algebra. Based on the parameterization, some disentanglement learning constraints are naturally derived. A simple model named Commutative Lie Group VAE is introduced to realize the group-based disentanglement learning. Experiments show that our model can effectively learn disentangled representations without supervision, and can achieve state-of-the-art performance without extra constraints.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/zhu21f.html
http://proceedings.mlr.press/v139/zhu21f.htmlClusterability as an Alternative to Anchor Points When Learning with Noisy LabelsThe label noise transition matrix, characterizing the probabilities of a training instance being wrongly annotated, is crucial to designing popular solutions to learning with noisy labels. Existing works heavily rely on finding “anchor points” or their approximates, defined as instances belonging to a particular class almost surely. Nonetheless, finding anchor points remains a non-trivial task, and the estimation accuracy is also often throttled by the number of available anchor points. In this paper, we propose an alternative option to the above task. Our main contribution is the discovery of an efficient estimation procedure based on a clusterability condition. We prove that with clusterable representations of features, using up to third-order consensuses of noisy labels among neighbor representations is sufficient to estimate a unique transition matrix. Compared with methods using anchor points, our approach uses substantially more instances and benefits from a much better sample complexity. We demonstrate the estimation accuracy and advantages of our estimates using both synthetic noisy labels (on CIFAR-10/100) and real human-level noisy labels (on Clothing1M and our self-collected human-annotated CIFAR-10). Our code and human-level noisy CIFAR-10 labels are available at https://github.com/UCSC-REAL/HOC.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/zhu21e.html
http://proceedings.mlr.press/v139/zhu21e.htmlFew-shot Language Coordination by Modeling Theory of MindNo man is an island. Humans develop the ability to communicate with a large community by coordinating with different interlocutors within short conversations. This ability is largely understudied by the research on building neural language communicative agents. We study the task of few-shot language coordination: agents quickly adapting to their conversational partners’ language abilities. Different from current communicative agents trained with self-play, we in- investigate this more general paradigm by requiring the lead agent to coordinate with a population of agents each of whom has different linguistic abilities. This leads to a general agent able to quickly adapt to communicating with unseen agents in the population. Unlike prior work, success here requires the ability to model the partner’s beliefs, a vital component of human communication. Drawing inspiration from the study of theory-of-mind (ToM; Premack & Woodruff (1978)), we study the effect of the speaker explicitly modeling the listener’s mental state. Learning by communicating with a population, the speakers, as shown in our experiments, acquire the ability to learn to predict the reactions of their partner upon various messages on-the-fly. The speaker’s predictions for the future actions help it generate the best instructions in order to maximize communicative goal with message costs. To examine our hypothesis that the instructions generated with ToM modeling yield better communication per- performance, we employ our agents in both a referential game and a language navigation task. Positive results from our experiments also hint at the importance of explicitly modeling language acquisition as a socio-pragmatic progress.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/zhu21d.html
http://proceedings.mlr.press/v139/zhu21d.htmlSpectral vertex sparsifiers and pair-wise spanners over distributed graphsGraph sparsification is a powerful tool to approximate an arbitrary graph and has been used in machine learning over graphs. As real-world networks are becoming very large and naturally distributed, distributed graph sparsification has drawn considerable attention. In this work, we design communication-efficient distributed algorithms for constructing spectral vertex sparsifiers, which closely preserve effective resistance distances on a subset of vertices of interest in the original graphs, under the well-established message passing communication model. We prove that the communication cost approximates the lower bound with only a small gap. We further provide algorithms for constructing pair-wise spanners which approximate the shortest distances between each pair of vertices in a target set, instead of all pairs, and incur communication costs that are much smaller than those of existing algorithms in the message passing model. Experiments are performed to validate the communication efficiency of the proposed algorithms under the guarantee that the constructed sparsifiers have a good approximation quality.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/zhu21c.html
http://proceedings.mlr.press/v139/zhu21c.htmlData-Free Knowledge Distillation for Heterogeneous Federated LearningFederated Learning (FL) is a decentralized machine-learning paradigm, in which a global server iteratively averages the model parameters of local users without accessing their data. User heterogeneity has imposed significant challenges to FL, which can incur drifted global models that are slow to converge. Knowledge Distillation has recently emerged to tackle this issue, by refining the server model using aggregated knowledge from heterogeneous users, other than directly averaging their model parameters. This approach, however, depends on a proxy dataset, making it impractical unless such a prerequisite is satisfied. Moreover, the ensemble knowledge is not fully utilized to guide local model learning, which may in turn affect the quality of the aggregated model. Inspired by the prior art, we propose a data-free knowledge distillation approach to address heterogeneous FL, where the server learns a lightweight generator to ensemble user information in a data-free manner, which is then broadcasted to users, regulating local training using the learned knowledge as an inductive bias. Empirical studies powered by theoretical implications show that our approach facilitates FL with better generalization performance using fewer communication rounds, compared with the state-of-the-art.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/zhu21b.html
http://proceedings.mlr.press/v139/zhu21b.htmlSparse and Imperceptible Adversarial Attack via a Homotopy AlgorithmSparse adversarial attacks can fool deep neural networks (DNNs) by only perturbing a few pixels (regularized by $\ell_0$ norm). Recent efforts combine it with another $\ell_\infty$ imperceptible on the perturbation magnitudes. The resultant sparse and imperceptible attacks are practically relevant, and indicate an even higher vulnerability of DNNs that we usually imagined. However, such attacks are more challenging to generate due to the optimization difficulty by coupling the $\ell_0$ regularizer and box constraints with a non-convex objective. In this paper, we address this challenge by proposing a homotopy algorithm, to jointly tackle the sparsity and the perturbation bound in one unified framework. Each iteration, the main step of our algorithm is to optimize an $\ell_0$-regularized adversarial loss, by leveraging the nonmonotone Accelerated Proximal Gradient Method (nmAPG) for nonconvex programming; it is followed by an $\ell_0$ change control step, and an optional post-attack step designed to escape bad local minima. We also extend the algorithm to handling the structural sparsity regularizer. We extensively examine the effectiveness of our proposed \textbf{homotopy attack} for both targeted and non-targeted attack scenarios, on CIFAR-10 and ImageNet datasets. Compared to state-of-the-art methods, our homotopy attack leads to significantly fewer perturbations, e.g., reducing 42.91% on CIFAR-10 and 75.03% on ImageNet (average case, targeted attack), at similar maximal perturbation magnitudes, when still achieving 100% attack success rates. Our codes are available at: {\small\url{https://github.com/VITA-Group/SparseADV_Homotopy}}.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/zhu21a.html
http://proceedings.mlr.press/v139/zhu21a.htmlExamining and Combating Spurious Features under Distribution ShiftA central goal of machine learning is to learn robust representations that capture the fundamental relationship between inputs and output labels. However, minimizing training errors over finite or biased datasets results in models latching on to spurious correlations between the training input/output pairs that are not fundamental to the problem at hand. In this paper, we define and analyze robust and spurious representations using the information-theoretic concept of minimal sufficient statistics. We prove that even when there is only bias of the input distribution (i.e. covariate shift), models can still pick up spurious features from their training data. Group distributionally robust optimization (DRO) provides an effective tool to alleviate covariate shift by minimizing the worst-case training losses over a set of pre-defined groups. Inspired by our analysis, we demonstrate that group DRO can fail when groups do not directly account for various spurious correlations that occur in the data. To address this, we further propose to minimize the worst-case losses over a more flexible set of distributions that are defined on the joint distribution of groups and instances, instead of treating each group as a whole at optimization time. Through extensive experiments on one image and two language tasks, we show that our model is significantly more robust than comparable baselines under various partitions.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/zhou21g.html
http://proceedings.mlr.press/v139/zhou21g.htmlAsymmetric Loss Functions for Learning with Noisy LabelsRobust loss functions are essential for training deep neural networks with better generalization power in the presence of noisy labels. Symmetric loss functions are confirmed to be robust to label noise. However, the symmetric condition is overly restrictive. In this work, we propose a new class of loss functions, namely asymmetric loss functions, which are robust to learning from noisy labels for arbitrary noise type. Subsequently, we investigate general theoretical properties of asymmetric loss functions, including classification-calibration, excess risk bound, and noise-tolerance. Meanwhile, we introduce the asymmetry ratio to measure the asymmetry of a loss function, and the empirical results show that a higher ratio will provide better robustness. Moreover, we modify several common loss functions, and establish the necessary and sufficient conditions for them to be asymmetric. Experiments on benchmark datasets demonstrate that asymmetric loss functions can outperform state-of-the-art methods.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/zhou21f.html
http://proceedings.mlr.press/v139/zhou21f.htmlTowards Defending against Adversarial Examples via Attack-Invariant FeaturesDeep neural networks (DNNs) are vulnerable to adversarial noise. Their adversarial robustness can be improved by exploiting adversarial examples. However, given the continuously evolving attacks, models trained on seen types of adversarial examples generally cannot generalize well to unseen types of adversarial examples. To solve this problem, in this paper, we propose to remove adversarial noise by learning generalizable invariant features across attacks which maintain semantic classification information. Specifically, we introduce an adversarial feature learning mechanism to disentangle invariant features from adversarial noise. A normalization term has been proposed in the encoded space of the attack-invariant features to address the bias issue between the seen and unseen types of attacks. Empirical evaluations demonstrate that our method could provide better protection in comparison to previous state-of-the-art approaches, especially against unseen types of attacks and adaptive attacks.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/zhou21e.html
http://proceedings.mlr.press/v139/zhou21e.htmlIncentivized Bandit Learning with Self-Reinforcing User PreferencesIn this paper, we investigate a new multi-armed bandit (MAB) online learning model that considers real-world phenomena in many recommender systems: (i) the learning agent cannot pull the arms by itself and thus has to offer rewards to users to incentivize arm-pulling indirectly; and (ii) if users with specific arm preferences are well rewarded, they induce a "self-reinforcing" effect in the sense that they will attract more users of similar arm preferences. Besides addressing the tradeoff of exploration and exploitation, another key feature of this new MAB model is to balance reward and incentivizing payment. The goal of the agent is to maximize the total reward over a fixed time horizon $T$ with a low total payment. Our contributions in this paper are two-fold: (i) We propose a new MAB model with random arm selection that considers the relationship of users’ self-reinforcing preferences and incentives; and (ii) We leverage the properties of a multi-color Polya urn with nonlinear feedback model to propose two MAB policies termed "At-Least-$n$ Explore-Then-Commit" and "UCB-List". We prove that both policies achieve $O(log T)$ expected regret with $O(log T)$ expected payment over a time horizon $T$. We conduct numerical simulations to demonstrate and verify the performances of these two policies and study their robustness under various settings.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/zhou21d.html
http://proceedings.mlr.press/v139/zhou21d.htmlOptimal Estimation of High Dimensional Smooth Additive Function Based on Noisy ObservationsGiven $\bx_j = \btheta + \bepsilon_j$, $j=1,...,n$ where $\btheta \in \RR^d$ is an unknown parameter and $\bepsilon_j$ are i.i.d. Gaussian noise vectors, we study the estimation of $f(\btheta)$ for a given smooth function $f:\RR^d \rightarrow \RR$ equipped with an additive structure. We inherit the idea from a recent work which introduced an effective bias reduction technique through iterative bootstrap and derive a bias-reducing estimator. By establishing its normal approximation results, we show that the proposed estimator can achieve asymptotic normality with a looser constraint on smoothness compared with general smooth function due to the additive structure. Such results further imply that the proposed estimator is asymptotically efficient. Both upper and lower bounds on mean squared error are proved which shows the proposed estimator is minimax optimal for the smooth class considered. Numerical simulation results are presented to validate our analysis and show its superior performance of the proposed estimator over the plug-in approach in terms of bias reduction and building confidence intervals.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/zhou21c.html
http://proceedings.mlr.press/v139/zhou21c.htmlAmortized Conditional Normalized Maximum Likelihood: Reliable Out of Distribution Uncertainty EstimationWhile deep neural networks provide good performance for a range of challenging tasks, calibration and uncertainty estimation remain major challenges, especially under distribution shift. In this paper, we propose the amortized conditional normalized maximum likelihood (ACNML) method as a scalable general-purpose approach for uncertainty estimation, calibration, and out-of-distribution robustness with deep networks. Our algorithm builds on the conditional normalized maximum likelihood (CNML) coding scheme, which has minimax optimal properties according to the minimum description length principle, but is computationally intractable to evaluate exactly for all but the simplest of model classes. We propose to use approximate Bayesian inference technqiues to produce a tractable approximation to the CNML distribution. Our approach can be combined with any approximate inference algorithm that provides tractable posterior densities over model parameters. We demonstrate that ACNML compares favorably to a number of prior techniques for uncertainty estimation in terms of calibration when faced with distribution shift.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/zhou21b.html
http://proceedings.mlr.press/v139/zhou21b.htmlProvably Efficient Reinforcement Learning for Discounted MDPs with Feature MappingModern tasks in reinforcement learning have large state and action spaces. To deal with them efficiently, one often uses predefined feature mapping to represent states and actions in a low dimensional space. In this paper, we study reinforcement learning for discounted Markov Decision Processes (MDPs), where the transition kernel can be parameterized as a linear function of certain feature mapping. We propose a novel algorithm which makes use of the feature mapping and obtains a $\tilde O(d\sqrt{T}/(1-\gamma)^2)$ regret, where $d$ is the dimension of the feature space, $T$ is the time horizon and $\gamma$ is the discount factor of the MDP. To the best of our knowledge, this is the first polynomial regret bound without accessing a generative model or making strong assumptions such as ergodicity of the MDP. By constructing a special class of MDPs, we also show that for any algorithms, the regret is lower bounded by $\Omega(d\sqrt{T}/(1-\gamma)^{1.5})$. Our upper and lower bound results together suggest that the proposed reinforcement learning algorithm is near-optimal up to a $(1-\gamma)^{-0.5}$ factor.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/zhou21a.html
http://proceedings.mlr.press/v139/zhou21a.htmlTowards Distraction-Robust Active Visual TrackingIn active visual tracking, it is notoriously difficult when distracting objects appear, as distractors often mislead the tracker by occluding the target or bringing a confusing appearance. To address this issue, we propose a mixed cooperative-competitive multi-agent game, where a target and multiple distractors form a collaborative team to play against a tracker and make it fail to follow. Through learning in our game, diverse distracting behaviors of the distractors naturally emerge, thereby exposing the tracker’s weakness, which helps enhance the distraction-robustness of the tracker. For effective learning, we then present a bunch of practical methods, including a reward function for distractors, a cross-modal teacher-student learning strategy, and a recurrent attention mechanism for the tracker. The experimental results show that our tracker performs desired distraction-robust active visual tracking and can be well generalized to unseen environments. We also show that the multi-agent game can be used to adversarially test the robustness of trackers.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/zhong21b.html
http://proceedings.mlr.press/v139/zhong21b.htmlProbabilistic Sequential Shrinking: A Best Arm Identification Algorithm for Stochastic Bandits with CorruptionsWe consider a best arm identification (BAI) problem for stochastic bandits with adversarial corruptions in the fixed-budget setting of T steps. We design a novel randomized algorithm, Probabilistic Sequential Shrinking(u) (PSS(u)), which is agnostic to the amount of corruptions. When the amount of corruptions per step (CPS) is below a threshold, PSS(u) identifies the best arm or item with probability tending to 1 as T{\rightarrow}$\infty$. Otherwise, the optimality gap of the identified item degrades gracefully with the CPS.We argue that such a bifurcation is necessary. In PSS(u), the parameter u serves to balance between the optimality gap and success probability. The injection of randomization is shown to be essential to mitigate the impact of corruptions. To demonstrate this, we design two attack strategies that are applicable to any algorithm. We apply one of them to a deterministic analogue of PSS(u) known as Successive Halving (SH) by Karnin et al. (2013). The attack strategy results in a high failure probability for SH, but PSS(u) remains robust. In the absence of corruptions, PSS(2)’s performance guarantee matches SH’s. We show that when the CPS is sufficiently large, no algorithm can achieve a BAI probability tending to 1 as T{\rightarrow}$\infty$. Numerical experiments corroborate our theoretical findings.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/zhong21a.html
http://proceedings.mlr.press/v139/zhong21a.htmlHow Framelets Enhance Graph Neural NetworksThis paper presents a new approach for assembling graph neural networks based on framelet transforms. The latter provides a multi-scale representation for graph-structured data. We decompose an input graph into low-pass and high-pass frequencies coefficients for network training, which then defines a framelet-based graph convolution. The framelet decomposition naturally induces a graph pooling strategy by aggregating the graph feature into low-pass and high-pass spectra, which considers both the feature values and geometry of the graph data and conserves the total information. The graph neural networks with the proposed framelet convolution and pooling achieve state-of-the-art performance in many node and graph prediction tasks. Moreover, we propose shrinkage as a new activation for the framelet convolution, which thresholds high-frequency information at different scales. Compared to ReLU, shrinkage activation improves model performance on denoising and signal compression: noises in both node and structure can be significantly reduced by accurately cutting off the high-pass coefficients from framelet decomposition, and the signal can be compressed to less than half its original size with well-preserved prediction performance.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/zheng21c.html
http://proceedings.mlr.press/v139/zheng21c.htmlTwo Heads are Better Than One: Hypergraph-Enhanced Graph Reasoning for Visual Event RatiocinationEven with a still image, humans can ratiocinate various visual cause-and-effect descriptions before, at present, and after, as well as beyond the given image. However, it is challenging for models to achieve such task–the visual event ratiocination, owing to the limitations of time and space. To this end, we propose a novel multi-modal model, Hypergraph-Enhanced Graph Reasoning. First it represents the contents from the same modality as a semantic graph and mines the intra-modality relationship, therefore breaking the limitations in the spatial domain. Then, we introduce the Graph Self-Attention Enhancement. On the one hand, this enables semantic graph representations from different modalities to enhance each other and captures the inter-modality relationship along the line. On the other hand, it utilizes our built multi-modal hypergraphs in different moments to boost individual semantic graph representations, and breaks the limitations in the temporal domain. Our method illustrates the case of "two heads are better than one" in the sense that semantic graph representations with the help of the proposed enhancement mechanism are more robust than those without. Finally, we re-project these representations and leverage their outcomes to generate textual cause-and-effect descriptions. Experimental results show that our model achieves significantly higher performance in comparison with other state-of-the-arts.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/zheng21b.html
http://proceedings.mlr.press/v139/zheng21b.htmlFused Acoustic and Text Encoding for Multimodal Bilingual Pretraining and Speech TranslationRecently, representation learning for text and speech has successfully improved many language related tasks. However, all existing methods suffer from two limitations: (a) they only learn from one input modality, while a unified representation for both speech and text is needed by tasks such as end-to-end speech translation, and as a result, (b) they can not exploit various large-scale text and speech data and their performance is limited by the scarcity of parallel speech translation data. To address these problems, we propose a Fused Acoustic and Text Masked Language Model (FAT-MLM) which jointly learns a unified representation for both acoustic and text input from various types of corpora including parallel data for speech recognition and machine translation, and even pure speech and text data. Within this cross-modal representation learning framework, we further present an end-to-end model for Fused Acoustic and Text Speech Translation (FAT-ST). Experiments on three translation directions show that by fine-tuning from FAT-MLM, our proposed speech translation models substantially improve translation quality by up to +5.9 BLEU.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/zheng21a.html
http://proceedings.mlr.press/v139/zheng21a.htmlExpressive 1-Lipschitz Neural Networks for Robust Multiple Graph Learning against Adversarial AttacksRecent findings have shown multiple graph learning models, such as graph classification and graph matching, are highly vulnerable to adversarial attacks, i.e. small input perturbations in graph structures and node attributes can cause the model failures. Existing defense techniques often defend specific attacks on particular multiple graph learning tasks. This paper proposes an attack-agnostic graph-adaptive 1-Lipschitz neural network, ERNN, for improving the robustness of deep multiple graph learning while achieving remarkable expressive power. A K_l-Lipschitz Weibull activation function is designed to enforce the gradient norm as K_l at layer l. The nearest matrix orthogonalization and polar decomposition techniques are utilized to constraint the weight norm as 1/K_l and make the norm-constrained weight close to the original weight. The theoretical analysis is conducted to derive lower and upper bounds of feasible K_l under the 1-Lipschitz constraint. The combination of norm-constrained weight and activation function leads to the 1-Lipschitz neural network for expressive and robust multiple graph learning.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/zhao21e.html
http://proceedings.mlr.press/v139/zhao21e.htmlFew-Shot Neural Architecture SearchEfficient evaluation of a network architecture drawn from a large search space remains a key challenge in Neural Architecture Search (NAS). Vanilla NAS evaluates each architecture by training from scratch, which gives the true performance but is extremely time-consuming. Recently, one-shot NAS substantially reduces the computation cost by training only one supernetwork, a.k.a. supernet, to approximate the performance of every architecture in the search space via weight-sharing. However, the performance estimation can be very inaccurate due to the co-adaption among operations. In this paper, we propose few-shot NAS that uses multiple supernetworks, called sub-supernet, each covering different regions of the search space to alleviate the undesired co-adaption. Compared to one-shot NAS, few-shot NAS improves the accuracy of architecture evaluation with a small increase of evaluation cost. With only up to 7 sub-supernets, few-shot NAS establishes new SoTAs: on ImageNet, it finds models that reach 80.5% top-1 accuracy at 600 MB FLOPS and 77.5% top-1 accuracy at 238 MFLOPS; on CIFAR10, it reaches 98.72% top-1 accuracy without using extra data or transfer learning. In Auto-GAN, few-shot NAS outperforms the previously published results by up to 20%. Extensive experiments show that few-shot NAS significantly improves various one-shot methods, including 4 gradient-based and 6 search-based methods on 3 different tasks in NasBench-201 and NasBench1-shot-1.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/zhao21d.html
http://proceedings.mlr.press/v139/zhao21d.htmlCalibrate Before Use: Improving Few-shot Performance of Language ModelsGPT-3 can perform numerous tasks when provided a natural language prompt that contains a few training examples. We show that this type of few-shot learning can be unstable: the choice of prompt format, training examples, and even the order of the examples can cause accuracy to vary from near chance to near state-of-the-art. We demonstrate that this instability arises from the bias of language models towards predicting certain answers, e.g., those that are placed near the end of the prompt or are common in the pre-training data. To mitigate this, we first estimate the model’s bias towards each answer by asking for its prediction when given a training prompt and a content-free test input such as "N/A". We then fit calibration parameters that cause the prediction for this input to be uniform across answers. On a diverse set of tasks, this contextual calibration procedure substantially improves GPT-3 and GPT-2’s accuracy (up to 30.0% absolute) across different choices of the prompt, while also making learning considerably more stable.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/zhao21c.html
http://proceedings.mlr.press/v139/zhao21c.htmlJoining datasets via data augmentation in the label space for neural networksMost, if not all, modern deep learning systems restrict themselves to a single dataset for neural network training and inference. In this article, we are interested in systematic ways to join datasets that are made of similar purposes. Unlike previous published works that ubiquitously conduct the dataset joining in the uninterpretable latent vectorial space, the core to our method is an augmentation procedure in the label space. The primary challenge to address the label space for dataset joining is the discrepancy between labels: non-overlapping label annotation sets, different labeling granularity or hierarchy and etc. Notably we propose a new technique leveraging artificially created knowledge graph, recurrent neural networks and policy gradient that successfully achieve the dataset joining in the label space. Empirical results on both image and text classification justify the validity of our approach.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/zhao21b.html
http://proceedings.mlr.press/v139/zhao21b.htmlDataset Condensation with Differentiable Siamese AugmentationIn many machine learning problems, large-scale datasets have become the de-facto standard to train state-of-the-art deep networks at the price of heavy computation load. In this paper, we focus on condensing large training sets into significantly smaller synthetic sets which can be used to train deep neural networks from scratch with minimum drop in performance. Inspired from the recent training set synthesis methods, we propose Differentiable Siamese Augmentation that enables effective use of data augmentation to synthesize more informative synthetic images and thus achieves better performance when training networks with augmentations. Experiments on multiple image classification benchmarks demonstrate that the proposed method obtains substantial gains over the state-of-the-art, 7% improvements on CIFAR10 and CIFAR100 datasets. We show with only less than 1% data that our method achieves 99.6%, 94.9%, 88.5%, 71.5% relative performance on MNIST, FashionMNIST, SVHN, CIFAR10 respectively. We also explore the use of our method in continual learning and neural architecture search, and show promising results.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/zhao21a.html
http://proceedings.mlr.press/v139/zhao21a.htmlMultiscale Invertible Generative Networks for High-Dimensional Bayesian InferenceWe propose a Multiscale Invertible Generative Network (MsIGN) and associated training algorithm that leverages multiscale structure to solve high-dimensional Bayesian inference. To address the curse of dimensionality, MsIGN exploits the low-dimensional nature of the posterior, and generates samples from coarse to fine scale (low to high dimension) by iteratively upsampling and refining samples. MsIGN is trained in a multi-stage manner to minimize the Jeffreys divergence, which avoids mode dropping in high-dimensional cases. On two high-dimensional Bayesian inverse problems, we show superior performance of MsIGN over previous approaches in posterior approximation and multiple mode capture. On the natural image synthesis task, MsIGN achieves superior performance in bits-per-dimension over baseline models and yields great interpret-ability of its neurons in intermediate layers.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/zhang21z.html
http://proceedings.mlr.press/v139/zhang21z.htmlBreaking the Deadly Triad with a Target NetworkThe deadly triad refers to the instability of a reinforcement learning algorithm when it employs off-policy learning, function approximation, and bootstrapping simultaneously. In this paper, we investigate the target network as a tool for breaking the deadly triad, providing theoretical support for the conventional wisdom that a target network stabilizes training. We first propose and analyze a novel target network update rule which augments the commonly used Polyak-averaging style update with two projections. We then apply the target network and ridge regularization in several divergent algorithms and show their convergence to regularized TD fixed points. Those algorithms are off-policy with linear function approximation and bootstrapping, spanning both policy evaluation and control, as well as both discounted and average-reward settings. In particular, we provide the first convergent linear $Q$-learning algorithms under nonrestrictive and changing behavior policies without bi-level optimization.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/zhang21y.html
http://proceedings.mlr.press/v139/zhang21y.htmlWorld Model as a Graph: Learning Latent Landmarks for PlanningPlanning, the ability to analyze the structure of a problem in the large and decompose it into interrelated subproblems, is a hallmark of human intelligence. While deep reinforcement learning (RL) has shown great promise for solving relatively straightforward control tasks, it remains an open problem how to best incorporate planning into existing deep RL paradigms to handle increasingly complex environments. One prominent framework, Model-Based RL, learns a world model and plans using step-by-step virtual rollouts. This type of world model quickly diverges from reality when the planning horizon increases, thus struggling at long-horizon planning. How can we learn world models that endow agents with the ability to do temporally extended reasoning? In this work, we propose to learn graph-structured world models composed of sparse, multi-step transitions. We devise a novel algorithm to learn latent landmarks that are scattered (in terms of reachability) across the goal space as the nodes on the graph. In this same graph, the edges are the reachability estimates distilled from Q-functions. On a variety of high-dimensional continuous control tasks ranging from robotic manipulation to navigation, we demonstrate that our method, named L3P, significantly outperforms prior work, and is oftentimes the only method capable of leveraging both the robustness of model-free RL and generalization of graph-search algorithms. We believe our work is an important step towards scalable planning in reinforcement learning.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/zhang21x.html
http://proceedings.mlr.press/v139/zhang21x.htmlMetaCURE: Meta Reinforcement Learning with Empowerment-Driven ExplorationMeta reinforcement learning (meta-RL) extracts knowledge from previous tasks and achieves fast adaptation to new tasks. Despite recent progress, efficient exploration in meta-RL remains a key challenge in sparse-reward tasks, as it requires quickly finding informative task-relevant experiences in both meta-training and adaptation. To address this challenge, we explicitly model an exploration policy learning problem for meta-RL, which is separated from exploitation policy learning, and introduce a novel empowerment-driven exploration objective, which aims to maximize information gain for task identification. We derive a corresponding intrinsic reward and develop a new off-policy meta-RL framework, which efficiently learns separate context-aware exploration and exploitation policies by sharing the knowledge of task inference. Experimental evaluation shows that our meta-RL method significantly outperforms state-of-the-art baselines on various sparse-reward MuJoCo locomotion tasks and more complex sparse-reward Meta-World tasks.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/zhang21w.html
http://proceedings.mlr.press/v139/zhang21w.htmlMatrix Sketching for Secure Collaborative Machine LearningCollaborative learning allows participants to jointly train a model without data sharing. To update the model parameters, the central server broadcasts model parameters to the clients, and the clients send updating directions such as gradients to the server. While data do not leave a client device, the communicated gradients and parameters will leak a client’s privacy. Attacks that infer clients’ privacy from gradients and parameters have been developed by prior work. Simple defenses such as dropout and differential privacy either fail to defend the attacks or seriously hurt test accuracy. We propose a practical defense which we call Double-Blind Collaborative Learning (DBCL). The high-level idea is to apply random matrix sketching to the parameters (aka weights) and re-generate random sketching after each iteration. DBCL prevents clients from conducting gradient-based privacy inferences which are the most effective attacks. DBCL works because from the attacker’s perspective, sketching is effectively random noise that outweighs the signal. Notably, DBCL does not much increase computation and communication costs and does not hurt test accuracy at all.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/zhang21v.html
http://proceedings.mlr.press/v139/zhang21v.htmlAverage-Reward Off-Policy Policy Evaluation with Function ApproximationWe consider off-policy policy evaluation with function approximation (FA) in average-reward MDPs, where the goal is to estimate both the reward rate and the differential value function. For this problem, bootstrapping is necessary and, along with off-policy learning and FA, results in the deadly triad (Sutton & Barto, 2018). To address the deadly triad, we propose two novel algorithms, reproducing the celebrated success of Gradient TD algorithms in the average-reward setting. In terms of estimating the differential value function, the algorithms are the first convergent off-policy linear function approximation algorithms. In terms of estimating the reward rate, the algorithms are the first convergent off-policy linear function approximation algorithms that do not require estimating the density ratio. We demonstrate empirically the advantage of the proposed algorithms, as well as their nonlinear variants, over a competitive density-ratio-based approach, in a simple domain as well as challenging robot simulation tasks.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/zhang21u.html
http://proceedings.mlr.press/v139/zhang21u.htmlDeep Coherent Exploration for Continuous ControlIn policy search methods for reinforcement learning (RL), exploration is often performed by injecting noise either in action space at each step independently or in parameter space over each full trajectory. In prior work, it has been shown that with linear policies, a more balanced trade-off between these two exploration strategies is beneficial. However, that method did not scale to policies using deep neural networks. In this paper, we introduce deep coherent exploration, a general and scalable exploration framework for deep RL algorithms for continuous control, that generalizes step-based and trajectory-based exploration. This framework models the last layer parameters of the policy network as latent variables and uses a recursive inference step within the policy update to handle these latent variables in a scalable manner. We find that deep coherent exploration improves the speed and stability of learning of A2C, PPO, and SAC on several continuous control tasks.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/zhang21t.html
http://proceedings.mlr.press/v139/zhang21t.htmliDARTS: Differentiable Architecture Search with Stochastic Implicit GradientsDifferentiable ARchiTecture Search(DARTS) has recently become the mainstream in the neural architecture search (NAS) due to its efficiency and simplicity. With a gradient-based bi-level optimization, DARTS alternately optimizes the inner model weights and the outer architecture parameter in a weight-sharing supernet. A key challenge to the scalability and quality of the learned architectures is the need for differentiating through the inner-loop optimisation. While much has been discussed about several potentially fatal factors in DARTS, the architecture gradient, a.k.a. hypergradient, has received less attention. In this paper, we tackle the hypergradient computation in DARTS based on the implicit function theorem, making it only depends on the obtained solution to the inner-loop optimization and agnostic to the optimization path. To further reduce the computational requirements, we formulate a stochastic hypergradient approximation for differentiable NAS, and theoretically show that the architecture optimization with the proposed method is expected to converge to a stationary point. Comprehensive experiments on two NAS benchmark search spaces and the common NAS search space verify the effectiveness of our proposed method. It leads to architectures outperforming, with large margins, those learned by the baseline methods.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/zhang21s.html
http://proceedings.mlr.press/v139/zhang21s.htmlDifferentiable Dynamic Quantization with Mixed Precision and Adaptive ResolutionModel quantization is challenging due to many tedious hyper-parameters such as precision (bitwidth), dynamic range (minimum and maximum discrete values) and stepsize (interval between discrete values). Unlike prior arts that carefully tune these values, we present a fully differentiable approach to learn all of them, named Differentiable Dynamic Quantization (DDQ), which has several benefits. (1) DDQ is able to quantize challenging lightweight architectures like MobileNets, where different layers prefer different quantization parameters. (2) DDQ is hardware-friendly and can be easily implemented using low-precision matrix-vector multiplication, making it capable in many hardware such as ARM. (3) Extensive experiments show that DDQ outperforms prior arts on many networks and benchmarks, especially when models are already efficient and compact. e.g., DDQ is the first approach that achieves lossless 4-bit quantization for MobileNetV2 on ImageNet.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/zhang21r.html
http://proceedings.mlr.press/v139/zhang21r.htmlOn-Policy Deep Reinforcement Learning for the Average-Reward CriterionWe develop theory and algorithms for average-reward on-policy Reinforcement Learning (RL). We first consider bounding the difference of the long-term average reward for two policies. We show that previous work based on the discounted return (Schulman et al. 2015, Achiam et al. 2017) results in a non-meaningful lower bound in the average reward setting. By addressing the average-reward criterion directly, we then derive a novel bound which depends on the average divergence between the policies and on Kemeny’s constant. Based on this bound, we develop an iterative procedure which produces a sequence of monotonically improved policies for the average reward criterion. This iterative procedure can then be combined with classic Deep Reinforcement Learning (DRL) methods, resulting in practical DRL algorithms that target the long-run average reward criterion. In particular, we demonstrate that Average-Reward TRPO (ATRPO), which adapts the on-policy TRPO algorithm to the average-reward criterion, significantly outperforms TRPO in the most challenging MuJuCo environments.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/zhang21q.html
http://proceedings.mlr.press/v139/zhang21q.htmlTowards Better Robust Generalization with Shift Consistency RegularizationWhile adversarial training becomes one of the most promising defending approaches against adversarial attacks for deep neural networks, the conventional wisdom through robust optimization may usually not guarantee good generalization for robustness. Concerning with robust generalization over unseen adversarial data, this paper investigates adversarial training from a novel perspective of shift consistency in latent space. We argue that the poor robust generalization of adversarial training is owing to the significantly dispersed latent representations generated by training and test adversarial data, as the adversarial perturbations push the latent features of natural examples in the same class towards diverse directions. This is underpinned by the theoretical analysis of the robust generalization gap, which is upper-bounded by the standard one over the natural data and a term of feature inconsistent shift caused by adversarial perturbation {–} a measure of latent dispersion. Towards better robust generalization, we propose a new regularization method {–} shift consistency regularization (SCR) {–} to steer the same-class latent features of both natural and adversarial data into a common direction during adversarial training. The effectiveness of SCR in adversarial training is evaluated through extensive experiments over different datasets, such as CIFAR-10, CIFAR-100, and SVHN, against several competitive methods.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/zhang21p.html
http://proceedings.mlr.press/v139/zhang21p.htmlQuantile Bandits for Best Arms IdentificationWe consider a variant of the best arm identification task in stochastic multi-armed bandits. Motivated by risk-averse decision-making problems, our goal is to identify a set of $m$ arms with the highest $\tau$-quantile values within a fixed budget. We prove asymmetric two-sided concentration inequalities for order statistics and quantiles of random variables that have non-decreasing hazard rate, which may be of independent interest. With these inequalities, we analyse a quantile version of Successive Accepts and Rejects (Q-SAR). We derive an upper bound for the probability of arm misidentification, the first justification of a quantile based algorithm for fixed budget multiple best arms identification. We show illustrative experiments for best arm identification.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/zhang21o.html
http://proceedings.mlr.press/v139/zhang21o.htmlLearning Noise Transition Matrix from Only Noisy Labels via Total Variation RegularizationMany weakly supervised classification methods employ a noise transition matrix to capture the class-conditional label corruption. To estimate the transition matrix from noisy data, existing methods often need to estimate the noisy class-posterior, which could be unreliable due to the overconfidence of neural networks. In this work, we propose a theoretically grounded method that can estimate the noise transition matrix and learn a classifier simultaneously, without relying on the error-prone noisy class-posterior estimation. Concretely, inspired by the characteristics of the stochastic label corruption process, we propose total variation regularization, which encourages the predicted probabilities to be more distinguishable from each other. Under mild assumptions, the proposed method yields a consistent estimator of the transition matrix. We show the effectiveness of the proposed method through experiments on benchmark and real-world datasets.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/zhang21n.html
http://proceedings.mlr.press/v139/zhang21n.htmlFOP: Factorizing Optimal Joint Policy of Maximum-Entropy Multi-Agent Reinforcement LearningValue decomposition recently injects vigorous vitality into multi-agent actor-critic methods. However, existing decomposed actor-critic methods cannot guarantee the convergence of global optimum. In this paper, we present a novel multi-agent actor-critic method, FOP, which can factorize the optimal joint policy induced by maximum-entropy multi-agent reinforcement learning (MARL) into individual policies. Theoretically, we prove that factorized individual policies of FOP converge to the global optimum. Empirically, in the well-known matrix game and differential game, we verify that FOP can converge to the global optimum for both discrete and continuous action spaces. We also evaluate FOP on a set of StarCraft II micromanagement tasks, and demonstrate that FOP substantially outperforms state-of-the-art decomposed value-based and actor-critic methods.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/zhang21m.html
http://proceedings.mlr.press/v139/zhang21m.htmlProgressive-Scale Boundary Blackbox Attack via Projective Gradient EstimationBoundary based blackbox attack has been recognized as practical and effective, given that an attacker only needs to access the final model prediction. However, the query efficiency of it is in general high especially for high dimensional image data. In this paper, we show that such efficiency highly depends on the scale at which the attack is applied, and attacking at the optimal scale significantly improves the efficiency. In particular, we propose a theoretical framework to analyze and show three key characteristics to improve the query efficiency. We prove that there exists an optimal scale for projective gradient estimation. Our framework also explains the satisfactory performance achieved by existing boundary black-box attacks. Based on our theoretical framework, we propose Progressive-Scale enabled projective Boundary Attack (PSBA) to improve the query efficiency via progressive scaling techniques. In particular, we employ Progressive-GAN to optimize the scale of projections, which we call PSBA-PGAN. We evaluate our approach on both spatial and frequency scales. Extensive experiments on MNIST, CIFAR-10, CelebA, and ImageNet against different models including a real-world face recognition API show that PSBA-PGAN significantly outperforms existing baseline attacks in terms of query efficiency and attack success rate. We also observe relatively stable optimal scales for different models and datasets. The code is publicly available at https://github.com/AI-secure/PSBA.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/zhang21l.html
http://proceedings.mlr.press/v139/zhang21l.htmlLearning from Noisy Labels with No Change to the Training ProcessThere has been much interest in recent years in developing learning algorithms that can learn accurate classifiers from data with noisy labels. A widely-studied noise model is that of \emph{class-conditional noise} (CCN), wherein a label $y$ is flipped to a label $\tilde{y}$ with some associated noise probability that depends on both $y$ and $\tilde{y}$. In the multiclass setting, all previously proposed algorithms under the CCN model involve changing the training process, by introducing a ‘noise-correction’ to the surrogate loss to be minimized over the noisy training examples. In this paper, we show that this is really unnecessary: one can simply perform class probability estimation (CPE) on the noisy examples, e.g. using a standard (multiclass) logistic regression algorithm, and then apply noise-correction only in the final prediction step. This means that the training algorithm itself does not need any change, and one can simply use standard off-the-shelf implementations with no modification to the code for training. Our approach can handle general multiclass loss matrices, including the usual 0-1 loss but also other losses such as those used for ordinal regression problems. We also provide a quantitative regret transfer bound, which bounds the target regret on the true distribution in terms of the CPE regret on the noisy distribution; in doing so, we extend the notion of strong properness introduced for binary losses by Agarwal (2014) to the multiclass case. Our bound suggests that the sample complexity of learning under CCN increases as the noise matrix approaches singularity. We also provide fixes and potential improvements for noise estimation methods that involve computing anchor points. Our experiments confirm our theoretical findings.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/zhang21k.html
http://proceedings.mlr.press/v139/zhang21k.htmlPAPRIKA: Private Online False Discovery Rate ControlIn hypothesis testing, a \emph{false discovery} occurs when a hypothesis is incorrectly rejected due to noise in the sample. When adaptively testing multiple hypotheses, the probability of a false discovery increases as more tests are performed. Thus the problem of \emph{False Discovery Rate (FDR) control} is to find a procedure for testing multiple hypotheses that accounts for this effect in determining the set of hypotheses to reject. The goal is to minimize the number (or fraction) of false discoveries, while maintaining a high true positive rate (i.e., correct discoveries). In this work, we study False Discovery Rate (FDR) control in multiple hypothesis testing under the constraint of differential privacy for the sample. Unlike previous work in this direction, we focus on the \emph{online setting}, meaning that a decision about each hypothesis must be made immediately after the test is performed, rather than waiting for the output of all tests as in the offline setting. We provide new private algorithms based on state-of-the-art results in non-private online FDR control. Our algorithms have strong provable guarantees for privacy and statistical performance as measured by FDR and power. We also provide experimental results to demonstrate the efficacy of our algorithms in a variety of data environments.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/zhang21j.html
http://proceedings.mlr.press/v139/zhang21j.htmlProbabilistic Generating CircuitsGenerating functions, which are widely used in combinatorics and probability theory, encode function values into the coefficients of a polynomial. In this paper, we explore their use as a tractable probabilistic model, and propose probabilistic generating circuits (PGCs) for their efficient representation. PGCs are strictly more expressive efficient than many existing tractable probabilistic models, including determinantal point processes (DPPs), probabilistic circuits (PCs) such as sum-product networks, and tractable graphical models. We contend that PGCs are not just a theoretical framework that unifies vastly different existing models, but also show great potential in modeling realistic data. We exhibit a simple class of PGCs that are not trivially subsumed by simple combinations of PCs and DPPs, and obtain competitive performance on a suite of density estimation benchmarks. We also highlight PGCs’ connection to the theory of strongly Rayleigh distributions.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/zhang21i.html
http://proceedings.mlr.press/v139/zhang21i.htmlPoolingformer: Long Document Modeling with Pooling AttentionIn this paper, we introduce a two-level attention schema, Poolingformer, for long document modeling. Its first level uses a smaller sliding window pattern to aggregate information from neighbors. Its second level employs a larger window to increase receptive fields with pooling attention to reduce both computational cost and memory consumption. We first evaluate Poolingformer on two long sequence QA tasks: the monolingual NQ and the multilingual TyDi QA. Experimental results show that Poolingformer sits atop three official leaderboards measured by F1, outperforming previous state-of-the-art models by 1.9 points (79.8 vs. 77.9) on NQ long answer, 1.9 points (79.5 vs. 77.6) on TyDi QA passage answer, and 1.6 points (67.6 vs. 66.0) on TyDi QA minimal answer. We further evaluate Poolingformer on a long sequence summarization task. Experimental results on the arXiv benchmark continue to demonstrate its superior performance.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/zhang21h.html
http://proceedings.mlr.press/v139/zhang21h.htmlUnderstanding Failures in Out-of-Distribution Detection with Deep Generative ModelsDeep generative models (DGMs) seem a natural fit for detecting out-of-distribution (OOD) inputs, but such models have been shown to assign higher probabilities or densities to OOD images than images from the training distribution. In this work, we explain why this behavior should be attributed to model misestimation. We first prove that no method can guarantee performance beyond random chance without assumptions on which out-distributions are relevant. We then interrogate the typical set hypothesis, the claim that relevant out-distributions can lie in high likelihood regions of the data distribution, and that OOD detection should be defined based on the data distribution’s typical set. We highlight the consequences implied by assuming support overlap between in- and out-distributions, as well as the arbitrariness of the typical set for OOD detection. Our results suggest that estimation error is a more plausible explanation than the misalignment between likelihood-based OOD detection and out-distributions of interest, and we illustrate how even minimal estimation error can lead to OOD detection failures, yielding implications for future work in deep generative modeling and OOD detection.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/zhang21g.html
http://proceedings.mlr.press/v139/zhang21g.htmlBayesian Attention Belief NetworksAttention-based neural networks have achieved state-of-the-art results on a wide range of tasks. Most such models use deterministic attention while stochastic attention is less explored due to the optimization difficulties or complicated model design. This paper introduces Bayesian attention belief networks, which construct a decoder network by modeling unnormalized attention weights with a hierarchy of gamma distributions, and an encoder network by stacking Weibull distributions with a deterministic-upward-stochastic-downward structure to approximate the posterior. The resulting auto-encoding networks can be optimized in a differentiable way with a variational lower bound. It is simple to convert any models with deterministic attention, including pretrained ones, to the proposed Bayesian attention belief networks. On a variety of language understanding tasks, we show that our method outperforms deterministic attention and state-of-the-art stochastic attention in accuracy, uncertainty estimation, generalization across domains, and robustness to adversarial attacks. We further demonstrate the general applicability of our method on neural machine translation and visual question answering, showing great potential of incorporating our method into various attention-related tasks.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/zhang21f.html
http://proceedings.mlr.press/v139/zhang21f.htmlNear Optimal Reward-Free Reinforcement LearningWe study the reward-free reinforcement learning framework, which is particularly suitable for batch reinforcement learning and scenarios where one needs policies for multiple reward functions. This framework has two phases: in the exploration phase, the agent collects trajectories by interacting with the environment without using any reward signal; in the planning phase, the agent needs to return a near-optimal policy for arbitrary reward functions. %This framework is suitable for batch RL setting and the setting where there are multiple reward functions of interes We give a new efficient algorithm, \textbf{S}taged \textbf{S}ampling + \textbf{T}runcated \textbf{P}lanning (\algoname), which interacts with the environment at most $O\left( \frac{S^2A}{\epsilon^2}\poly\log\left(\frac{SAH}{\epsilon}\right) \right)$ episodes in the exploration phase, and guarantees to output a near-optimal policy for arbitrary reward functions in the planning phase, where $S$ is the size of state space, $A$ is the size of action space, $H$ is the planning horizon, and $\epsilon$ is the target accuracy relative to the total reward. Notably, our sample complexity scales only \emph{logarithmically} with $H$, in contrast to all existing results which scale \emph{polynomially} with $H$. Furthermore, this bound matches the minimax lower bound $\Omega\left(\frac{S^2A}{\epsilon^2}\right)$ up to logarithmic factors. Our results rely on three new techniques : 1) A new sufficient condition for the dataset to plan for an $\epsilon$-suboptimal policy % for any totally bounded reward function ; 2) A new way to plan efficiently under the proposed condition using soft-truncated planning; 3) Constructing extended MDP to maximize the truncated accumulative rewards efficiently.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/zhang21e.html
http://proceedings.mlr.press/v139/zhang21e.htmlRobust Policy Gradient against Strong Data CorruptionWe study the problem of robust reinforcement learning under adversarial corruption on both rewards and transitions. Our attack model assumes an \textit{adaptive} adversary who can arbitrarily corrupt the reward and transition at every step within an episode, for at most $\epsilon$-fraction of the learning episodes. Our attack model is strictly stronger than those considered in prior works. Our first result shows that no algorithm can find a better than $O(\epsilon)$-optimal policy under our attack model. Next, we show that surprisingly the natural policy gradient (NPG) method retains a natural robustness property if the reward corruption is bounded, and can find an $O(\sqrt{\epsilon})$-optimal policy. Consequently, we develop a Filtered Policy Gradient (FPG) algorithm that can tolerate even unbounded reward corruption and can find an $O(\epsilon^{1/4})$-optimal policy. We emphasize that FPG is the first that can achieve a meaningful learning guarantee when a constant fraction of episodes are corrupted. Complimentary to the theoretical results, we show that a neural implementation of FPG achieves strong robust learning performance on the MuJoCo continuous control benchmarks.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/zhang21d.html
http://proceedings.mlr.press/v139/zhang21d.htmlEfficient Lottery Ticket Finding: Less Data is MoreThe lottery ticket hypothesis (LTH) reveals the existence of winning tickets (sparse but critical subnetworks) for dense networks, that can be trained in isolation from random initialization to match the latter’s accuracies. However, finding winning tickets requires burdensome computations in the train-prune-retrain process, especially on large-scale datasets (e.g., ImageNet), restricting their practical benefits. This paper explores a new perspective on finding lottery tickets more efficiently, by doing so only with a specially selected subset of data, called Pruning-Aware Critical set (PrAC set), rather than using the full training set. The concept of PrAC set was inspired by the recent observation, that deep networks have samples that are either hard to memorize during training, or easy to forget during pruning. A PrAC set is thus hypothesized to capture those most challenging and informative examples for the dense model. We observe that a high-quality winning ticket can be found with training and pruning the dense network on the very compact PrAC set, which can substantially save training iterations for the ticket finding process. Extensive experiments validate our proposal across diverse datasets and network architectures. Specifically, on CIFAR-10, CIFAR-100, and Tiny ImageNet, we locate effective PrAC sets at 35.32% 78.19% of their training set sizes. On top of them, we can obtain the same competitive winning tickets for the corresponding dense networks, yet saving up to 82.85% 92.77%, 63.54% 74.92%, and 76.14% 86.56% training iterations, respectively. Crucially, we show that a PrAC set found is reusable across different network architectures, which can amortize the extra cost of finding PrAC sets, yielding a practical regime for efficient lottery ticket finding.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/zhang21c.html
http://proceedings.mlr.press/v139/zhang21c.htmlTowards Certifying L-infinity Robustness using Neural Networks with L-inf-dist NeuronsIt is well-known that standard neural networks, even with a high classification accuracy, are vulnerable to small $\ell_\infty$-norm bounded adversarial perturbations. Although many attempts have been made, most previous works either can only provide empirical verification of the defense to a particular attack method, or can only develop a certified guarantee of the model robustness in limited scenarios. In this paper, we seek for a new approach to develop a theoretically principled neural network that inherently resists $\ell_\infty$ perturbations. In particular, we design a novel neuron that uses $\ell_\infty$-distance as its basic operation (which we call $\ell_\infty$-dist neuron), and show that any neural network constructed with $\ell_\infty$-dist neurons (called $\ell_{\infty}$-dist net) is naturally a 1-Lipschitz function with respect to $\ell_\infty$-norm. This directly provides a rigorous guarantee of the certified robustness based on the margin of prediction outputs. We then prove that such networks have enough expressive power to approximate any 1-Lipschitz function with robust generalization guarantee. We further provide a holistic training strategy that can greatly alleviate optimization difficulties. Experimental results show that using $\ell_{\infty}$-dist nets as basic building blocks, we consistently achieve state-of-the-art performance on commonly used datasets: 93.09% certified accuracy on MNIST ($\epsilon=0.3$), 35.42% on CIFAR-10 ($\epsilon=8/255$) and 16.31% on TinyImageNet ($\epsilon=1/255$).Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/zhang21b.html
http://proceedings.mlr.press/v139/zhang21b.htmlLearning to Rehearse in Long Sequence MemorizationExisting reasoning tasks often have an important assumption that the input contents can be always accessed while reasoning, requiring unlimited storage resources and suffering from severe time delay on long sequences. To achieve efficient reasoning on long sequences with limited storage resources, memory augmented neural networks introduce a human-like write-read memory to compress and memorize the long input sequence in one pass, trying to answer subsequent queries only based on the memory. But they have two serious drawbacks: 1) they continually update the memory from current information and inevitably forget the early contents; 2) they do not distinguish what information is important and treat all contents equally. In this paper, we propose the Rehearsal Memory (RM) to enhance long-sequence memorization by self-supervised rehearsal with a history sampler. To alleviate the gradual forgetting of early information, we design self-supervised rehearsal training with recollection and familiarity tasks. Further, we design a history sampler to select informative fragments for rehearsal training, making the memory focus on the crucial information. We evaluate the performance of our rehearsal memory by the synthetic bAbI task and several downstream tasks, including text/video question answering and recommendation on long sequences.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/zhang21ac.html
http://proceedings.mlr.press/v139/zhang21ac.htmlModel-Free Reinforcement Learning: from Clipped Pseudo-Regret to Sample ComplexityIn this paper we consider the problem of learning an $\epsilon$-optimal policy for a discounted Markov Decision Process (MDP). Given an MDP with $S$ states, $A$ actions, the discount factor $\gamma \in (0,1)$, and an approximation threshold $\epsilon > 0$, we provide a model-free algorithm to learn an $\epsilon$-optimal policy with sample complexity $\tilde{O}(\frac{SA\ln(1/p)}{\epsilon^2(1-\gamma)^{5.5}})$ \footnote{In this work, the notation $\tilde{O}(\cdot)$ hides poly-logarithmic factors of $S,A,1/(1-\gamma)$, and $1/\epsilon$.} and success probability $(1-p)$. For small enough $\epsilon$, we show an improved algorithm with sample complexity $\tilde{O}(\frac{SA\ln(1/p)}{\epsilon^2(1-\gamma)^{3}})$. While the first bound improves upon all known model-free algorithms and model-based ones with tight dependence on $S$, our second algorithm beats all known sample complexity bounds and matches the information theoretic lower bound up to logarithmic factors.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/zhang21ab.html
http://proceedings.mlr.press/v139/zhang21ab.htmlMeta Learning for Support Recovery in High-dimensional Precision Matrix EstimationIn this paper, we study meta learning for support (i.e., the set of non-zero entries) recovery in high-dimensional precision matrix estimation where we reduce the sufficient sample complexity in a novel task with the information learned from other auxiliary tasks. In our setup, each task has a different random true precision matrix, each with a possibly different support. We assume that the union of the supports of all the true precision matrices (i.e., the true support union) is small in size. We propose to pool all the samples from different tasks, and \emph{improperly} estimate a single precision matrix by minimizing the $\ell_1$-regularized log-determinant Bregman divergence. We show that with high probability, the support of the \emph{improperly} estimated single precision matrix is equal to the true support union, provided a sufficient number of samples per task $n \in O((\log N)/K)$, for $N$-dimensional vectors and $K$ tasks. That is, one requires less samples per task when more tasks are available. We prove a matching information-theoretic lower bound for the necessary number of samples, which is $n \in \Omega((\log N)/K)$, and thus, our algorithm is minimax optimal. Then for the novel task, we prove that the minimization of the $\ell_1$-regularized log-determinant Bregman divergence with the additional constraint that the support is a subset of the estimated support union could reduce the sufficient sample complexity of successful support recovery to $O(\log(|S_{\text{off}}|))$ where $|S_{\text{off}}|$ is the number of off-diagonal elements in the support union and is much less than $N$ for sparse matrices. We also prove a matching information-theoretic lower bound of $\Omega(\log(|S_{\text{off}}|))$ for the necessary number of samples.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/zhang21aa.html
http://proceedings.mlr.press/v139/zhang21aa.htmlCan Subnetwork Structure Be the Key to Out-of-Distribution Generalization?Can models with particular structure avoid being biased towards spurious correlation in out-of-distribution (OOD) generalization? Peters et al. (2016) provides a positive answer for linear cases. In this paper, we use a functional modular probing method to analyze deep model structures under OOD setting. We demonstrate that even in biased models (which focus on spurious correlation) there still exist unbiased functional subnetworks. Furthermore, we articulate and confirm the functional lottery ticket hypothesis: the full network contains a subnetwork with proper structure that can achieve better OOD performance. We then propose Modular Risk Minimization to solve the subnetwork selection problem. Our algorithm learns the functional structure from a given dataset, and can be combined with any other OOD regularization methods. Experiments on various OOD generalization tasks corroborate the effectiveness of our method.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/zhang21a.html
http://proceedings.mlr.press/v139/zhang21a.htmlDORO: Distributional and Outlier Robust OptimizationMany machine learning tasks involve subpopulation shift where the testing data distribution is a subpopulation of the training distribution. For such settings, a line of recent work has proposed the use of a variant of empirical risk minimization(ERM) known as distributionally robust optimization (DRO). In this work, we apply DRO to real, large-scale tasks with subpopulation shift, and observe that DRO performs relatively poorly, and moreover has severe instability. We identify one direct cause of this phenomenon: sensitivity of DRO to outliers in the datasets. To resolve this issue, we propose the framework of DORO, for Distributional and Outlier Robust Optimization. At the core of this approach is a refined risk function which prevents DRO from overfitting to potential outliers. We instantiate DORO for the Cressie-Read family of Rényi divergence, and delve into two specific instances of this family: CVaR and $\chi^2$-DRO. We theoretically prove the effectiveness of the proposed method, and empirically show that DORO improves the performance and stability of DRO with experiments on large modern datasets, thereby positively addressing the open question raised by Hashimoto et al., 2018. Codes are available at https://github.com/RuntianZ/doro.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/zhai21a.html
http://proceedings.mlr.press/v139/zhai21a.htmlDouZero: Mastering DouDizhu with Self-Play Deep Reinforcement LearningGames are abstractions of the real world, where artificial agents learn to compete and cooperate with other agents. While significant achievements have been made in various perfect- and imperfect-information games, DouDizhu (a.k.a. Fighting the Landlord), a three-player card game, is still unsolved. DouDizhu is a very challenging domain with competition, collaboration, imperfect information, large state space, and particularly a massive set of possible actions where the legal actions vary significantly from turn to turn. Unfortunately, modern reinforcement learning algorithms mainly focus on simple and small action spaces, and not surprisingly, are shown not to make satisfactory progress in DouDizhu. In this work, we propose a conceptually simple yet effective DouDizhu AI system, namely DouZero, which enhances traditional Monte-Carlo methods with deep neural networks, action encoding, and parallel actors. Starting from scratch in a single server with four GPUs, DouZero outperformed all the existing DouDizhu AI programs in days of training and was ranked the first in the Botzone leaderboard among 344 AI agents. Through building DouZero, we show that classic Monte-Carlo methods can be made to deliver strong results in a hard domain with a complex action space. The code and an online demo are released at https://github.com/kwai/DouZero with the hope that this insight could motivate future work.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/zha21a.html
http://proceedings.mlr.press/v139/zha21a.htmlYou Only Sample (Almost) Once: Linear Cost Self-Attention Via Bernoulli SamplingTransformer-based models are widely used in natural language processing (NLP). Central to the transformer model is the self-attention mechanism, which captures the interactions of token pairs in the input sequences and depends quadratically on the sequence length. Training such models on longer sequences is expensive. In this paper, we show that a Bernoulli sampling attention mechanism based on Locality Sensitive Hashing (LSH), decreases the quadratic complexity of such models to linear. We bypass the quadratic cost by considering self-attention as a sum of individual tokens associated with Bernoulli random variables that can, in principle, be sampled at once by a single hash (although in practice, this number may be a small constant). This leads to an efficient sampling scheme to estimate self-attention which relies on specific modifications of LSH (to enable deployment on GPU architectures). We evaluate our algorithm on the GLUE benchmark with standard 512 sequence length where we see favorable performance relative to a standard pretrained Transformer. On the Long Range Arena (LRA) benchmark, for evaluating performance on long sequences, our method achieves results consistent with softmax self-attention but with sizable speed-ups and memory savings and often outperforms other efficient self-attention methods. Our code is available at https://github.com/mlpen/YOSO.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/zeng21a.html
http://proceedings.mlr.press/v139/zeng21a.htmlBarlow Twins: Self-Supervised Learning via Redundancy ReductionSelf-supervised learning (SSL) is rapidly closing the gap with supervised methods on large computer vision benchmarks. A successful approach to SSL is to learn embeddings which are invariant to distortions of the input sample. However, a recurring issue with this approach is the existence of trivial constant solutions. Most current methods avoid such solutions by careful implementation details. We propose an objective function that naturally avoids collapse by measuring the cross-correlation matrix between the outputs of two identical networks fed with distorted versions of a sample, and making it as close to the identity matrix as possible. This causes the embedding vectors of distorted versions of a sample to be similar, while minimizing the redundancy between the components of these vectors. The method is called Barlow Twins, owing to neuroscientist H. Barlow’s redundancy-reduction principle applied to a pair of identical networks. Barlow Twins does not require large batches nor asymmetry between the network twins such as a predictor network, gradient stopping, or a moving average on the weight updates. Intriguingly it benefits from very high-dimensional output vectors. Barlow Twins outperforms previous methods on ImageNet for semi-supervised classification in the low-data regime, and is on par with current state of the art for ImageNet classification with a linear classifier head, and for transfer tasks of classification and object detection.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/zbontar21a.html
http://proceedings.mlr.press/v139/zbontar21a.htmlLearning Binary Decision Trees by Argmin DifferentiationWe address the problem of learning binary decision trees that partition data for some downstream task. We propose to learn discrete parameters (i.e., for tree traversals and node pruning) and continuous parameters (i.e., for tree split functions and prediction functions) simultaneously using argmin differentiation. We do so by sparsely relaxing a mixed-integer program for the discrete parameters, to allow gradients to pass through the program to continuous parameters. We derive customized algorithms to efficiently compute the forward and backward passes. This means that our tree learning procedure can be used as an (implicit) layer in arbitrary deep networks, and can be optimized with arbitrary loss functions. We demonstrate that our approach produces binary trees that are competitive with existing single tree and ensemble approaches, in both supervised and unsupervised settings. Further, apart from greedy approaches (which do not have competitive accuracies), our method is faster to train than all other tree-learning baselines we compare with.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/zantedeschi21a.html
http://proceedings.mlr.press/v139/zantedeschi21a.htmlExponential Lower Bounds for Batch Reinforcement Learning: Batch RL can be Exponentially Harder than Online RLSeveral practical applications of reinforcement learning involve an agent learning from past data without the possibility of further exploration. Often these applications require us to 1) identify a near optimal policy or to 2) estimate the value of a target policy. For both tasks we derive exponential information-theoretic lower bounds in discounted infinite horizon MDPs with a linear function representation for the action value function even if 1) realizability holds, 2) the batch algorithm observes the exact reward and transition functions, and 3) the batch algorithm is given the best a priori data distribution for the problem class. Our work introduces a new ‘oracle + batch algorithm’ framework to prove lower bounds that hold for every distribution. The work shows an exponential separation between batch and online reinforcement learning.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/zanette21a.html
http://proceedings.mlr.press/v139/zanette21a.htmlGrey-box Extraction of Natural Language ModelsModel extraction attacks attempt to replicate a target machine learning model by querying its inference API. State-of-the-art attacks are learning-based and construct replicas by supervised training on the target model’s predictions, but an emerging class of attacks exploit algebraic properties to obtain high-fidelity replicas using orders of magnitude fewer queries. So far, these algebraic attacks have been limited to neural networks with few hidden layers and ReLU activations. In this paper we present algebraic and hybrid algebraic/learning-based attacks on large-scale natural language models. We consider a grey-box setting, targeting models with a pre-trained (public) encoder followed by a single (private) classification layer. Our key findings are that (i) with a frozen encoder, high-fidelity extraction is possible with a small number of in-distribution queries, making extraction attacks indistinguishable from legitimate use; (ii) when the encoder is fine-tuned, a hybrid learning-based/algebraic attack improves over the learning-based state-of-the-art without requiring additional queries.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/zanella-beguelin21a.html
http://proceedings.mlr.press/v139/zanella-beguelin21a.htmlThree Operator Splitting with a Nonconvex Loss FunctionWe consider the problem of minimizing the sum of three functions, one of which is nonconvex but differentiable, and the other two are convex but possibly nondifferentiable. We investigate the Three Operator Splitting method (TOS) of Davis & Yin (2017) with an aim to extend its theoretical guarantees for this nonconvex problem template. In particular, we prove convergence of TOS with nonasymptotic bounds on its nonstationarity and infeasibility errors. In contrast with the existing work on nonconvex TOS, our guarantees do not require additional smoothness assumptions on the terms comprising the objective; hence they cover instances of particular interest where the nondifferentiable terms are indicator functions. We also extend our results to a stochastic setting where we have access only to an unbiased estimator of the gradient. Finally, we illustrate the effectiveness of the proposed method through numerical experiments on quadratic assignment problems.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/yurtsever21a.html
http://proceedings.mlr.press/v139/yurtsever21a.htmlFederated Composite OptimizationFederated Learning (FL) is a distributed learning paradigm that scales on-device learning collaboratively and privately. Standard FL algorithms such as FEDAVG are primarily geared towards smooth unconstrained settings. In this paper, we study the Federated Composite Optimization (FCO) problem, in which the loss function contains a non-smooth regularizer. Such problems arise naturally in FL applications that involve sparsity, low-rank, monotonicity, or more general constraints. We first show that straightforward extensions of primal algorithms such as FedAvg are not well-suited for FCO since they suffer from the "curse of primal averaging," resulting in poor convergence. As a solution, we propose a new primal-dual algorithm, Federated Dual Averaging (FedDualAvg), which by employing a novel server dual averaging procedure circumvents the curse of primal averaging. Our theoretical analysis and empirical experiments demonstrate that FedDualAvg outperforms the other baselines.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/yuan21d.html
http://proceedings.mlr.press/v139/yuan21d.htmlOn Explainability of Graph Neural Networks via Subgraph ExplorationsWe consider the problem of explaining the predictions of graph neural networks (GNNs), which otherwise are considered as black boxes. Existing methods invariably focus on explaining the importance of graph nodes or edges but ignore the substructures of graphs, which are more intuitive and human-intelligible. In this work, we propose a novel method, known as SubgraphX, to explain GNNs by identifying important subgraphs. Given a trained GNN model and an input graph, our SubgraphX explains its predictions by efficiently exploring different subgraphs with Monte Carlo tree search. To make the tree search more effective, we propose to use Shapley values as a measure of subgraph importance, which can also capture the interactions among different subgraphs. To expedite computations, we propose efficient approximation schemes to compute Shapley values for graph data. Our work represents the first attempt to explain GNNs via identifying subgraphs explicitly and directly. Experimental results show that our SubgraphX achieves significantly improved explanations, while keeping computations at a reasonable level.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/yuan21c.html
http://proceedings.mlr.press/v139/yuan21c.htmlNeural Tangent Generalization AttacksThe remarkable performance achieved by Deep Neural Networks (DNNs) in many applications is followed by the rising concern about data privacy and security. Since DNNs usually require large datasets to train, many practitioners scrape data from external sources such as the Internet. However, an external data owner may not be willing to let this happen, causing legal or ethical issues. In this paper, we study the generalization attacks against DNNs, where an attacker aims to slightly modify training data in order to spoil the training process such that a trained network lacks generalizability. These attacks can be performed by data owners and protect data from unexpected use. However, there is currently no efficient generalization attack against DNNs due to the complexity of a bilevel optimization involved. We propose the Neural Tangent Generalization Attack (NTGA) that, to the best of our knowledge, is the first work enabling clean-label, black-box generalization attack against DNNs. We conduct extensive experiments, and the empirical results demonstrate the effectiveness of NTGA. Our code and perturbed datasets are available at: https://github.com/lionelmessi6410/ntga.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/yuan21b.html
http://proceedings.mlr.press/v139/yuan21b.htmlFederated Deep AUC Maximization for Hetergeneous Data with a Constant Communication ComplexityDeep AUC (area under the ROC curve) Maximization (DAM) has attracted much attention recently due to its great potential for imbalanced data classification. However, the research on Federated Deep AUC Maximization (FDAM) is still limited. Compared with standard federated learning (FL) approaches that focus on decomposable minimization objectives, FDAM is more complicated due to its minimization objective is non-decomposable over individual examples. In this paper, we propose improved FDAM algorithms for heterogeneous data by solving the popular non-convex strongly-concave min-max formulation of DAM in a distributed fashion, which can also be applied to a class of non-convex strongly-concave min-max problems. A striking result of this paper is that the communication complexity of the proposed algorithm is a constant independent of the number of machines and also independent of the accuracy level, which improves an existing result by orders of magnitude. The experiments have demonstrated the effectiveness of our FDAM algorithm on benchmark datasets, and on medical chest X-ray images from different organizations. Our experiment shows that the performance of FDAM using data from multiple hospitals can improve the AUC score on testing data from a single hospital for detecting life-threatening diseases based on chest radiographs.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/yuan21a.html
http://proceedings.mlr.press/v139/yuan21a.htmlLarge Scale Private Learning via Low-rank ReparametrizationWe propose a reparametrization scheme to address the challenges of applying differentially private SGD on large neural networks, which are 1) the huge memory cost of storing individual gradients, 2) the added noise suffering notorious dimensional dependence. Specifically, we reparametrize each weight matrix with two \emph{gradient-carrier} matrices of small dimension and a \emph{residual weight} matrix. We argue that such reparametrization keeps the forward/backward process unchanged while enabling us to compute the projected gradient without computing the gradient itself. To learn with differential privacy, we design \emph{reparametrized gradient perturbation (RGP)} that perturbs the gradients on gradient-carrier matrices and reconstructs an update for the original weight from the noisy gradients. Importantly, we use historical updates to find the gradient-carrier matrices, whose optimality is rigorously justified under linear regression and empirically verified with deep learning tasks. RGP significantly reduces the memory cost and improves the utility. For example, we are the first able to apply differential privacy on the BERT model and achieve an average accuracy of $83.9%$ on four downstream tasks with $\epsilon=8$, which is within $5%$ loss compared to the non-private baseline but enjoys much lower privacy leakage risk.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/yu21f.html
http://proceedings.mlr.press/v139/yu21f.htmlLearning Generalized Intersection Over Union for Dense Pixelwise PredictionIntersection over union (IoU) score, also named Jaccard Index, is one of the most fundamental evaluation methods in machine learning. The original IoU computation cannot provide non-zero gradients and thus cannot be directly optimized by nowadays deep learning methods. Several recent works generalized IoU for bounding box regression, but they are not straightforward to adapt for pixelwise prediction. In particular, the original IoU fails to provide effective gradients for the non-overlapping and location-deviation cases, which results in performance plateau. In this paper, we propose PixIoU, a generalized IoU for pixelwise prediction that is sensitive to the distance for non-overlapping cases and the locations in prediction. We provide proofs that PixIoU holds many nice properties as the original IoU. To optimize the PixIoU, we also propose a loss function that is proved to be submodular, hence we can apply the Lovász functions, the efficient surrogates for submodular functions for learning this loss. Experimental results show consistent performance improvements by learning PixIoU over the original IoU for several different pixelwise prediction tasks on Pascal VOC, VOT-2020 and Cityscapes.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/yu21e.html
http://proceedings.mlr.press/v139/yu21e.htmlDeep Latent Graph MatchingDeep learning for graph matching (GM) has emerged as an important research topic due to its superior performance over traditional methods and insights it provides for solving other combinatorial problems on graph. While recent deep methods for GM extensively investigated effective node/edge feature learning or downstream GM solvers given such learned features, there is little existing work questioning if the fixed connectivity/topology typically constructed using heuristics (e.g., Delaunay or k-nearest) is indeed suitable for GM. From a learning perspective, we argue that the fixed topology may restrict the model capacity and thus potentially hinder the performance. To address this, we propose to learn the (distribution of) latent topology, which can better support the downstream GM task. We devise two latent graph generation procedures, one deterministic and one generative. Particularly, the generative procedure emphasizes the across-graph consistency and thus can be viewed as a matching-guided co-generative model. Our methods deliver superior performance over previous state-of-the-arts on public benchmarks, hence supporting our hypothesis.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/yu21d.html
http://proceedings.mlr.press/v139/yu21d.htmlWhittle Networks: A Deep Likelihood Model for Time SeriesWhile probabilistic circuits have been extensively explored for tabular data, less attention has been paid to time series. Here, the goal is to estimate joint densities among the entire time series and, in turn, determining, for instance, conditional independence relations between them. To this end, we propose the first probabilistic circuits (PCs) approach for modeling the joint distribution of multivariate time series, called Whittle sum-product networks (WSPNs). WSPNs leverage the Whittle approximation, casting the likelihood in the frequency domain, and place a complex-valued sum-product network, the most prominent PC, over the frequencies. The conditional independence relations among the time series can then be determined efficiently in the spectral domain. Moreover, WSPNs can naturally be placed into the deep neural learning stack for time series, resulting in Whittle Networks, opening the likelihood toolbox for training deep neural models and inspecting their behaviour. Our experiments show that Whittle Networks can indeed capture complex dependencies between time series and provide a useful measure of uncertainty for neural networks.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/yu21c.html
http://proceedings.mlr.press/v139/yu21c.htmlProvably Efficient Algorithms for Multi-Objective Competitive RLWe study multi-objective reinforcement learning (RL) where an agent’s reward is represented as a vector. In settings where an agent competes against opponents, its performance is measured by the distance of its average return vector to a target set. We develop statistically and computationally efficient algorithms to approach the associated target set. Our results extend Blackwell’s approachability theorem \citep{blackwell1956analog} to tabular RL, where strategic exploration becomes essential. The algorithms presented are adaptive; their guarantees hold even without Blackwell’s approachability condition. If the opponents use fixed policies, we give an improved rate of approaching the target set while also tackling the more ambitious goal of simultaneously minimizing a scalar cost function. We discuss our analysis for this special case by relating our results to previous works on constrained RL. To our knowledge, this work provides the first provably efficient algorithms for vector-valued Markov games and our theoretical guarantees are near-optimal.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/yu21b.html
http://proceedings.mlr.press/v139/yu21b.htmlDAGs with No Curl: An Efficient DAG Structure Learning ApproachRecently directed acyclic graph (DAG) structure learning is formulated as a constrained continuous optimization problem with continuous acyclicity constraints and was solved iteratively through subproblem optimization. To further improve efficiency, we propose a novel learning framework to model and learn the weighted adjacency matrices in the DAG space directly. Specifically, we first show that the set of weighted adjacency matrices of DAGs are equivalent to the set of weighted gradients of graph potential functions, and one may perform structure learning by searching in this equivalent set of DAGs. To instantiate this idea, we propose a new algorithm, DAG-NoCurl, which solves the optimization problem efficiently with a two-step procedure: $1)$ first we find an initial non-acyclic solution to the optimization problem, and $2)$ then we employ the Hodge decomposition of graphs and learn an acyclic graph by projecting the non-acyclic graph to the gradient of a potential function. Experimental studies on benchmark datasets demonstrate that our method provides comparable accuracy but better efficiency than baseline DAG structure learning methods on both linear and generalized structural equation models, often by more than one order of magnitude.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/yu21a.html
http://proceedings.mlr.press/v139/yu21a.htmlExponentially Many Local Minima in Quantum Neural NetworksQuantum Neural Networks (QNNs), or the so-called variational quantum circuits, are important quantum applications both because of their similar promises as classical neural networks and because of the feasibility of their implementation on near-term intermediate-size noisy quantum machines (NISQ). However, the training task of QNNs is challenging and much less understood. We conduct a quantitative investigation on the landscape of loss functions of QNNs and identify a class of simple yet extremely hard QNN instances for training. Specifically, we show for typical under-parameterized QNNs, there exists a dataset that induces a loss function with the number of spurious local minima depending exponentially on the number of parameters. Moreover, we show the optimality of our construction by providing an almost matching upper bound on such dependence. While local minima in classical neural networks are due to non-linear activations, in quantum neural networks local minima appear as a result of the quantum interference phenomenon. Finally, we empirically confirm that our constructions can indeed be hard instances in practice with typical gradient-based optimizers, which demonstrates the practical value of our findings.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/you21c.html
http://proceedings.mlr.press/v139/you21c.htmlLogME: Practical Assessment of Pre-trained Models for Transfer LearningThis paper studies task adaptive pre-trained model selection, an underexplored problem of assessing pre-trained models for the target task and select best ones from the model zoo \emph{without fine-tuning}. A few pilot works addressed the problem in transferring supervised pre-trained models to classification tasks, but they cannot handle emerging unsupervised pre-trained models or regression tasks. In pursuit of a practical assessment method, we propose to estimate the maximum value of label evidence given features extracted by pre-trained models. Unlike the maximum likelihood, the maximum evidence is \emph{immune to over-fitting}, while its expensive computation can be dramatically reduced by our carefully designed algorithm. The Logarithm of Maximum Evidence (LogME) can be used to assess pre-trained models for transfer learning: a pre-trained model with a high LogME value is likely to have good transfer performance. LogME is \emph{fast, accurate, and general}, characterizing itself as the first practical method for assessing pre-trained models. Compared with brute-force fine-tuning, LogME brings at most $3000\times$ speedup in wall-clock time and requires only $1%$ memory footprint. It outperforms prior methods by a large margin in their setting and is applicable to new settings. It is general enough for diverse pre-trained models (supervised pre-trained and unsupervised pre-trained), downstream tasks (classification and regression), and modalities (vision and language). Code is available at this repository: \href{https://github.com/thuml/LogME}{https://github.com/thuml/LogME}.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/you21b.html
http://proceedings.mlr.press/v139/you21b.htmlGraph Contrastive Learning AutomatedSelf-supervised learning on graph-structured data has drawn recent interest for learning generalizable, transferable and robust representations from unlabeled graphs. Among many, graph contrastive learning (GraphCL) has emerged with promising representation learning performance. Unfortunately, unlike its counterpart on image data, the effectiveness of GraphCL hinges on ad-hoc data augmentations, which have to be manually picked per dataset, by either rules of thumb or trial-and-errors, owing to the diverse nature of graph data. That significantly limits the more general applicability of GraphCL. Aiming to fill in this crucial gap, this paper proposes a unified bi-level optimization framework to automatically, adaptively and dynamically select data augmentations when performing GraphCL on specific graph data. The general framework, dubbed JOint Augmentation Optimization (JOAO), is instantiated as min-max optimization. The selections of augmentations made by JOAO are shown to be in general aligned with previous "best practices" observed from handcrafted tuning: yet now being automated, more flexible and versatile. Moreover, we propose a new augmentation-aware projection head mechanism, which will route output features through different projection heads corresponding to different augmentations chosen at each training step. Extensive experiments demonstrate that JOAO performs on par with or sometimes better than the state-of-the-art competitors including GraphCL, on multiple graph datasets of various scales and types, yet without resorting to any laborious dataset-specific tuning on augmentation selection. We release the code at https://github.com/Shen-Lab/GraphCL_Automated.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/you21a.html
http://proceedings.mlr.press/v139/you21a.htmlLower-Bounded Proper Losses for Weakly Supervised ClassificationThis paper discusses the problem of weakly supervised classification, in which instances are given weak labels that are produced by some label-corruption process. The goal is to derive conditions under which loss functions for weak-label learning are proper and lower-bounded—two essential requirements for the losses used in class-probability estimation. To this end, we derive a representation theorem for proper losses in supervised learning, which dualizes the Savage representation. We use this theorem to characterize proper weak-label losses and find a condition for them to be lower-bounded. From these theoretical findings, we derive a novel regularization scheme called generalized logit squeezing, which makes any proper weak-label loss bounded from below, without losing properness. Furthermore, we experimentally demonstrate the effectiveness of our proposed approach, as compared to improper or unbounded losses. The results highlight the importance of properness and lower-boundedness.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/yoshida21a.html
http://proceedings.mlr.press/v139/yoshida21a.htmlAccelerated Algorithms for Smooth Convex-Concave Minimax Problems with O(1/k^2) Rate on Squared Gradient NormIn this work, we study the computational complexity of reducing the squared gradient magnitude for smooth minimax optimization problems. First, we present algorithms with accelerated $\mathcal{O}(1/k^2)$ last-iterate rates, faster than the existing $\mathcal{O}(1/k)$ or slower rates for extragradient, Popov, and gradient descent with anchoring. The acceleration mechanism combines extragradient steps with anchoring and is distinct from Nesterov’s acceleration. We then establish optimality of the $\mathcal{O}(1/k^2)$ rate through a matching lower bound.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/yoon21d.html
http://proceedings.mlr.press/v139/yoon21d.htmlAutoencoding Under Normalization ConstraintsLikelihood is a standard estimate for outlier detection. The specific role of the normalization constraint is to ensure that the out-of-distribution (OOD) regime has a small likelihood when samples are learned using maximum likelihood. Because autoencoders do not possess such a process of normalization, they often fail to recognize outliers even when they are obviously OOD. We propose the Normalized Autoencoder (NAE), a normalized probabilistic model constructed from an autoencoder. The probability density of NAE is defined using the reconstruction error of an autoencoder, which is differently defined in the conventional energy-based model. In our model, normalization is enforced by suppressing the reconstruction of negative samples, significantly improving the outlier detection performance. Our experimental results confirm the efficacy of NAE, both in detecting outliers and in generating in-distribution samples.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/yoon21c.html
http://proceedings.mlr.press/v139/yoon21c.htmlFederated Continual Learning with Weighted Inter-client TransferThere has been a surge of interest in continual learning and federated learning, both of which are important in deep neural networks in real-world scenarios. Yet little research has been done regarding the scenario where each client learns on a sequence of tasks from a private local data stream. This problem of federated continual learning poses new challenges to continual learning, such as utilizing knowledge from other clients, while preventing interference from irrelevant knowledge. To resolve these issues, we propose a novel federated continual learning framework, Federated Weighted Inter-client Transfer (FedWeIT), which decomposes the network weights into global federated parameters and sparse task-specific parameters, and each client receives selective knowledge from other clients by taking a weighted combination of their task-specific parameters. FedWeIT minimizes interference between incompatible tasks, and also allows positive knowledge transfer across clients during learning. We validate our FedWeIT against existing federated learning and continual learning methods under varying degrees of task similarity across clients, and our model significantly outperforms them with a large reduction in the communication cost.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/yoon21b.html
http://proceedings.mlr.press/v139/yoon21b.htmlAdversarial Purification with Score-based Generative ModelsWhile adversarial training is considered as a standard defense method against adversarial attacks for image classifiers, adversarial purification, which purifies attacked images into clean images with a standalone purification, model has shown promises as an alternative defense method. Recently, an EBM trained with MCMC has been highlighted as a purification model, where an attacked image is purified by running a long Markov-chain using the gradients of the EBM. Yet, the practicality of the adversarial purification using an EBM remains questionable because the number of MCMC steps required for such purification is too large. In this paper, we propose a novel adversarial purification method based on an EBM trained with DSM. We show that an EBM trained with DSM can quickly purify attacked images within a few steps. We further introduce a simple yet effective randomized purification scheme that injects random noises into images before purification. This process screens the adversarial perturbations imposed on images by the random noises and brings the images to the regime where the EBM can denoise well. We show that our purification method is robust against various attacks and demonstrate its state-of-the-art performances.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/yoon21a.html
http://proceedings.mlr.press/v139/yoon21a.htmlConditional Temporal Neural Processes with Covariance LossWe introduce a novel loss function, Covariance Loss, which is conceptually equivalent to conditional neural processes and has a form of regularization so that is applicable to many kinds of neural networks. With the proposed loss, mappings from input variables to target variables are highly affected by dependencies of target variables as well as mean activation and mean dependencies of input and target variables. This nature enables the resulting neural networks to become more robust to noisy observations and recapture missing dependencies from prior information. In order to show the validity of the proposed loss, we conduct extensive sets of experiments on real-world datasets with state-of-the-art models and discuss the benefits and drawbacks of the proposed Covariance Loss.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/yoo21b.html
http://proceedings.mlr.press/v139/yoo21b.htmlSinIR: Efficient General Image Manipulation with Single Image ReconstructionWe propose SinIR, an efficient reconstruction-based framework trained on a single natural image for general image manipulation, including super-resolution, editing, harmonization, paint-to-image, photo-realistic style transfer, and artistic style transfer. We train our model on a single image with cascaded multi-scale learning, where each network at each scale is responsible for image reconstruction. This reconstruction objective greatly reduces the complexity and running time of training, compared to the GAN objective. However, the reconstruction objective also exacerbates the output quality. Therefore, to solve this problem, we further utilize simple random pixel shuffling, which also gives control over manipulation, inspired by the Denoising Autoencoder. With quantitative evaluation, we show that SinIR has competitive performance on various image manipulation tasks. Moreover, with a much simpler training objective (i.e., reconstruction), SinIR is trained 33.5 times faster than SinGAN (for 500x500 images) that solves similar tasks. Our code is publicly available at github.com/YooJiHyeong/SinIR.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/yoo21a.html
http://proceedings.mlr.press/v139/yoo21a.htmlPath Planning using Neural A* SearchWe present Neural A*, a novel data-driven search method for path planning problems. Despite the recent increasing attention to data-driven path planning, machine learning approaches to search-based planning are still challenging due to the discrete nature of search algorithms. In this work, we reformulate a canonical A* search algorithm to be differentiable and couple it with a convolutional encoder to form an end-to-end trainable neural network planner. Neural A* solves a path planning problem by encoding a problem instance to a guidance map and then performing the differentiable A* search with the guidance map. By learning to match the search results with ground-truth paths provided by experts, Neural A* can produce a path consistent with the ground truth accurately and efficiently. Our extensive experiments confirmed that Neural A* outperformed state-of-the-art data-driven planners in terms of the search optimality and efficiency trade-off. Furthermore, Neural A* successfully predicted realistic human trajectories by directly performing search-based planning on natural image inputs.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/yonetani21a.html
http://proceedings.mlr.press/v139/yonetani21a.htmlDistributed Nyström Kernel Learning with CommunicationsWe study the statistical performance for distributed kernel ridge regression with Nyström (DKRR-NY) and with Nyström and iterative solvers (DKRR-NY-PCG) and successfully derive the optimal learning rates, which can improve the ranges of the number of local processors $p$ to the optimal in existing state-of-art bounds. More precisely, our theoretical analysis show that DKRR-NY and DKRR-NY-PCG achieve the same learning rates as the exact KRR requiring essentially $\mathcal{O}(|D|^{1.5})$ time and $\mathcal{O}(|D|)$ memory with relaxing the restriction on $p$ in expectation, where $|D|$ is the number of data, which exhibits the average effectiveness of multiple trials. Furthermore, for showing the generalization performance in a single trial, we deduce the learning rates for DKRR-NY and DKRR-NY-PCG in probability. Finally, we propose a novel algorithm DKRR-NY-CM based on DKRR-NY, which employs a communication strategy to further improve the learning performance, whose effectiveness of communications is validated in theoretical and experimental analysis.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/yin21a.html
http://proceedings.mlr.press/v139/yin21a.htmlContinuous-time Model-based Reinforcement LearningModel-based reinforcement learning (MBRL) approaches rely on discrete-time state transition models whereas physical systems and the vast majority of control tasks operate in continuous-time. To avoid time-discretization approximation of the underlying process, we propose a continuous-time MBRL framework based on a novel actor-critic method. Our approach also infers the unknown state evolution differentials with Bayesian neural ordinary differential equations (ODE) to account for epistemic uncertainty. We implement and test our method on a new ODE-RL suite that explicitly solves continuous-time control systems. Our experiments illustrate that the model is robust against irregular and noisy data, and can solve classic control problems in a sample-efficient manner.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/yildiz21a.html
http://proceedings.mlr.press/v139/yildiz21a.htmlRegret and Cumulative Constraint Violation Analysis for Online Convex Optimization with Long Term ConstraintsThis paper considers online convex optimization with long term constraints, where constraints can be violated in intermediate rounds, but need to be satisfied in the long run. The cumulative constraint violation is used as the metric to measure constraint violations, which excludes the situation that strictly feasible constraints can compensate the effects of violated constraints. A novel algorithm is first proposed and it achieves an $\mathcal{O}(T^{\max\{c,1-c\}})$ bound for static regret and an $\mathcal{O}(T^{(1-c)/2})$ bound for cumulative constraint violation, where $c\in(0,1)$ is a user-defined trade-off parameter, and thus has improved performance compared with existing results. Both static regret and cumulative constraint violation bounds are reduced to $\mathcal{O}(\log(T))$ when the loss functions are strongly convex, which also improves existing results. %In order to bound the regret with respect to any comparator sequence, In order to achieve the optimal regret with respect to any comparator sequence, another algorithm is then proposed and it achieves the optimal $\mathcal{O}(\sqrt{T(1+P_T)})$ regret and an $\mathcal{O}(\sqrt{T})$ cumulative constraint violation, where $P_T$ is the path-length of the comparator sequence. Finally, numerical simulations are provided to illustrate the effectiveness of the theoretical results.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/yi21b.html
http://proceedings.mlr.press/v139/yi21b.htmlImproved OOD Generalization via Adversarial Training and PretraingRecently, learning a model that generalizes well on out-of-distribution (OOD) data has attracted great attention in the machine learning community. In this paper, after defining OOD generalization by Wasserstein distance, we theoretically justify that a model robust to input perturbation also generalizes well on OOD data. Inspired by previous findings that adversarial training helps improve robustness, we show that models trained by adversarial training have converged excess risk on OOD data. Besides, in the paradigm of pre-training then fine-tuning, we theoretically justify that the input perturbation robust model in the pre-training stage provides an initialization that generalizes well on downstream OOD data. Finally, various experiments conducted on image classification and natural language understanding tasks verify our theoretical findings.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/yi21a.html
http://proceedings.mlr.press/v139/yi21a.htmlFrom Local Structures to Size Generalization in Graph Neural NetworksGraph neural networks (GNNs) can process graphs of different sizes, but their ability to generalize across sizes, specifically from small to large graphs, is still not well understood. In this paper, we identify an important type of data where generalization from small to large graphs is challenging: graph distributions for which the local structure depends on the graph size. This effect occurs in multiple important graph learning domains, including social and biological networks. We first prove that when there is a difference between the local structures, GNNs are not guaranteed to generalize across sizes: there are "bad" global minima that do well on small graphs but fail on large graphs. We then study the size-generalization problem empirically and demonstrate that when there is a discrepancy in local structure, GNNs tend to converge to non-generalizing solutions. Finally, we suggest two approaches for improving size generalization, motivated by our findings. Notably, we propose a novel Self-Supervised Learning (SSL) task aimed at learning meaningful representations of local structures that appear in large graphs. Our SSL task improves classification accuracy on several popular datasets.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/yehudai21a.html
http://proceedings.mlr.press/v139/yehudai21a.htmlNeighborhood Contrastive Learning Applied to Online Patient MonitoringIntensive care units (ICU) are increasingly looking towards machine learning for methods to provide online monitoring of critically ill patients. In machine learning, online monitoring is often formulated as a supervised learning problem. Recently, contrastive learning approaches have demonstrated promising improvements over competitive supervised benchmarks. These methods rely on well-understood data augmentation techniques developed for image data which do not apply to online monitoring. In this work, we overcome this limitation by supplementing time-series data augmentation techniques with a novel contrastive learning objective which we call neighborhood contrastive learning (NCL). Our objective explicitly groups together contiguous time segments from each patient while maintaining state-specific information. Our experiments demonstrate a marked improvement over existing work applying contrastive methods to medical time-series.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/yeche21a.html
http://proceedings.mlr.press/v139/yeche21a.htmlImproving Gradient Regularization using Complex-Valued Neural NetworksGradient regularization is a neural network defense technique that requires no prior knowledge of an adversarial attack and that brings only limited increase in training computational complexity. A form of complex-valued neural network (CVNN) is proposed to improve the performance of gradient regularization on classification tasks of real-valued input in adversarial settings. The activation derivatives of each layer of the CVNN are dependent on the combination of inputs to the layer, and locally stable representations can be learned for inputs the network is trained on. Furthermore, the properties of the CVNN parameter derivatives resist decrease of performance on the standard objective that is caused by competition with the gradient regularization objective. Experimental results show that the performance of gradient regularized CVNN surpasses that of real-valued neural networks with comparable storage and computational complexity. Moreover, gradient regularized complex-valued networks exhibit robust performance approaching that of real-valued networks trained with multi-step adversarial training.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/yeats21a.html
http://proceedings.mlr.press/v139/yeats21a.htmlBreak-It-Fix-It: Unsupervised Learning for Program RepairWe consider repair tasks: given a critic (e.g., compiler) that assesses the quality of an input, the goal is to train a fixer that converts a bad example (e.g., code with syntax errors) into a good one (e.g., code with no errors). Existing works create training data consisting of (bad, good) pairs by corrupting good examples using heuristics (e.g., dropping tokens). However, fixers trained on this synthetically-generated data do not extrapolate well to the real distribution of bad inputs. To bridge this gap, we propose a new training approach, Break-It-Fix-It (BIFI), which has two key ideas: (i) we use the critic to check a fixer’s output on real bad inputs and add good (fixed) outputs to the training data, and (ii) we train a breaker to generate realistic bad code from good code. Based on these ideas, we iteratively update the breaker and the fixer while using them in conjunction to generate more paired data. We evaluate BIFI on two code repair datasets: GitHub-Python, a new dataset we introduce where the goal is to repair Python code with AST parse errors; and DeepFix, where the goal is to repair C code with compiler errors. BIFI outperforms existing methods, obtaining 90.5% repair accuracy on GitHub-Python (+28.5%) and 71.7% on DeepFix (+5.6%). Notably, BIFI does not require any labeled data; we hope it will be a strong starting point for unsupervised learning of various repair tasks.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/yasunaga21a.html
http://proceedings.mlr.press/v139/yasunaga21a.htmlElementary superexpressive activationsWe call a finite family of activation functions \emph{superexpressive} if any multivariate continuous function can be approximated by a neural network that uses these activations and has a fixed architecture only depending on the number of input variables (i.e., to achieve any accuracy we only need to adjust the weights, without increasing the number of neurons). Previously, it was known that superexpressive activations exist, but their form was quite complex. We give examples of very simple superexpressive families: for example, we prove that the family $\{sin, arcsin\}$ is superexpressive. We also show that most practical activations (not involving periodic functions) are not superexpressive.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/yarotsky21a.html
http://proceedings.mlr.press/v139/yarotsky21a.htmlReinforcement Learning with Prototypical RepresentationsLearning effective representations in image-based environments is crucial for sample efficient Reinforcement Learning (RL). Unfortunately, in RL, representation learning is confounded with the exploratory experience of the agent – learning a useful representation requires diverse data, while effective exploration is only possible with coherent representations. Furthermore, we would like to learn representations that not only generalize across tasks but also accelerate downstream exploration for efficient task-specific training. To address these challenges we propose Proto-RL, a self-supervised framework that ties representation learning with exploration through prototypical representations. These prototypes simultaneously serve as a summarization of the exploratory experience of an agent as well as a basis for representing observations. We pre-train these task-agnostic representations and prototypes on environments without downstream task information. This enables state-of-the-art downstream policy learning on a set of difficult continuous control tasks.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/yarats21a.html
http://proceedings.mlr.press/v139/yarats21a.htmlAddressing Catastrophic Forgetting in Few-Shot ProblemsNeural networks are known to suffer from catastrophic forgetting when trained on sequential datasets. While there have been numerous attempts to solve this problem in large-scale supervised classification, little has been done to overcome catastrophic forgetting in few-shot classification problems. We demonstrate that the popular gradient-based model-agnostic meta-learning algorithm (MAML) indeed suffers from catastrophic forgetting and introduce a Bayesian online meta-learning framework that tackles this problem. Our framework utilises Bayesian online learning and meta-learning along with Laplace approximation and variational inference to overcome catastrophic forgetting in few-shot classification problems. The experimental evaluations demonstrate that our framework can effectively achieve this goal in comparison with various baselines. As an additional utility, we also demonstrate empirically that our framework is capable of meta-learning on sequentially arriving few-shot tasks from a stationary task distribution.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/yap21a.html
http://proceedings.mlr.press/v139/yap21a.htmlDeep Learning for Functional Data Analysis with Adaptive Basis LayersDespite their widespread success, the application of deep neural networks to functional data remains scarce today. The infinite dimensionality of functional data means standard learning algorithms can be applied only after appropriate dimension reduction, typically achieved via basis expansions. Currently, these bases are chosen a priori without the information for the task at hand and thus may not be effective for the designated task. We instead propose to adaptively learn these bases in an end-to-end fashion. We introduce neural networks that employ a new Basis Layer whose hidden units are each basis functions themselves implemented as a micro neural network. Our architecture learns to apply parsimonious dimension reduction to functional inputs that focuses only on information relevant to the target rather than irrelevant variation in the input function. Across numerous classification/regression tasks with functional data, our method empirically outperforms other types of neural networks, and we prove that our approach is statistically consistent with low generalization error.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/yao21c.html
http://proceedings.mlr.press/v139/yao21c.htmlImproving Generalization in Meta-learning via Task AugmentationMeta-learning has proven to be a powerful paradigm for transferring the knowledge from previous tasks to facilitate the learning of a novel task. Current dominant algorithms train a well-generalized model initialization which is adapted to each task via the support set. The crux lies in optimizing the generalization capability of the initialization, which is measured by the performance of the adapted model on the query set of each task. Unfortunately, this generalization measure, evidenced by empirical results, pushes the initialization to overfit the meta-training tasks, which significantly impairs the generalization and adaptation to novel tasks. To address this issue, we actively augment a meta-training task with “more data” when evaluating the generalization. Concretely, we propose two task augmentation methods, including MetaMix and Channel Shuffle. MetaMix linearly combines features and labels of samples from both the support and query sets. For each class of samples, Channel Shuffle randomly replaces a subset of their channels with the corresponding ones from a different class. Theoretical studies show how task augmentation improves the generalization of meta-learning. Moreover, both MetaMix and Channel Shuffle outperform state-of-the-art results by a large margin across many datasets and are compatible with existing meta-learning algorithms.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/yao21b.html
http://proceedings.mlr.press/v139/yao21b.htmlHAWQ-V3: Dyadic Neural Network QuantizationCurrent low-precision quantization algorithms often have the hidden cost of conversion back and forth from floating point to quantized integer values. This hidden cost limits the latency improvement realized by quantizing Neural Networks. To address this, we present HAWQ-V3, a novel mixed-precision integer-only quantization framework. The contributions of HAWQ-V3 are the following: (i) An integer-only inference where the entire computational graph is performed only with integer multiplication, addition, and bit shifting, without any floating point operations or even integer division; (ii) A novel hardware-aware mixed-precision quantization method where the bit-precision is calculated by solving an integer linear programming problem that balances the trade-off between model perturbation and other constraints, e.g., memory footprint and latency; (iii) Direct hardware deployment and open source contribution for 4-bit uniform/mixed-precision quantization in TVM, achieving an average speed up of 1.45x for uniform 4-bit, as compared to uniform 8-bit for ResNet50 on T4 GPUs; and (iv) extensive evaluation of the proposed methods on ResNet18/50 and InceptionV3, for various model compression levels with/without mixed precision. For ResNet50, our INT8 quantization achieves an accuracy of 77.58%, which is 2.68% higher than prior integer-only work, and our mixed-precision INT4/8 quantization can reduce INT8 latency by 23% and still achieve 76.73% accuracy. Our framework and the TVM implementation have been open sourced (HAWQ, 2020).Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/yao21a.html
http://proceedings.mlr.press/v139/yao21a.htmlSimAM: A Simple, Parameter-Free Attention Module for Convolutional Neural NetworksIn this paper, we propose a conceptually simple but very effective attention module for Convolutional Neural Networks (ConvNets). In contrast to existing channel-wise and spatial-wise attention modules, our module instead infers 3-D attention weights for the feature map in a layer without adding parameters to the original networks. Specifically, we base on some well-known neuroscience theories and propose to optimize an energy function to find the importance of each neuron. We further derive a fast closed-form solution for the energy function, and show that the solution can be implemented in less than ten lines of code. Another advantage of the module is that most of the operators are selected based on the solution to the defined energy function, avoiding too many efforts for structure tuning. Quantitative evaluations on various visual tasks demonstrate that the proposed module is flexible and effective to improve the representation ability of many ConvNets. Our code is available at Pytorch-SimAM.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/yang21o.html
http://proceedings.mlr.press/v139/yang21o.htmlBackpropagated Neighborhood Aggregation for Accurate Training of Spiking Neural NetworksWhile Backpropagation (BP) has been applied to spiking neural networks (SNNs) achieving encouraging results, a key challenge involved is to backpropagate a differentiable continuous-valued loss over layers of spiking neurons exhibiting discontinuous all-or-none firing activities. Existing methods deal with this difficulty by introducing compromises that come with their own limitations, leading to potential performance degradation. We propose a novel BP-like method, called neighborhood aggregation (NA), which computes accurate error gradients guiding weight updates that may lead to discontinuous modifications of firing activities. NA achieves this goal by aggregating the error gradient over multiple spike trains in the neighborhood of the present spike train of each neuron. The employed aggregation is based on a generalized finite difference approximation with a proposed distance metric quantifying the similarity between a given pair of spike trains. Our experiments show that the proposed NA algorithm delivers state-of-the-art performance for SNN training on several datasets including CIFAR10.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/yang21n.html
http://proceedings.mlr.press/v139/yang21n.htmlDelving into Deep Imbalanced RegressionReal-world data often exhibit imbalanced distributions, where certain target values have significantly fewer observations. Existing techniques for dealing with imbalanced data focus on targets with categorical indices, i.e., different classes. However, many tasks involve continuous targets, where hard boundaries between classes do not exist. We define Deep Imbalanced Regression (DIR) as learning from such imbalanced data with continuous targets, dealing with potential missing data for certain target values, and generalizing to the entire target range. Motivated by the intrinsic difference between categorical and continuous label space, we propose distribution smoothing for both labels and features, which explicitly acknowledges the effects of nearby targets, and calibrates both label and learned feature distributions. We curate and benchmark large-scale DIR datasets from common real-world tasks in computer vision, natural language processing, and healthcare domains. Extensive experiments verify the superior performance of our strategies. Our work fills the gap in benchmarks and techniques for practical imbalanced regression problems. Code and data are available at: https://github.com/YyzHarry/imbalanced-regression.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/yang21m.html
http://proceedings.mlr.press/v139/yang21m.htmlRethinking Rotated Object Detection with Gaussian Wasserstein Distance LossBoundary discontinuity and its inconsistency to the final detection metric have been the bottleneck for rotating detection regression loss design. In this paper, we propose a novel regression loss based on Gaussian Wasserstein distance as a fundamental approach to solve the problem. Specifically, the rotated bounding box is converted to a 2-D Gaussian distribution, which enables to approximate the indifferentiable rotational IoU induced loss by the Gaussian Wasserstein distance (GWD) which can be learned efficiently by gradient back-propagation. GWD can still be informative for learning even there is no overlapping between two rotating bounding boxes which is often the case for small object detection. Thanks to its three unique properties, GWD can also elegantly solve the boundary discontinuity and square-like problem regardless how the bounding box is defined. Experiments on five datasets using different detectors show the effectiveness of our approach, and codes are available at https://github.com/yangxue0827/RotationDetection.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/yang21l.html
http://proceedings.mlr.press/v139/yang21l.htmlWhen All We Need is a Piece of the Pie: A Generic Framework for Optimizing Two-way Partial AUCThe Area Under the ROC Curve (AUC) is a crucial metric for machine learning, which evaluates the average performance over all possible True Positive Rates (TPRs) and False Positive Rates (FPRs). Based on the knowledge that a skillful classifier should simultaneously embrace a high TPR and a low FPR, we turn to study a more general variant called Two-way Partial AUC (TPAUC), where only the region with $\mathsf{TPR} \ge \alpha, \mathsf{FPR} \le \beta$ is included in the area. Moreover, a recent work shows that the TPAUC is essentially inconsistent with the existing Partial AUC metrics where only the FPR range is restricted, opening a new problem to seek solutions to leverage high TPAUC. Motivated by this, we present the first trial in this paper to optimize this new metric. The critical challenge along this course lies in the difficulty of performing gradient-based optimization with end-to-end stochastic training, even with a proper choice of surrogate loss. To address this issue, we propose a generic framework to construct surrogate optimization problems, which supports efficient end-to-end training with deep-learning. Moreover, our theoretical analyses show that: 1) the objective function of the surrogate problems will achieve an upper bound of the original problem under mild conditions, and 2) optimizing the surrogate problems leads to good generalization performance in terms of TPAUC with a high probability. Finally, empirical studies over several benchmark datasets speak to the efficacy of our framework.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/yang21k.html
http://proceedings.mlr.press/v139/yang21k.htmlVoice2Series: Reprogramming Acoustic Models for Time Series ClassificationLearning to classify time series with limited data is a practical yet challenging problem. Current methods are primarily based on hand-designed feature extraction rules or domain-specific data augmentation. Motivated by the advances in deep speech processing models and the fact that voice data are univariate temporal signals, in this paper we propose Voice2Serie (V2S), a novel end-to-end approach that reprograms acoustic models for time series classification, through input transformation learning and output label mapping. Leveraging the representation learning power of a large-scale pre-trained speech processing model, on 31 different time series tasks we show that V2S outperforms or is on part with state-of-the-art methods on 22 tasks, and improves their average accuracy by 1.72%. We further provide theoretical justification of V2S by proving its population risk is upper bounded by the source risk and a Wasserstein distance accounting for feature alignment via reprogramming. Our results offer new and effective means to time series classification.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/yang21j.html
http://proceedings.mlr.press/v139/yang21j.htmlAccelerating Safe Reinforcement Learning with Constraint-mismatched Baseline PoliciesWe consider the problem of reinforcement learning when provided with (1) a baseline control policy and (2) a set of constraints that the learner must satisfy. The baseline policy can arise from demonstration data or a teacher agent and may provide useful cues for learning, but it might also be sub-optimal for the task at hand, and is not guaranteed to satisfy the specified constraints, which might encode safety, fairness or other application-specific requirements. In order to safely learn from baseline policies, we propose an iterative policy optimization algorithm that alternates between maximizing expected return on the task, minimizing distance to the baseline policy, and projecting the policy onto the constraint-satisfying set. We analyze our algorithm theoretically and provide a finite-time convergence guarantee. In our experiments on five different control tasks, our algorithm consistently outperforms several state-of-the-art baselines, achieving 10 times fewer constraint violations and 40% higher reward on average.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/yang21i.html
http://proceedings.mlr.press/v139/yang21i.htmlRepresentation Matters: Offline Pretraining for Sequential Decision MakingThe recent success of supervised learning methods on ever larger offline datasets has spurred interest in the reinforcement learning (RL) field to investigate whether the same paradigms can be translated to RL algorithms. This research area, known as offline RL, has largely focused on offline policy optimization, aiming to find a return-maximizing policy exclusively from offline data. In this paper, we consider a slightly different approach to incorporating offline data into sequential decision-making. We aim to answer the question, what unsupervised objectives applied to offline datasets are able to learn state representations which elevate performance on downstream tasks, whether those downstream tasks be online RL, imitation learning from expert demonstrations, or even offline policy optimization based on the same offline dataset? Through a variety of experiments utilizing standard offline RL datasets, we find that the use of pretraining with unsupervised learning objectives can dramatically improve the performance of policy learning algorithms that otherwise yield mediocre performance on their own. Extensive ablations further provide insights into what components of these unsupervised objectives {–} e.g., reward prediction, continuous or discrete representations, pretraining or finetuning {–} are most important and in which settings.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/yang21h.html
http://proceedings.mlr.press/v139/yang21h.htmlGraph Neural Networks Inspired by Classical Iterative AlgorithmsDespite the recent success of graph neural networks (GNN), common architectures often exhibit significant limitations, including sensitivity to oversmoothing, long-range dependencies, and spurious edges, e.g., as can occur as a result of graph heterophily or adversarial attacks. To at least partially address these issues within a simple transparent framework, we consider a new family of GNN layers designed to mimic and integrate the update rules of two classical iterative algorithms, namely, proximal gradient descent and iterative reweighted least squares (IRLS). The former defines an extensible base GNN architecture that is immune to oversmoothing while nonetheless capturing long-range dependencies by allowing arbitrary propagation steps. In contrast, the latter produces a novel attention mechanism that is explicitly anchored to an underlying end-to-end energy function, contributing stability with respect to edge uncertainty. When combined we obtain an extremely simple yet robust model that we evaluate across disparate scenarios including standardized benchmarks, adversarially-perturbated graphs, graphs with heterophily, and graphs involving long-range dependencies. In doing so, we compare against SOTA GNN approaches that have been explicitly designed for the respective task, achieving competitive or superior node classification accuracy. Our code is available at https://github.com/FFTYYY/TWIRLS. And for an extended version of this work, please see https://arxiv.org/abs/2103.06064.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/yang21g.html
http://proceedings.mlr.press/v139/yang21g.htmlTensor Programs IIb: Architectural Universality Of Neural Tangent Kernel Training DynamicsYang (2020) recently showed that the Neural Tangent Kernel (NTK) at initialization has an infinite-width limit for a large class of architectures including modern staples such as ResNet and Transformers. However, their analysis does not apply to training. Here, we show the same neural networks (in the so-called NTK parametrization) during training follow a kernel gradient descent dynamics in function space, where the kernel is the infinite-width NTK. This completes the proof of the architectural universality of NTK behavior. To achieve this result, we apply the Tensor Programs technique: Write the entire SGD dynamics inside a Tensor Program and analyze it via the Master Theorem. To facilitate this proof, we develop a graphical notation for Tensor Programs, which we believe is also an important contribution toward the pedagogy and exposition of the Tensor Programs technique.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/yang21f.html
http://proceedings.mlr.press/v139/yang21f.htmlBASGD: Buffered Asynchronous SGD for Byzantine LearningDistributed learning has become a hot research topic due to its wide application in cluster-based large-scale learning, federated learning, edge computing and so on. Most traditional distributed learning methods typically assume no failure or attack. However, many unexpected cases, such as communication failure and even malicious attack, may happen in real applications. Hence, Byzantine learning (BL), which refers to distributed learning with failure or attack, has recently attracted much attention. Most existing BL methods are synchronous, which are impractical in some applications due to heterogeneous or offline workers. In these cases, asynchronous BL (ABL) is usually preferred. In this paper, we propose a novel method, called buffered asynchronous stochastic gradient descent (BASGD), for ABL. To the best of our knowledge, BASGD is the first ABL method that can resist malicious attack without storing any instances on server. Compared with those methods which need to store instances on server, BASGD has a wider scope of application. BASGD is proved to be convergent, and be able to resist failure or attack. Empirical results show that BASGD significantly outperforms vanilla asynchronous stochastic gradient descent (ASGD) and other ABL baselines when there exists failure or attack on workers.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/yang21e.html
http://proceedings.mlr.press/v139/yang21e.htmlLARNet: Lie Algebra Residual Network for Face RecognitionFace recognition is an important yet challenging problem in computer vision. A major challenge in practical face recognition applications lies in significant variations between profile and frontal faces. Traditional techniques address this challenge either by synthesizing frontal faces or by pose invariant learning. In this paper, we propose a novel method with Lie algebra theory to explore how face rotation in the 3D space affects the deep feature generation process of convolutional neural networks (CNNs). We prove that face rotation in the image space is equivalent to an additive residual component in the feature space of CNNs, which is determined solely by the rotation. Based on this theoretical finding, we further design a Lie Algebraic Residual Network (LARNet) for tackling pose robust face recognition. Our LARNet consists of a residual subnet for decoding rotation information from input face images, and a gating subnet to learn rotation magnitude for controlling the strength of the residual component contributing to the feature learning process. Comprehensive experimental evaluations on both frontal-profile face datasets and general face recognition datasets convincingly demonstrate that our method consistently outperforms the state-of-the-art ones.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/yang21d.html
http://proceedings.mlr.press/v139/yang21d.htmlTensor Programs IV: Feature Learning in Infinite-Width Neural NetworksAs its width tends to infinity, a deep neural network’s behavior under gradient descent can become simplified and predictable (e.g. given by the Neural Tangent Kernel (NTK)), if it is parametrized appropriately (e.g. the NTK parametrization). However, we show that the standard and NTK parametrizations of a neural network do not admit infinite-width limits that can *learn* features, which is crucial for pretraining and transfer learning such as with BERT. We propose simple modifications to the standard parametrization to allow for feature learning in the limit. Using the *Tensor Programs* technique, we derive explicit formulas for such limits. On Word2Vec and few-shot learning on Omniglot via MAML, two canonical tasks that rely crucially on feature learning, we compute these limits exactly. We find that they outperform both NTK baselines and finite-width networks, with the latter approaching the infinite-width feature learning performance as width increases.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/yang21c.html
http://proceedings.mlr.press/v139/yang21c.htmlLearning Optimal Auctions with Correlated Valuations from SamplesIn single-item auction design, it is well known due to Cremer and McLean that when bidders’ valuations are drawn from a correlated prior distribution, the auctioneer can extract full social surplus as revenue. However, in most real-world applications, the prior is usually unknown and can only be learned from historical data. In this work, we investigate the robustness of the optimal auction with correlated valuations via sample complexity analysis. We prove upper and lower bounds on the number of samples from the unknown prior required to learn a (1-epsilon)-approximately optimal auction. Our results reinforce the common belief that optimal correlated auctions are sensitive to the distribution parameters and hard to learn unless the prior distribution is well-behaved.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/yang21b.html
http://proceedings.mlr.press/v139/yang21b.htmlExact Gap between Generalization Error and Uniform Convergence in Random Feature ModelsRecent work showed that there could be a large gap between the classical uniform convergence bound and the actual test error of zero-training-error predictors (interpolators) such as deep neural networks. To better understand this gap, we study the uniform convergence in the nonlinear random feature model and perform a precise theoretical analysis on how uniform convergence depends on the sample size and the number of parameters. We derive and prove analytical expressions for three quantities in this model: 1) classical uniform convergence over norm balls, 2) uniform convergence over interpolators in the norm ball (recently proposed by \citet{zhou2021uniform}), and 3) the risk of minimum norm interpolator. We show that, in the setting where the classical uniform convergence bound is vacuous (diverges to $\infty$), uniform convergence over the interpolators still gives a non-trivial bound of the test error of interpolating solutions. We also showcase a different setting where classical uniform convergence bound is non-vacuous, but uniform convergence over interpolators can give an improved sample complexity guarantee. Our result provides a first exact comparison between the test errors and uniform convergence bounds for interpolators beyond simple linear models.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/yang21a.html
http://proceedings.mlr.press/v139/yang21a.htmlCIFS: Improving Adversarial Robustness of CNNs via Channel-wise Importance-based Feature SelectionWe investigate the adversarial robustness of CNNs from the perspective of channel-wise activations. By comparing normally trained and adversarially trained models, we observe that adversarial training (AT) robustifies CNNs by aligning the channel-wise activations of adversarial data with those of their natural counterparts. However, the channels that are \textit{negatively-relevant} (NR) to predictions are still over-activated when processing adversarial data. Besides, we also observe that AT does not result in similar robustness for all classes. For the robust classes, channels with larger activation magnitudes are usually more \textit{positively-relevant} (PR) to predictions, but this alignment does not hold for the non-robust classes. Given these observations, we hypothesize that suppressing NR channels and aligning PR ones with their relevances further enhances the robustness of CNNs under AT. To examine this hypothesis, we introduce a novel mechanism, \textit{i.e.}, \underline{C}hannel-wise \underline{I}mportance-based \underline{F}eature \underline{S}election (CIFS). The CIFS manipulates channels’ activations of certain layers by generating non-negative multipliers to these channels based on their relevances to predictions. Extensive experiments on benchmark datasets including CIFAR10 and SVHN clearly verify the hypothesis and CIFS’s effectiveness of robustifying CNNs.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/yan21e.html
http://proceedings.mlr.press/v139/yan21e.htmlOn Perceptual Lossy Compression: The Cost of Perceptual Reconstruction and An Optimal Training FrameworkLossy compression algorithms are typically designed to achieve the lowest possible distortion at a given bit rate. However, recent studies show that pursuing high perceptual quality would lead to increase of the lowest achievable distortion (e.g., MSE). This paper provides nontrivial results theoretically revealing that, 1) the cost of achieving perfect perception quality is exactly a doubling of the lowest achievable MSE distortion, 2) an optimal encoder for the “classic” rate-distortion problem is also optimal for the perceptual compression problem, 3) distortion loss is unnecessary for training a perceptual decoder. Further, we propose a novel training framework to achieve the lowest MSE distortion under perfect perception constraint at a given bit rate. This framework uses a GAN with discriminator conditioned on an MSE-optimized encoder, which is superior over the traditional framework using distortion plus adversarial loss. Experiments are provided to verify the theoretical finding and demonstrate the superiority of the proposed training framework.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/yan21d.html
http://proceedings.mlr.press/v139/yan21d.htmlCATE: Computation-aware Neural Architecture Encoding with TransformersRecent works (White et al., 2020a; Yan et al., 2020) demonstrate the importance of architecture encodings in Neural Architecture Search (NAS). These encodings encode either structure or computation information of the neural architectures. Compared to structure-aware encodings, computation-aware encodings map architectures with similar accuracies to the same region, which improves the downstream architecture search performance (Zhang et al., 2019; White et al., 2020a). In this work, we introduce a Computation-Aware Transformer-based Encoding method called CATE. Different from existing computation-aware encodings based on fixed transformation (e.g. path encoding), CATE employs a pairwise pre-training scheme to learn computation-aware encodings using Transformers with cross-attention. Such learned encodings contain dense and contextualized computation information of neural architectures. We compare CATE with eleven encodings under three major encoding-dependent NAS subroutines in both small and large search spaces. Our experiments show that CATE is beneficial to the downstream search, especially in the large search space. Moreover, the outside search space experiment demonstrates its superior generalization ability beyond the search space on which it was trained. Our code is available at: https://github.com/MSU-MLSys-Lab/CATE.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/yan21c.html
http://proceedings.mlr.press/v139/yan21c.htmlLink Prediction with Persistent Homology: An Interactive ViewLink prediction is an important learning task for graph-structured data. In this paper, we propose a novel topological approach to characterize interactions between two nodes. Our topological feature, based on the extended persistent homology, encodes rich structural information regarding the multi-hop paths connecting nodes. Based on this feature, we propose a graph neural network method that outperforms state-of-the-arts on different benchmarks. As another contribution, we propose a novel algorithm to more efficiently compute the extended persistence diagrams for graphs. This algorithm can be generally applied to accelerate many other topological methods for graph learning tasks.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/yan21b.html
http://proceedings.mlr.press/v139/yan21b.htmlEL-Attention: Memory Efficient Lossless Attention for GenerationTransformer model with multi-head attention requires caching intermediate results for efficient inference in generation tasks. However, cache brings new memory-related costs and prevents leveraging larger batch size for faster speed. We propose memory-efficient lossless attention (called EL-attention) to address this issue. It avoids heavy operations for building multi-head keys and values, cache for them is not needed. EL-attention constructs an ensemble of attention results by expanding query while keeping key and value shared. It produces the same result as multi-head attention with less GPU memory and faster inference speed. We conduct extensive experiments on Transformer, BART, and GPT-2 for summarization and question generation tasks. The results show EL-attention speeds up existing models by 1.6x to 5.3x without accuracy loss.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/yan21a.html
http://proceedings.mlr.press/v139/yan21a.htmlMediated Uncoupled Learning: Learning Functions without Direct Input-output CorrespondencesOrdinary supervised learning is useful when we have paired training data of input $X$ and output $Y$. However, such paired data can be difficult to collect in practice. In this paper, we consider the task of predicting $Y$ from $X$ when we have no paired data of them, but we have two separate, independent datasets of $X$ and $Y$ each observed with some mediating variable $U$, that is, we have two datasets $S_X = \{(X_i, U_i)\}$ and $S_Y = \{(U’_j, Y’_j)\}$. A naive approach is to predict $U$ from $X$ using $S_X$ and then $Y$ from $U$ using $S_Y$, but we show that this is not statistically consistent. Moreover, predicting $U$ can be more difficult than predicting $Y$ in practice, e.g., when $U$ has higher dimensionality. To circumvent the difficulty, we propose a new method that avoids predicting $U$ but directly learns $Y = f(X)$ by training $f(X)$ with $S_{X}$ to predict $h(U)$ which is trained with $S_{Y}$ to approximate $Y$. We prove statistical consistency and error bounds of our method and experimentally confirm its practical usefulness.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/yamane21a.html
http://proceedings.mlr.press/v139/yamane21a.htmlStructured Convolutional Kernel Networks for Airline Crew SchedulingMotivated by the needs from an airline crew scheduling application, we introduce structured convolutional kernel networks (Struct-CKN), which combine CKNs from Mairal et al. (2014) in a structured prediction framework that supports constraints on the outputs. CKNs are a particular kind of convolutional neural networks that approximate a kernel feature map on training data, thus combining properties of deep learning with the non-parametric flexibility of kernel methods. Extending CKNs to structured outputs allows us to obtain useful initial solutions on a flight-connection dataset that can be further refined by an airline crew scheduling solver. More specifically, we use a flight-based network modeled as a general conditional random field capable of incorporating local constraints in the learning process. Our experiments demonstrate that this approach yields significant improvements for the large-scale crew pairing problem (50,000 flights per month) over standard approaches, reducing the solution cost by 17% (a gain of millions of dollars) and the cost of global constraints by 97%.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/yaakoubi21a.html
http://proceedings.mlr.press/v139/yaakoubi21a.htmlKNAS: Green Neural Architecture SearchMany existing neural architecture search (NAS) solutions rely on downstream training for architecture evaluation, which takes enormous computations. Considering that these computations bring a large carbon footprint, this paper aims to explore a green (namely environmental-friendly) NAS solution that evaluates architectures without training. Intuitively, gradients, induced by the architecture itself, directly decide the convergence and generalization results. It motivates us to propose the gradient kernel hypothesis: Gradients can be used as a coarse-grained proxy of downstream training to evaluate random-initialized networks. To support the hypothesis, we conduct a theoretical analysis and find a practical gradient kernel that has good correlations with training loss and validation performance. According to this hypothesis, we propose a new kernel based architecture search approach KNAS. Experiments show that KNAS achieves competitive results with orders of magnitude faster than “train-then-test” paradigms on image classification tasks. Furthermore, the extremely low search cost enables its wide applications. The searched network also outperforms strong baseline RoBERTA-large on two text classification tasks.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/xu21m.html
http://proceedings.mlr.press/v139/xu21m.htmlGroup-Sparse Matrix Factorization for Transfer Learning of Word EmbeddingsSparse regression has recently been applied to enable transfer learning from very limited data. We study an extension of this approach to unsupervised learning—in particular, learning word embeddings from unstructured text corpora using low-rank matrix factorization. Intuitively, when transferring word embeddings to a new domain, we expect that the embeddings change for only a small number of words—e.g., the ones with novel meanings in that domain. We propose a novel group-sparse penalty that exploits this sparsity to perform transfer learning when there is very little text data available in the target domain—e.g., a single article of text. We prove generalization bounds for our algorithm. Furthermore, we empirically evaluate its effectiveness, both in terms of prediction accuracy in downstream tasks as well as in terms of interpretability of the results.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/xu21l.html
http://proceedings.mlr.press/v139/xu21l.htmlOptimization of Graph Neural Networks: Implicit Acceleration by Skip Connections and More DepthGraph Neural Networks (GNNs) have been studied through the lens of expressive power and generalization. However, their optimization properties are less well understood. We take the first step towards analyzing GNN training by studying the gradient dynamics of GNNs. First, we analyze linearized GNNs and prove that despite the non-convexity of training, convergence to a global minimum at a linear rate is guaranteed under mild assumptions that we validate on real-world graphs. Second, we study what may affect the GNNs’ training speed. Our results show that the training of GNNs is implicitly accelerated by skip connections, more depth, and/or a good label distribution. Empirical results confirm that our theoretical results for linearized GNNs align with the training behavior of nonlinear GNNs. Our results provide the first theoretical support for the success of GNNs with skip connections in terms of optimization, and suggest that deep GNNs with skip connections would be promising in practice.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/xu21k.html
http://proceedings.mlr.press/v139/xu21k.htmlDoubly Robust Off-Policy Actor-Critic: Convergence and OptimalityDesigning off-policy reinforcement learning algorithms is typically a very challenging task, because a desirable iteration update often involves an expectation over an on-policy distribution. Prior off-policy actor-critic (AC) algorithms have introduced a new critic that uses the density ratio for adjusting the distribution mismatch in order to stabilize the convergence, but at the cost of potentially introducing high biases due to the estimation errors of both the density ratio and value function. In this paper, we develop a doubly robust off-policy AC (DR-Off-PAC) for discounted MDP, which can take advantage of learned nuisance functions to reduce estimation errors. Moreover, DR-Off-PAC adopts a single timescale structure, in which both actor and critics are updated simultaneously with constant stepsize, and is thus more sample efficient than prior algorithms that adopt either two timescale or nested-loop structure. We study the finite-time convergence rate and characterize the sample complexity for DR-Off-PAC to attain an $\epsilon$-accurate optimal policy. We also show that the overall convergence of DR-Off-PAC is doubly robust to the approximation errors that depend only on the expressive power of approximation functions. To the best of our knowledge, our study establishes the first overall sample complexity analysis for single time-scale off-policy AC algorithm.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/xu21j.html
http://proceedings.mlr.press/v139/xu21j.htmlLearner-Private Convex OptimizationConvex optimization with feedback is a framework where a learner relies on iterative queries and feedback to arrive at the minimizer of a convex function. The paradigm has gained significant popularity recently thanks to its scalability in large-scale optimization and machine learning. The repeated interactions, however, expose the learner to privacy risks from eavesdropping adversaries that observe the submitted queries. In this paper, we study how to optimally obfuscate the learner’s queries in convex optimization with first-order feedback, so that their learned optimal value is provably difficult to estimate for the eavesdropping adversary. We consider two formulations of learner privacy: a Bayesian formulation in which the convex function is drawn randomly, and a minimax formulation in which the function is fixed and the adversary’s probability of error is measured with respect to a minimax criterion. We show that, if the learner wants to ensure the probability of the adversary estimating accurately be kept below 1/L, then the overhead in query complexity is additive in L in the minimax formulation, but multiplicative in L in the Bayesian formulation. Compared to existing learner-private sequential learning models with binary feedback, our results apply to the significantly richer family of general convex functions with full-gradient feedback. Our proofs are largely enabled by tools from the theory of Dirichlet processes, as well as more sophisticated lines of analysis aimed at measuring the amount of information leakage under a full-gradient oracle.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/xu21i.html
http://proceedings.mlr.press/v139/xu21i.htmlConformal prediction interval for dynamic time-seriesWe develop a method to construct distribution-free prediction intervals for dynamic time-series, called \Verb|EnbPI| that wraps around any bootstrap ensemble estimator to construct sequential prediction intervals. \Verb|EnbPI| is closely related to the conformal prediction (CP) framework but does not require data exchangeability. Theoretically, these intervals attain finite-sample, \textit{approximately valid} marginal coverage for broad classes of regression functions and time-series with strongly mixing stochastic errors. Computationally, \Verb|EnbPI| avoids overfitting and requires neither data-splitting nor training multiple ensemble estimators; it efficiently aggregates bootstrap estimators that have been trained. In general, \Verb|EnbPI| is easy to implement, scalable to producing arbitrarily many prediction intervals sequentially, and well-suited to a wide range of regression functions. We perform extensive real-data analyses to demonstrate its effectiveness.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/xu21h.html
http://proceedings.mlr.press/v139/xu21h.htmlSelf-supervised Graph-level Representation Learning with Local and Global StructureThis paper studies unsupervised/self-supervised whole-graph representation learning, which is critical in many tasks such as molecule properties prediction in drug and material discovery. Existing methods mainly focus on preserving the local similarity structure between different graph instances but fail to discover the global semantic structure of the entire data set. In this paper, we propose a unified framework called Local-instance and Global-semantic Learning (GraphLoG) for self-supervised whole-graph representation learning. Specifically, besides preserving the local similarities, GraphLoG introduces the hierarchical prototypes to capture the global semantic clusters. An efficient online expectation-maximization (EM) algorithm is further developed for learning the model. We evaluate GraphLoG by pre-training it on massive unlabeled graphs followed by fine-tuning on downstream tasks. Extensive experiments on both chemical and biological benchmark data sets demonstrate the effectiveness of the proposed approach.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/xu21g.html
http://proceedings.mlr.press/v139/xu21g.htmlAn End-to-End Framework for Molecular Conformation Generation via Bilevel ProgrammingPredicting molecular conformations (or 3D structures) from molecular graphs is a fundamental problem in many applications. Most existing approaches are usually divided into two steps by first predicting the distances between atoms and then generating a 3D structure through optimizing a distance geometry problem. However, the distances predicted with such two-stage approaches may not be able to consistently preserve the geometry of local atomic neighborhoods, making the generated structures unsatisfying. In this paper, we propose an end-to-end solution for molecular conformation prediction called ConfVAE based on the conditional variational autoencoder framework. Specifically, the molecular graph is first encoded in a latent space, and then the 3D structures are generated by solving a principled bilevel optimization program. Extensive experiments on several benchmark data sets prove the effectiveness of our proposed approach over existing state-of-the-art approaches. Code is available at \url{https://github.com/MinkaiXu/ConfVAE-ICML21}.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/xu21f.html
http://proceedings.mlr.press/v139/xu21f.htmlDash: Semi-Supervised Learning with Dynamic ThresholdingWhile semi-supervised learning (SSL) has received tremendous attentions in many machine learning tasks due to its successful use of unlabeled data, existing SSL algorithms use either all unlabeled examples or the unlabeled examples with a fixed high-confidence prediction during the training progress. However, it is possible that too many correct/wrong pseudo labeled examples are eliminated/selected. In this work we develop a simple yet powerful framework, whose key idea is to select a subset of training examples from the unlabeled data when performing existing SSL methods so that only the unlabeled examples with pseudo labels related to the labeled data will be used to train models. The selection is performed at each updating iteration by only keeping the examples whose losses are smaller than a given threshold that is dynamically adjusted through the iteration. Our proposed approach, Dash, enjoys its adaptivity in terms of unlabeled data selection and its theoretical guarantee. Specifically, we theoretically establish the convergence rate of Dash from the view of non-convex optimization. Finally, we empirically demonstrate the effectiveness of the proposed method in comparison with state-of-the-art over benchmarks.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/xu21e.html
http://proceedings.mlr.press/v139/xu21e.htmlRethinking Neural vs. Matrix-Factorization Collaborative Filtering: the Theoretical PerspectivesThe recent work by Rendle et al. (2020), based on empirical observations, argues that matrix-factorization collaborative filtering (MCF) compares favorably to neural collaborative filtering (NCF), and conjectures the dot product’s superiority over the feed-forward neural network as similarity function. In this paper, we address the comparison rigorously by answering the following questions: 1. what is the limiting expressivity of each model; 2. under the practical gradient descent, to which solution does each optimization path converge; 3. how would the models generalize under the inductive and transductive learning setting. Our results highlight the similar expressivity for the overparameterized NCF and MCF as kernelized predictors, and reveal the relation between their optimization paths. We further show their different generalization behaviors, where MCF and NCF experience specific tradeoff and comparison in the transductive and inductive collaborative filtering setting. Lastly, by showing a novel generalization result, we reveal the critical role of correcting exposure bias for model evaluation in the inductive setting. Our results explain some of the previously observed conflicts, and we provide synthetic and real-data experiments to shed further insights to this topic.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/xu21d.html
http://proceedings.mlr.press/v139/xu21d.htmlInterpretable Stein Goodness-of-fit Tests on Riemannian ManifoldIn many applications, we encounter data on Riemannian manifolds such as torus and rotation groups. Standard statistical procedures for multivariate data are not applicable to such data. In this study, we develop goodness-of-fit testing and interpretable model criticism methods for general distributions on Riemannian manifolds, including those with an intractable normalization constant. The proposed methods are based on extensions of kernel Stein discrepancy, which are derived from Stein operators on Riemannian manifolds. We discuss the connections between the proposed tests with existing ones and provide a theoretical analysis of their asymptotic Bahadur efficiency. Simulation results and real data applications show the validity and usefulness of the proposed methods.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/xu21c.html
http://proceedings.mlr.press/v139/xu21c.htmlTo be Robust or to be Fair: Towards Fairness in Adversarial TrainingAdversarial training algorithms have been proved to be reliable to improve machine learning models’ robustness against adversarial examples. However, we find that adversarial training algorithms tend to introduce severe disparity of accuracy and robustness between different groups of data. For instance, PGD adversarially trained ResNet18 model on CIFAR-10 has 93% clean accuracy and 67% PGD l_infty-8 adversarial accuracy on the class ”automobile” but only 65% and 17% on class ”cat”. This phenomenon happens in balanced datasets and does not exist in naturally trained models when only using clean samples. In this work, we empirically and theoretically show that this phenomenon can generally happen under adversarial training algorithms which minimize DNN models’ robust errors. Motivated by these findings, we propose a Fair-Robust-Learning (FRL) framework to mitigate this unfairness problem when doing adversarial defenses and experimental results validate the effectiveness of FRL.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/xu21b.html
http://proceedings.mlr.press/v139/xu21b.htmlCRPO: A New Approach for Safe Reinforcement Learning with Convergence GuaranteeIn safe reinforcement learning (SRL) problems, an agent explores the environment to maximize an expected total reward and meanwhile avoids violation of certain constraints on a number of expected total costs. In general, such SRL problems have nonconvex objective functions subject to multiple nonconvex constraints, and hence are very challenging to solve, particularly to provide a globally optimal policy. Many popular SRL algorithms adopt a primal-dual structure which utilizes the updating of dual variables for satisfying the constraints. In contrast, we propose a primal approach, called constraint-rectified policy optimization (CRPO), which updates the policy alternatingly between objective improvement and constraint satisfaction. CRPO provides a primal-type algorithmic framework to solve SRL problems, where each policy update can take any variant of policy optimization step. To demonstrate the theoretical performance of CRPO, we adopt natural policy gradient (NPG) for each policy update step and show that CRPO achieves an $\mathcal{O}(1/\sqrt{T})$ convergence rate to the global optimal policy in the constrained policy set and an $\mathcal{O}(1/\sqrt{T})$ error bound on constraint satisfaction. This is the first finite-time analysis of primal SRL algorithms with global optimality guarantee. Our empirical results demonstrate that CRPO can outperform the existing primal-dual baseline algorithms significantly.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/xu21a.html
http://proceedings.mlr.press/v139/xu21a.htmlExplore Visual Concept Formation for Image ClassificationHuman beings acquire the ability of image classification through visual concept learning, in which the process of concept formation involves intertwined searches of common properties and concept descriptions. However, in most image classification algorithms using deep convolutional neural network (ConvNet), the representation space is constructed under the premise that concept descriptions are fixed as one-hot codes, which limits the mining of properties and the ability of identifying unseen samples. Inspired by this, we propose a learning strategy of visual concept formation (LSOVCF) based on the ConvNet, in which the two intertwined parts of concept formation, i.e. feature extraction and concept description, are learned together. First, LSOVCF takes sample response in the last layer of ConvNet to induct concept description being assumed as Gaussian distribution, which is part of the training process. Second, the exploration and experience loss is designed for optimization, which adopts experience cache pool to speed up convergence. Experiments show that LSOVCF improves the ability of identifying unseen samples on cifar10, STL10, flower17 and ImageNet based on several backbones, from the classic VGG to the SOTA Ghostnet. The code is available at \url{https://github.com/elvintanhust/LSOVCF}.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/xiong21a.html
http://proceedings.mlr.press/v139/xiong21a.htmlA Hybrid Variance-Reduced Method for Decentralized Stochastic Non-Convex OptimizationThis paper considers decentralized stochastic optimization over a network of $n$ nodes, where each node possesses a smooth non-convex local cost function and the goal of the networked nodes is to find an $\epsilon$-accurate first-order stationary point of the sum of the local costs. We focus on an online setting, where each node accesses its local cost only by means of a stochastic first-order oracle that returns a noisy version of the exact gradient. In this context, we propose a novel single-loop decentralized hybrid variance-reduced stochastic gradient method, called GT-HSGD, that outperforms the existing approaches in terms of both the oracle complexity and practical implementation. The GT-HSGD algorithm implements specialized local hybrid stochastic gradient estimators that are fused over the network to track the global gradient. Remarkably, GT-HSGD achieves a network topology-independent oracle complexity of $O(n^{-1}\epsilon^{-3})$ when the required error tolerance $\epsilon$ is small enough, leading to a linear speedup with respect to the centralized optimal online variance-reduced approaches that operate on a single node. Numerical experiments are provided to illustrate our main technical results.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/xin21a.html
http://proceedings.mlr.press/v139/xin21a.htmlPositive-Negative Momentum: Manipulating Stochastic Gradient Noise to Improve GeneralizationIt is well-known that stochastic gradient noise (SGN) acts as implicit regularization for deep learning and is essentially important for both optimization and generalization of deep networks. Some works attempted to artificially simulate SGN by injecting random noise to improve deep learning. However, it turned out that the injected simple random noise cannot work as well as SGN, which is anisotropic and parameter-dependent. For simulating SGN at low computational costs and without changing the learning rate or batch size, we propose the Positive-Negative Momentum (PNM) approach that is a powerful alternative to conventional Momentum in classic optimizers. The introduced PNM method maintains two approximate independent momentum terms. Then, we can control the magnitude of SGN explicitly by adjusting the momentum difference. We theoretically prove the convergence guarantee and the generalization advantage of PNM over Stochastic Gradient Descent (SGD). By incorporating PNM into the two conventional optimizers, SGD with Momentum and Adam, our extensive experiments empirically verified the significant advantage of the PNM-based variants over the corresponding conventional Momentum-based optimizers. Code: \url{https://github.com/zeke-xie/Positive-Negative-Momentum}.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/xie21h.html
http://proceedings.mlr.press/v139/xie21h.htmlLearning While Playing in Mean-Field Games: Convergence and OptimalityWe study reinforcement learning in mean-field games. To achieve the Nash equilibrium, which consists of a policy and a mean-field state, existing algorithms require obtaining the optimal policy while fixing any mean-field state. In practice, however, the policy and the mean-field state evolve simultaneously, as each agent is learning while playing. To bridge such a gap, we propose a fictitious play algorithm, which alternatively updates the policy (learning) and the mean-field state (playing) by one step of policy optimization and gradient descent, respectively. Despite the nonstationarity induced by such an alternating scheme, we prove that the proposed algorithm converges to the Nash equilibrium with an explicit convergence rate. To the best of our knowledge, it is the first provably efficient algorithm that achieves learning while playing via alternating updates.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/xie21g.html
http://proceedings.mlr.press/v139/xie21g.htmlComposed Fine-Tuning: Freezing Pre-Trained Denoising Autoencoders for Improved GeneralizationWe focus on prediction problems with structured outputs that are subject to output validity constraints, e.g. pseudocode-to-code translation where the code must compile. While labeled input-output pairs are expensive to obtain, "unlabeled" outputs, i.e. outputs without corresponding inputs, are freely available (e.g. code on GitHub) and provide information about output validity. Pre-training captures this structure by training a denoiser to denoise corrupted versions of unlabeled outputs. We first show that standard fine-tuning after pre-training destroys some of this structure. We then propose composed fine-tuning, which trains a predictor composed with the pre-trained denoiser. Importantly, the denoiser is fixed to preserve output structure. Like standard fine-tuning, the predictor is also initialized with the pre-trained denoiser. We prove for two-layer ReLU networks that composed fine-tuning significantly reduces the complexity of the predictor, thus improving generalization. Empirically, we show that composed fine-tuning improves over standard fine-tuning on two pseudocode-to-code translation datasets (3% and 6% relative). The improvement is magnified on out-of-distribution (OOD) examples (4% and 25% relative), suggesting that reducing predictor complexity improves OOD extrapolation.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/xie21f.html
http://proceedings.mlr.press/v139/xie21f.htmlInteraction-Grounded LearningConsider a prosthetic arm, learning to adapt to its user’s control signals. We propose \emph{Interaction-Grounded Learning} for this novel setting, in which a learner’s goal is to interact with the environment with no grounding or explicit reward to optimize its policies. Such a problem evades common RL solutions which require an explicit reward. The learning agent observes a multidimensional \emph{context vector}, takes an \emph{action}, and then observes a multidimensional \emph{feedback vector}. This multidimensional feedback vector has \emph{no} explicit reward information. In order to succeed, the algorithm must learn how to evaluate the feedback vector to discover a latent reward signal, with which it can ground its policies without supervision. We show that in an Interaction-Grounded Learning setting, with certain natural assumptions, a learner can discover the latent reward and ground its policy for successful interaction. We provide theoretical guarantees and a proof-of-concept empirical evaluation to demonstrate the effectiveness of our proposed approach.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/xie21e.html
http://proceedings.mlr.press/v139/xie21e.htmlBatch Value-function Approximation with Only RealizabilityWe make progress in a long-standing problem of batch reinforcement learning (RL): learning Q* from an exploratory and polynomial-sized dataset, using a realizable and otherwise arbitrary function class. In fact, all existing algorithms demand function-approximation assumptions stronger than realizability, and the mounting negative evidence has led to a conjecture that sample-efficient learning is impossible in this setting (Chen & Jiang, 2019). Our algorithm, BVFT, breaks the hardness conjecture (albeit under a stronger notion of exploratory data) via a tournament procedure that reduces the learning problem to pairwise comparison, and solves the latter with the help of a state-action-space partition constructed from the compared functions. We also discuss how BVFT can be applied to model selection among other extensions and open problems.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/xie21d.html
http://proceedings.mlr.press/v139/xie21d.htmlDeep Reinforcement Learning amidst Continual Structured Non-StationarityAs humans, our goals and our environment are persistently changing throughout our lifetime based on our experiences, actions, and internal and external drives. In contrast, typical reinforcement learning problem set-ups consider decision processes that are stationary across episodes. Can we develop reinforcement learning algorithms that can cope with the persistent change in the former, more realistic problem settings? While on-policy algorithms such as policy gradients in principle can be extended to non-stationary settings, the same cannot be said for more efficient off-policy algorithms that replay past experiences when learning. In this work, we formalize this problem setting, and draw upon ideas from the online learning and probabilistic inference literature to derive an off-policy RL algorithm that can reason about and tackle such lifelong non-stationarity. Our method leverages latent variable models to learn a representation of the environment from current and past experiences, and performs off-policy RL with this representation. We further introduce several simulation environments that exhibit lifelong non-stationarity, and empirically find that our approach substantially outperforms approaches that do not reason about environment shift.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/xie21c.html
http://proceedings.mlr.press/v139/xie21c.htmlRNNRepair: Automatic RNN Repair via Model-based AnalysisDeep neural networks are vulnerable to adversarial attacks. Due to their black-box nature, it is rather challenging to interpret and properly repair these incorrect behaviors. This paper focuses on interpreting and repairing the incorrect behaviors of Recurrent Neural Networks (RNNs). We propose a lightweight model-based approach (RNNRepair) to help understand and repair incorrect behaviors of an RNN. Specifically, we build an influence model to characterize the stateful and statistical behaviors of an RNN over all the training data and to perform the influence analysis for the errors. Compared with the existing techniques on influence function, our method can efficiently estimate the influence of existing or newly added training samples for a given prediction at both sample level and segmentation level. Our empirical evaluation shows that the proposed influence model is able to extract accurate and understandable features. Based on the influence model, our proposed technique could effectively infer the influential instances from not only an entire testing sequence but also a segment within that sequence. Moreover, with the sample-level and segment-level influence relations, RNNRepair could further remediate two types of incorrect predictions at the sample level and segment level.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/xie21b.html
http://proceedings.mlr.press/v139/xie21b.htmlCRFL: Certifiably Robust Federated Learning against Backdoor AttacksFederated Learning (FL) as a distributed learning paradigm that aggregates information from diverse clients to train a shared global model, has demonstrated great success. However, malicious clients can perform poisoning attacks and model replacement to introduce backdoors into the trained global model. Although there have been intensive studies designing robust aggregation methods and empirical robust federated training protocols against backdoors, existing approaches lack robustness certification. This paper provides the first general framework, Certifiably Robust Federated Learning (CRFL), to train certifiably robust FL models against backdoors. Our method exploits clipping and smoothing on model parameters to control the global model smoothness, which yields a sample-wise robustness certification on backdoors with limited magnitude. Our certification also specifies the relation to federated learning parameters, such as poisoning ratio on instance level, number of attackers, and training iterations. Practically, we conduct comprehensive experiments across a range of federated datasets, and provide the first benchmark for certified robustness against backdoor attacks in federated learning. Our code is publicaly available at https://github.com/AI-secure/CRFL.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/xie21a.html
http://proceedings.mlr.press/v139/xie21a.htmlOn the Optimality of Batch Policy Optimization AlgorithmsBatch policy optimization considers leveraging existing data for policy construction before interacting with an environment. Although interest in this problem has grown significantly in recent years, its theoretical foundations remain under-developed. To advance the understanding of this problem, we provide three results that characterize the limits and possibilities of batch policy optimization in the finite-armed stochastic bandit setting. First, we introduce a class of confidence-adjusted index algorithms that unifies optimistic and pessimistic principles in a common framework, which enables a general analysis. For this family, we show that any confidence-adjusted index algorithm is minimax optimal, whether it be optimistic, pessimistic or neutral. Our analysis reveals that instance-dependent optimality, commonly used to establish optimality of on-line stochastic bandit algorithms, cannot be achieved by any algorithm in the batch setting. In particular, for any algorithm that performs optimally in some environment, there exists another environment where the same algorithm suffers arbitrarily larger regret. Therefore, to establish a framework for distinguishing algorithms, we introduce a new weighted-minimax criterion that considers the inherent difficulty of optimal value prediction. We demonstrate how this criterion can be used to justify commonly used pessimistic principles for batch policy optimization.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/xiao21b.html
http://proceedings.mlr.press/v139/xiao21b.htmlA Bit More Bayesian: Domain-Invariant Learning with UncertaintyDomain generalization is challenging due to the domain shift and the uncertainty caused by the inaccessibility of target domain data. In this paper, we address both challenges with a probabilistic framework based on variational Bayesian inference, by incorporating uncertainty into neural network weights. We couple domain invariance in a probabilistic formula with the variational Bayesian inference. This enables us to explore domain-invariant learning in a principled way. Specifically, we derive domain-invariant representations and classifiers, which are jointly established in a two-layer Bayesian neural network. We empirically demonstrate the effectiveness of our proposal on four widely used cross-domain visual recognition benchmarks. Ablation studies validate the synergistic benefits of our Bayesian treatment when jointly learning domain-invariant representations and classifiers for domain generalization. Further, our method consistently delivers state-of-the-art mean accuracy on all benchmarks.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/xiao21a.html
http://proceedings.mlr.press/v139/xiao21a.htmlData-efficient Hindsight Off-policy Option LearningWe introduce Hindsight Off-policy Options (HO2), a data-efficient option learning algorithm. Given any trajectory, HO2 infers likely option choices and backpropagates through the dynamic programming inference procedure to robustly train all policy components off-policy and end-to-end. The approach outperforms existing option learning methods on common benchmarks. To better understand the option framework and disentangle benefits from both temporal and action abstraction, we evaluate ablations with flat policies and mixture policies with comparable optimization. The results highlight the importance of both types of abstraction as well as off-policy training and trust-region constraints, particularly in challenging, simulated 3D robot manipulation tasks from raw pixel inputs. Finally, we intuitively adapt the inference step to investigate the effect of increased temporal abstraction on training with pre-trained options and from scratch.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/wulfmeier21a.html
http://proceedings.mlr.press/v139/wulfmeier21a.htmlTowards Open-World Recommendation: An Inductive Model-based Collaborative Filtering ApproachRecommendation models can effectively estimate underlying user interests and predict one’s future behaviors by factorizing an observed user-item rating matrix into products of two sets of latent factors. However, the user-specific embedding factors can only be learned in a transductive way, making it difficult to handle new users on-the-fly. In this paper, we propose an inductive collaborative filtering framework that contains two representation models. The first model follows conventional matrix factorization which factorizes a group of key users’ rating matrix to obtain meta latents. The second model resorts to attention-based structure learning that estimates hidden relations from query to key users and learns to leverage meta latents to inductively compute embeddings for query users via neural message passing. Our model enables inductive representation learning for users and meanwhile guarantees equivalent representation capacity as matrix factorization. Experiments demonstrate that our model achieves promising results for recommendation on few-shot users with limited training ratings and new unseen users which are commonly encountered in open-world recommender systems.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/wu21j.html
http://proceedings.mlr.press/v139/wu21j.htmlUncertainty Weighted Actor-Critic for Offline Reinforcement LearningOffline Reinforcement Learning promises to learn effective policies from previously-collected, static datasets without the need for exploration. However, existing Q-learning and actor-critic based off-policy RL algorithms fail when bootstrapping from out-of-distribution (OOD) actions or states. We hypothesize that a key missing ingredient from the existing methods is a proper treatment of uncertainty in the offline setting. We propose Uncertainty Weighted Actor-Critic (UWAC), an algorithm that detects OOD state-action pairs and down-weights their contribution in the training objectives accordingly. Implementation-wise, we adopt a practical and effective dropout-based uncertainty estimation method that introduces very little overhead over existing RL algorithms. Empirically, we observe that UWAC substantially improves model stability during training. In addition, UWAC out-performs existing offline RL methods on a variety of competitive tasks, and achieves significant performance gains over the state-of-the-art baseline on datasets with sparse demonstrations collected from human experts.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/wu21i.html
http://proceedings.mlr.press/v139/wu21i.htmlGenerative Video Transformer: Can Objects be the Words?Transformers have been successful for many natural language processing tasks. However, applying transformers to the video domain for tasks such as long-term video generation and scene understanding has remained elusive due to the high computational complexity and the lack of natural tokenization. In this paper, we propose the ObjectCentric Video Transformer (OCVT) which utilizes an object-centric approach for decomposing scenes into tokens suitable for use in a generative video transformer. By factoring the video into objects, our fully unsupervised model is able to learn complex spatio-temporal dynamics of multiple interacting objects in a scene and generate future frames of the video. Our model is also significantly more memory-efficient than pixel-based models and thus able to train on videos of length up to 70 frames with a single 48GB GPU. We compare our model with previous RNN-based approaches as well as other possible video transformer baselines. We demonstrate OCVT performs well when compared to baselines in generating future frames. OCVT also develops useful representations for video reasoning, achieving start-of-the-art performance on the CATER task.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/wu21h.html
http://proceedings.mlr.press/v139/wu21h.htmlOn Reinforcement Learning with Adversarial Corruption and Its Application to Block MDPWe study reinforcement learning (RL) in episodic tabular MDPs with adversarial corruptions, where some episodes can be adversarially corrupted. When the total number of corrupted episodes is known, we propose an algorithm, Corruption Robust Monotonic Value Propagation (\textsf{CR-MVP}), which achieves a regret bound of $\tilde{O}\left(\left(\sqrt{SAK}+S^2A+CSA)\right)\polylog(H)\right)$, where $S$ is the number of states, $A$ is the number of actions, $H$ is the planning horizon, $K$ is the number of episodes, and $C$ is the corruption level. We also provide a corresponding lower bound, which indicates that our upper bound is tight. Finally, as an application, we study RL with rich observations in the block MDP model. We provide the first algorithm that achieves a $\sqrt{K}$-type regret in this setting and is computationally efficient.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/wu21g.html
http://proceedings.mlr.press/v139/wu21g.htmlClass2Simi: A Noise Reduction Perspective on Learning with Noisy LabelsLearning with noisy labels has attracted a lot of attention in recent years, where the mainstream approaches are in \emph{pointwise} manners. Meanwhile, \emph{pairwise} manners have shown great potential in supervised metric learning and unsupervised contrastive learning. Thus, a natural question is raised: does learning in a pairwise manner \emph{mitigate} label noise? To give an affirmative answer, in this paper, we propose a framework called \emph{Class2Simi}: it transforms data points with noisy \emph{class labels} to data pairs with noisy \emph{similarity labels}, where a similarity label denotes whether a pair shares the class label or not. Through this transformation, the \emph{reduction of the noise rate} is theoretically guaranteed, and hence it is in principle easier to handle noisy similarity labels. Amazingly, DNNs that predict the \emph{clean} class labels can be trained from noisy data pairs if they are first pretrained from noisy data points. Class2Simi is \emph{computationally efficient} because not only this transformation is on-the-fly in mini-batches, but also it just changes loss computation on top of model prediction into a pairwise manner. Its effectiveness is verified by extensive experiments.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/wu21f.html
http://proceedings.mlr.press/v139/wu21f.htmlTemporally Correlated Task Scheduling for Sequence LearningSequence learning has attracted much research attention from the machine learning community in recent years. In many applications, a sequence learning task is usually associated with multiple temporally correlated auxiliary tasks, which are different in terms of how much input information to use or which future step to predict. For example, (i) in simultaneous machine translation, one can conduct translation under different latency (i.e., how many input words to read/wait before translation); (ii) in stock trend forecasting, one can predict the price of a stock in different future days (e.g., tomorrow, the day after tomorrow). While it is clear that those temporally correlated tasks can help each other, there is a very limited exploration on how to better leverage multiple auxiliary tasks to boost the performance of the main task. In this work, we introduce a learnable scheduler to sequence learning, which can adaptively select auxiliary tasks for training depending on the model status and the current training data. The scheduler and the model for the main task are jointly trained through bi-level optimization. Experiments show that our method significantly improves the performance of simultaneous machine translation and stock trend forecasting.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/wu21e.html
http://proceedings.mlr.press/v139/wu21e.htmlChaCha for Online AutoMLWe propose the ChaCha (Champion-Challengers) algorithm for making an online choice of hyperparameters in online learning settings. ChaCha handles the process of determining a champion and scheduling a set of ‘live’ challengers over time based on sample complexity bounds. It is guaranteed to have sublinear regret after the optimal configuration is added into consideration by an application-dependent oracle based on the champions. Empirically, we show that ChaCha provides good performance across a wide array of datasets when optimizing over featurization and hyperparameter decisions.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/wu21d.html
http://proceedings.mlr.press/v139/wu21d.htmlLIME: Learning Inductive Bias for Primitives of Mathematical ReasoningWhile designing inductive bias in neural architectures has been widely studied, we hypothesize that transformer networks are flexible enough to learn inductive bias from suitable generic tasks. Here, we replace architecture engineering by encoding inductive bias in the form of datasets. Inspired by Peirce’s view that deduction, induction, and abduction are the primitives of reasoning, we design three synthetic tasks that are intended to require the model to have these three abilities. We specifically design these tasks to be synthetic and devoid of mathematical knowledge to ensure that only the fundamental reasoning biases can be learned from these tasks. This defines a new pre-training methodology called "LIME" (Learning Inductive bias for Mathematical rEasoning). Models trained with LIME significantly outperform vanilla transformers on four very different large mathematical reasoning benchmarks. Unlike dominating the computation cost as traditional pre-training approaches, LIME requires only a small fraction of the computation cost of the typical downstream task. The code for generating LIME tasks is available at https://github.com/tonywu95/LIME.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/wu21c.html
http://proceedings.mlr.press/v139/wu21c.htmlMaking Paper Reviewing Robust to Bid Manipulation AttacksMost computer science conferences rely on paper bidding to assign reviewers to papers. Although paper bidding enables high-quality assignments in days of unprecedented submission numbers, it also opens the door for dishonest reviewers to adversarially influence paper reviewing assignments. Anecdotal evidence suggests that some reviewers bid on papers by "friends" or colluding authors, even though these papers are outside their area of expertise, and recommend them for acceptance without considering the merit of the work. In this paper, we study the efficacy of such bid manipulation attacks and find that, indeed, they can jeopardize the integrity of the review process. We develop a novel approach for paper bidding and assignment that is much more robust against such attacks. We show empirically that our approach provides robustness even when dishonest reviewers collude, have full knowledge of the assignment system’s internal workings, and have access to the system’s inputs. In addition to being more robust, the quality of our paper review assignments is comparable to that of current, non-robust assignment approaches.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/wu21b.html
http://proceedings.mlr.press/v139/wu21b.htmlConjugate Energy-Based ModelsIn this paper, we propose conjugate energy-based models (CEBMs), a new class of energy-based models that define a joint density over data and latent variables. The joint density of a CEBM decomposes into an intractable distribution over data and a tractable posterior over latent variables. CEBMs have similar use cases as variational autoencoders, in the sense that they learn an unsupervised mapping from data to latent variables. However, these models omit a generator network, which allows them to learn more flexible notions of similarity between data points. Our experiments demonstrate that conjugate EBMs achieve competitive results in terms of image modelling, predictive power of latent space, and out-of-domain detection on a variety of datasets.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/wu21a.html
http://proceedings.mlr.press/v139/wu21a.htmlLearning Neural Network SubspacesRecent observations have advanced our understanding of the neural network optimization landscape, revealing the existence of (1) paths of high accuracy containing diverse solutions and (2) wider minima offering improved performance. Previous methods observing diverse paths require multiple training runs. In contrast we aim to leverage both property (1) and (2) with a single method and in a single training run. With a similar computational cost as training one model, we learn lines, curves, and simplexes of high-accuracy neural networks. These neural network subspaces contain diverse solutions that can be ensembled, approaching the ensemble performance of independently trained networks without the training cost. Moreover, using the subspace midpoint boosts accuracy, calibration, and robustness to label noise, outperforming Stochastic Weight Averaging.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/wortsman21a.html
http://proceedings.mlr.press/v139/wortsman21a.htmlLeveraging Sparse Linear Layers for Debuggable Deep NetworksWe show how fitting sparse linear models over learned deep feature representations can lead to more debuggable neural networks. These networks remain highly accurate while also being more amenable to human interpretation, as we demonstrate quantitatively and via human experiments. We further illustrate how the resulting sparse explanations can help to identify spurious correlations, explain misclassifications, and diagnose model biases in vision and language tasks.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/wong21b.html
http://proceedings.mlr.press/v139/wong21b.htmlLeveraging Language to Learn Program Abstractions and Search HeuristicsInductive program synthesis, or inferring programs from examples of desired behavior, offers a general paradigm for building interpretable, robust, andgeneralizable machine learning systems. Effective program synthesis depends on two key ingredients: a strong library of functions from which to build programs, and an efficient search strategy for finding programs that solve a given task. We introduce LAPS (Language for Abstraction and Program Search), a technique for using natural language annotations to guide joint learning of libraries and neurally-guided search models for synthesis. When integrated into a state-of-the-art library learning system (DreamCoder), LAPS produces higher-quality libraries and improves search efficiency and generalization on three domains {–} string editing, image composition, and abstract reasoning about scenes {–} even when no natural language hints are available at test time.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/wong21a.html
http://proceedings.mlr.press/v139/wong21a.htmlPrediction-Centric Learning of Independent Cascade Dynamics from Partial ObservationsSpreading processes play an increasingly important role in modeling for diffusion networks, information propagation, marketing and opinion setting. We address the problem of learning of a spreading model such that the predictions generated from this model are accurate and could be subsequently used for the optimization, and control of diffusion dynamics. We focus on a challenging setting where full observations of the dynamics are not available, and standard approaches such as maximum likelihood quickly become intractable for large network instances. We introduce a computationally efficient algorithm, based on a scalable dynamic message-passing approach, which is able to learn parameters of the effective spreading model given only limited information on the activation times of nodes in the network. The popular Independent Cascade model is used to illustrate our approach. We show that tractable inference from the learned model generates a better prediction of marginal probabilities compared to the original model. We develop a systematic procedure for learning a mixture of models which further improves the prediction quality.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/wilinski21a.html
http://proceedings.mlr.press/v139/wilinski21a.htmlWhich transformer architecture fits my data? A vocabulary bottleneck in self-attentionAfter their successful debut in natural language processing, Transformer architectures are now becoming the de-facto standard in many domains. An obstacle for their deployment over new modalities is the architectural configuration: the optimal depth-to-width ratio has been shown to dramatically vary across data types (i.e., 10x larger over images than over language). We theoretically predict the existence of an embedding rank bottleneck that limits the contribution of self-attention width to the Transformer expressivity. We thus directly tie the input vocabulary size and rank to the optimal depth-to-width ratio, since a small vocabulary size or rank dictates an added advantage of depth over width. We empirically demonstrate the existence of this bottleneck and its implications on the depth-to-width interplay of Transformer architectures, linking the architecture variability across domains to the often glossed-over usage of different vocabulary sizes or embedding ranks in different domains. As an additional benefit, our rank bottlenecking framework allows us to identify size redundancies of 25%-50% in leading NLP models such as ALBERT and T5.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/wies21a.html
http://proceedings.mlr.press/v139/wies21a.htmlComposing Normalizing Flows for Inverse ProblemsGiven an inverse problem with a normalizing flow prior, we wish to estimate the distribution of the underlying signal conditioned on the observations. We approach this problem as a task of conditional inference on the pre-trained unconditional flow model. We first establish that this is computationally hard for a large class of flow models. Motivated by this, we propose a framework for approximate inference that estimates the target conditional as a composition of two flow models. This formulation leads to a stable variational inference training procedure that avoids adversarial training. Our method is evaluated on a variety of inverse problems and is shown to produce high-quality samples with uncertainty quantification. We further demonstrate that our approach can be amortized for zero-shot inference.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/whang21b.html
http://proceedings.mlr.press/v139/whang21b.htmlSolving Inverse Problems with a Flow-based Noise ModelWe study image inverse problems with a normalizing flow prior. Our formulation views the solution as the maximum a posteriori estimate of the image conditioned on the measurements. This formulation allows us to use noise models with arbitrary dependencies as well as non-linear forward operators. We empirically validate the efficacy of our method on various inverse problems, including compressed sensing with quantized measurements and denoising with highly structured noise patterns. We also present initial theoretical recovery guarantees for solving inverse problems with a flow prior.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/whang21a.html
http://proceedings.mlr.press/v139/whang21a.htmlLearning de-identified representations of prosody from raw audioWe propose a method for learning de-identified prosody representations from raw audio using a contrastive self-supervised signal. Whereas prior work has relied on conditioning models with bottlenecks, we introduce a set of inductive biases that exploit the natural structure of prosody to minimize timbral information and decouple prosody from speaker representations. Despite aggressive downsampling of the input and having no access to linguistic information, our model performs comparably to state-of-the-art speech representations on DAMMP, a new benchmark we introduce for spoken language understanding. We use minimum description length probing to show that our representations have selectively learned the subcomponents of non-timbral prosody, and that the product quantizer naturally disentangles them without using bottlenecks. We derive an information-theoretic definition of speech de-identifiability and use it to demonstrate that our prosody representations are less identifiable than the other speech representations.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/weston21a.html
http://proceedings.mlr.press/v139/weston21a.htmlKeyframe-Focused Visual Imitation LearningImitation learning trains control policies by mimicking pre-recorded expert demonstrations. In partially observable settings, imitation policies must rely on observation histories, but many seemingly paradoxical results show better performance for policies that only access the most recent observation. Recent solutions ranging from causal graph learning to deep information bottlenecks have shown promising results, but failed to scale to realistic settings such as visual imitation. We propose a solution that outperforms these prior approaches by upweighting demonstration keyframes corresponding to expert action changepoints. This simple approach easily scales to complex visual imitation settings. Our experimental results demonstrate consistent performance improvements over all baselines on image-based Gym MuJoCo continuous control tasks. Finally, on the CARLA photorealistic vision-based urban driving simulator, we resolve a long-standing issue in behavioral cloning for driving by demonstrating effective imitation from observation histories. Supplementary materials and code at: \url{https://tinyurl.com/imitation-keyframes}.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/wen21d.html
http://proceedings.mlr.press/v139/wen21d.htmlToward Understanding the Feature Learning Process of Self-supervised Contrastive LearningWe formally study how contrastive learning learns the feature representations for neural networks by investigating its feature learning process. We consider the case where our data are comprised of two types of features: the sparse features which we want to learn from, and the dense features we want to get rid of. Theoretically, we prove that contrastive learning using ReLU networks provably learns the desired features if proper augmentations are adopted. We present an underlying principle called feature decoupling to explain the effects of augmentations, where we theoretically characterize how augmentations can reduce the correlations of dense features between positive samples while keeping the correlations of sparse features intact, thereby forcing the neural networks to learn from the self-supervision of sparse features. Empirically, we verified that the feature decoupling principle matches the underlying mechanism of contrastive learning in practice.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/wen21c.html
http://proceedings.mlr.press/v139/wen21c.htmlCharacterizing the Gap Between Actor-Critic and Policy GradientActor-critic (AC) methods are ubiquitous in reinforcement learning. Although it is understood that AC methods are closely related to policy gradient (PG), their precise connection has not been fully characterized previously. In this paper, we explain the gap between AC and PG methods by identifying the exact adjustment to the AC objective/gradient that recovers the true policy gradient of the cumulative reward objective (PG). Furthermore, by viewing the AC method as a two-player Stackelberg game between the actor and critic, we show that the Stackelberg policy gradient can be recovered as a special case of our more general analysis. Based on these results, we develop practical algorithms, Residual Actor-Critic and Stackelberg Actor-Critic, for estimating the correction between AC and PG and use these to modify the standard AC algorithm. Experiments on popular tabular and continuous environments show the proposed corrections can improve both the sample efficiency and final performance of existing AC methods.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/wen21b.html
http://proceedings.mlr.press/v139/wen21b.htmlLeveraged Weighted Loss for Partial Label LearningAs an important branch of weakly supervised learning, partial label learning deals with data where each instance is assigned with a set of candidate labels, whereas only one of them is true. Despite many methodology studies on learning from partial labels, there still lacks theoretical understandings of their risk consistent properties under relatively weak assumptions, especially on the link between theoretical results and the empirical choice of parameters. In this paper, we propose a family of loss functions named \textit{Leveraged Weighted} (LW) loss, which for the first time introduces the leverage parameter $\beta$ to consider the trade-off between losses on partial labels and non-partial ones. From the theoretical side, we derive a generalized result of risk consistency for the LW loss in learning from partial labels, based on which we provide guidance to the choice of the leverage parameter $\beta$. In experiments, we verify the theoretical guidance, and show the high effectiveness of our proposed LW loss on both benchmark and real datasets compared with other state-of-the-art partial label learning algorithms.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/wen21a.html
http://proceedings.mlr.press/v139/wen21a.htmlThinking Like TransformersWhat is the computational model behind a Transformer? Where recurrent neural networks have direct parallels in finite state machines, allowing clear discussion and thought around architecture variants or trained models, Transformers have no such familiar parallel. In this paper we aim to change that, proposing a computational model for the transformer-encoder in the form of a programming language. We map the basic components of a transformer-encoder—attention and feed-forward computation—into simple primitives, around which we form a programming language: the Restricted Access Sequence Processing Language (RASP). We show how RASP can be used to program solutions to tasks that could conceivably be learned by a Transformer, and how a Transformer can be trained to mimic a RASP solution. In particular, we provide RASP programs for histograms, sorting, and Dyck-languages. We further use our model to relate their difficulty in terms of the number of required layers and attention heads: analyzing a RASP program implies a maximum number of heads and layers necessary to encode a task in a transformer. Finally, we see how insights gained from our abstraction might be used to explain phenomena seen in recent works.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/weiss21a.html
http://proceedings.mlr.press/v139/weiss21a.htmlA Structured Observation Distribution for Generative Biological Sequence Prediction and ForecastingGenerative probabilistic modeling of biological sequences has widespread existing and potential application across biology and biomedicine, from evolutionary biology to epidemiology to protein design. Many standard sequence analysis methods preprocess data using a multiple sequence alignment (MSA) algorithm, one of the most widely used computational methods in all of science. However, as we show in this article, training generative probabilistic models with MSA preprocessing leads to statistical pathologies in the context of sequence prediction and forecasting. To address these problems, we propose a principled drop-in alternative to MSA preprocessing in the form of a structured observation distribution (the "MuE" distribution). We prove theoretically that the MuE distribution comprehensively generalizes popular methods for inferring biological sequence alignments, and provide a precise characterization of how such biological models have differed from natural language latent alignment models. We show empirically that models that use the MuE as an observation distribution outperform comparable methods across a variety of datasets, and apply MuE models to a novel problem for generative probabilistic sequence models: forecasting pathogen evolution.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/weinstein21a.html
http://proceedings.mlr.press/v139/weinstein21a.htmlMeta-learning Hyperparameter Performance Prediction with Neural ProcessesThe surrogate that predicts the performance of hyperparameters has been a key component for sequential model-based hyperparameter optimization. In practical applications, a trial of a hyper-parameter configuration may be so costly that a surrogate is expected to return an optimal configuration with as few trials as possible. Observing that human experts draw on their expertise in a machine learning model by trying configurations that once performed well on other datasets, we are inspired to build a trial-efficient surrogate by transferring the meta-knowledge learned from historical trials on other datasets. We propose an end-to-end surrogate named as Transfer NeuralProcesses (TNP) that learns a comprehensive set of meta-knowledge, including the parameters of historical surrogates, historical trials, and initial configurations for other datasets. Experiments on extensive OpenML datasets and three computer vision datasets demonstrate that the proposed algorithm achieves state-of-the-art performance in at least one order of magnitude less trials.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/wei21c.html
http://proceedings.mlr.press/v139/wei21c.htmlInferring serial correlation with dynamic backgroundsSequential data with serial correlation and an unknown, unstructured, and dynamic background is ubiquitous in neuroscience, psychology, and econometrics. Inferring serial correlation for such data is a fundamental challenge in statistics. We propose a Total Variation (TV) constrained least square estimator coupled with hypothesis tests to infer the serial correlation in the presence of unknown and unstructured dynamic background. The TV constraint on the dynamic background encourages a piecewise constant structure, which can approximate a wide range of dynamic backgrounds. The tuning parameter is selected via the Ljung-Box test to control the bias-variance trade-off. We establish a non-asymptotic upper bound for the estimation error through variational inequalities. We also derive a lower error bound via Fano’s method and show the proposed method is near-optimal. Numerical simulation and a real study in psychology demonstrate the excellent performance of our proposed method compared with the state-of-the-art.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/wei21b.html
http://proceedings.mlr.press/v139/wei21b.htmlDecision-Making Under Selective Labels: Optimal Finite-Domain Policies and BeyondSelective labels are a common feature of high-stakes decision-making applications, referring to the lack of observed outcomes under one of the possible decisions. This paper studies the learning of decision policies in the face of selective labels, in an online setting that balances learning costs against future utility. In the homogeneous case in which individuals’ features are disregarded, the optimal decision policy is shown to be a threshold policy. The threshold becomes more stringent as more labels are collected; the rate at which this occurs is characterized. In the case of features drawn from a finite domain, the optimal policy consists of multiple homogeneous policies in parallel. For the general infinite-domain case, the homogeneous policy is extended by using a probabilistic classifier and bootstrapping to provide its inputs. In experiments on synthetic and real data, the proposed policies achieve consistently superior utility with no parameter tuning in the finite-domain case and lower parameter sensitivity in the general case.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/wei21a.html
http://proceedings.mlr.press/v139/wei21a.htmlA Unified Generative Adversarial Network Training via Self-Labeling and Self-AttentionWe propose a novel GAN training scheme that can handle any level of labeling in a unified manner. Our scheme introduces a form of artificial labeling that can incorporate manually defined labels, when available, and induce an alignment between them. To define the artificial labels, we exploit the assumption that neural network generators can be trained more easily to map nearby latent vectors to data with semantic similarities, than across separate categories. We use generated data samples and their corresponding artificial conditioning labels to train a classifier. The classifier is then used to self-label real data. To boost the accuracy of the self-labeling, we also use the exponential moving average of the classifier. However, because the classifier might still make mistakes, especially at the beginning of the training, we also refine the labels through self-attention, by using the labeling of real data samples only when the classifier outputs a high classification probability score. We evaluate our approach on CIFAR-10, STL-10 and SVHN, and show that both self-labeling and self-attention consistently improve the quality of generated data. More surprisingly, we find that the proposed scheme can even outperform class-conditional GANs.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/watanabe21a.html
http://proceedings.mlr.press/v139/watanabe21a.htmlRobust Asymmetric Learning in POMDPsPolicies for partially observed Markov decision processes can be efficiently learned by imitating expert policies generated using asymmetric information. Unfortunately, existing approaches for this kind of imitation learning have a serious flaw: the expert does not know what the trainee cannot see, and as a result may encourage actions that are sub-optimal or unsafe under partial information. To address this issue, we derive an update which, when applied iteratively to an expert, maximizes the expected reward of the trainee’s policy. Using this update, we construct a computationally efficient algorithm, adaptive asymmetric DAgger (A2D), that jointly trains the expert and trainee policies. We then show that A2D allows the trainee to safely imitate the modified expert, and outperforms policies learned either by imitating a fixed expert or through direct reinforcement learning.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/warrington21a.html
http://proceedings.mlr.press/v139/warrington21a.htmlInstabilities of Offline RL with Pre-Trained Neural RepresentationIn offline reinforcement learning (RL), we seek to utilize offline data to evaluate (or learn) policies in scenarios where the data are collected from a distribution that substantially differs from that of the target policy to be evaluated. Recent theoretical advances have shown that such sample-efficient offline RL is indeed possible provided certain strong representational conditions hold, else there are lower bounds exhibiting exponential error amplification (in the problem horizon) unless the data collection distribution has only a mild distribution shift relative to the target policy. This work studies these issues from an empirical perspective to gauge how stable offline RL methods are. In particular, our methodology explores these ideas when using features from pre-trained neural networks, in the hope that these representations are powerful enough to permit sample efficient offline RL. Through extensive experiments on a range of tasks, we see that substantial error amplification does occur even when using such pre-trained representations (trained on the same task itself); we find offline RL is stable only under extremely mild distribution shift. The implications of these results, both from a theoretical and an empirical perspective, are that successful offline RL (where we seek to go beyond the low distribution shift regime) requires substantially stronger conditions beyond those which suffice for successful supervised learning.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/wang21z.html
http://proceedings.mlr.press/v139/wang21z.htmlUniSpeech: Unified Speech Representation Learning with Labeled and Unlabeled DataIn this paper, we propose a unified pre-training approach called UniSpeech to learn speech representations with both labeled and unlabeled data, in which supervised phonetic CTC learning and phonetically-aware contrastive self-supervised learning are conducted in a multi-task learning manner. The resultant representations can capture information more correlated with phonetic structures and improve the generalization across languages and domains. We evaluate the effectiveness of UniSpeech for cross-lingual representation learning on public CommonVoice corpus. The results show that UniSpeech outperforms self-supervised pretraining and supervised transfer learning for speech recognition by a maximum of 13.4% and 26.9% relative phone error rate reductions respectively (averaged over all testing languages). The transferability of UniSpeech is also verified on a domain-shift speech recognition task, i.e., a relative word error rate reduction of 6% against the previous approach.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/wang21y.html
http://proceedings.mlr.press/v139/wang21y.htmlMatrix Completion with Model-free WeightingIn this paper, we propose a novel method for matrix completion under general non-uniform missing structures. By controlling an upper bound of a novel balancing error, we construct weights that can actively adjust for the non-uniformity in the empirical risk without explicitly modeling the observation probabilities, and can be computed efficiently via convex optimization. The recovered matrix based on the proposed weighted empirical risk enjoys appealing theoretical guarantees. In particular, the proposed method achieves stronger guarantee than existing work in terms of the scaling with respect to the observation probabilities, under asymptotically heterogeneous missing settings (where entry-wise observation probabilities can be of different orders). These settings can be regarded as a better theoretical model of missing patterns with highly varying probabilities. We also provide a new minimax lower bound under a class of heterogeneous settings. Numerical experiments are also provided to demonstrate the effectiveness of the proposed method.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/wang21x.html
http://proceedings.mlr.press/v139/wang21x.htmlQuantum algorithms for reinforcement learning with a generative modelReinforcement learning studies how an agent should interact with an environment to maximize its cumulative reward. A standard way to study this question abstractly is to ask how many samples an agent needs from the environment to learn an optimal policy for a $\gamma$-discounted Markov decision process (MDP). For such an MDP, we design quantum algorithms that approximate an optimal policy ($\pi^*$), the optimal value function ($v^*$), and the optimal $Q$-function ($q^*$), assuming the algorithms can access samples from the environment in quantum superposition. This assumption is justified whenever there exists a simulator for the environment; for example, if the environment is a video game or some other program. Our quantum algorithms, inspired by value iteration, achieve quadratic speedups over the best-possible classical sample complexities in the approximation accuracy ($\epsilon$) and two main parameters of the MDP: the effective time horizon ($\frac{1}{1-\gamma}$) and the size of the action space ($A$). Moreover, we show that our quantum algorithm for computing $q^*$ is optimal by proving a matching quantum lower bound.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/wang21w.html
http://proceedings.mlr.press/v139/wang21w.htmlSCC: an efficient deep reinforcement learning agent mastering the game of StarCraft IIAlphaStar, the AI that reaches GrandMaster level in StarCraft II, is a remarkable milestone demonstrating what deep reinforcement learning can achieve in complex Real-Time Strategy (RTS) games. However, the complexities of the game, algorithms and systems, and especially the tremendous amount of computation needed are big obstacles for the community to conduct further research in this direction. We propose a deep reinforcement learning agent, StarCraft Commander (SCC). With order of magnitude less computation, it demonstrates top human performance defeating GrandMaster players in test matches and top professional players in a live event. Moreover, it shows strong robustness to various human strategies and discovers novel strategies unseen from human plays. In this paper, we’ll share the key insights and optimizations on efficient imitation learning and reinforcement learning for StarCraft II full game.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/wang21v.html
http://proceedings.mlr.press/v139/wang21v.htmlAn exact solver for the Weston-Watkins SVM subproblemRecent empirical evidence suggests that the Weston-Watkins support vector machine is among the best performing multiclass extensions of the binary SVM. Current state-of-the-art solvers repeatedly solve a particular subproblem approximately using an iterative strategy. In this work, we propose an algorithm that solves the subproblem exactly using a novel reparametrization of the Weston-Watkins dual problem. For linear WW-SVMs, our solver shows significant speed-up over the state-of-the-art solver when the number of classes is large. Our exact subproblem solver also allows us to prove linear convergence of the overall solver.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/wang21u.html
http://proceedings.mlr.press/v139/wang21u.htmlDirectional Bias AmplificationMitigating bias in machine learning systems requires refining our understanding of bias propagation pathways: from societal structures to large-scale data to trained models to impact on society. In this work, we focus on one aspect of the problem, namely bias amplification: the tendency of models to amplify the biases present in the data they are trained on. A metric for measuring bias amplification was introduced in the seminal work by Zhao et al. (2017); however, as we demonstrate, this metric suffers from a number of shortcomings including conflating different types of bias amplification and failing to account for varying base rates of protected attributes. We introduce and analyze a new, decoupled metric for measuring bias amplification, $BiasAmp_{\rightarrow}$ (Directional Bias Amplification). We thoroughly analyze and discuss both the technical assumptions and normative implications of this metric. We provide suggestions about its measurement by cautioning against predicting sensitive attributes, encouraging the use of confidence intervals due to fluctuations in the fairness of models across runs, and discussing the limitations of what this metric captures. Throughout this paper, we work to provide an interrogative look at the technical measurement of bias amplification, guided by our normative ideas of what we want it to encompass. Code is located at https://github.com/princetonvisualai/directional-bias-amp.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/wang21t.html
http://proceedings.mlr.press/v139/wang21t.htmlSketchEmbedNet: Learning Novel Concepts by Imitating DrawingsSketch drawings capture the salient information of visual concepts. Previous work has shown that neural networks are capable of producing sketches of natural objects drawn from a small number of classes. While earlier approaches focus on generation quality or retrieval, we explore properties of image representations learned by training a model to produce sketches of images. We show that this generative, class-agnostic model produces informative embeddings of images from novel examples, classes, and even novel datasets in a few-shot setting. Additionally, we find that these learned representations exhibit interesting structure and compositionality.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/wang21s.html
http://proceedings.mlr.press/v139/wang21s.htmlRobust Learning for Data Poisoning AttacksWe investigate the robustness of stochastic approximation approaches against data poisoning attacks. We focus on two-layer neural networks with ReLU activation and show that under a specific notion of separability in the RKHS induced by the infinite-width network, training (finite-width) networks with stochastic gradient descent is robust against data poisoning attacks. Interestingly, we find that in addition to a lower bound on the width of the network, which is standard in the literature, we also require a distribution-dependent upper bound on the width for robust generalization. We provide extensive empirical evaluations that support and validate our theoretical results.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/wang21r.html
http://proceedings.mlr.press/v139/wang21r.htmlThe Implicit Bias for Adaptive Optimization Algorithms on Homogeneous Neural NetworksDespite their overwhelming capacity to overfit, deep neural networks trained by specific optimization algorithms tend to generalize relatively well to unseen data. Recently, researchers explained it by investigating the implicit bias of optimization algorithms. A remarkable progress is the work (Lyu & Li, 2019), which proves gradient descent (GD) maximizes the margin of homogeneous deep neural networks. Except the first-order optimization algorithms like GD, adaptive algorithms such as AdaGrad, RMSProp and Adam are popular owing to their rapid training process. Mean-while, numerous works have provided empirical evidence that adaptive methods may suffer from poor generalization performance. However, theoretical explanation for the generalization of adaptive optimization algorithms is still lacking. In this paper, we study the implicit bias of adaptive optimization algorithms on homogeneous neural networks. In particular, we study the convergent direction of parameters when they are optimizing the logistic loss. We prove that the convergent direction of Adam and RMSProp is the same as GD, while for AdaGrad, the convergent direction depends on the adaptive conditioner. Technically, we provide a unified framework to analyze convergent direction of adaptive optimization algorithms by constructing novel and nontrivial adaptive gradient flow and surrogate margin. The theoretical findings explain the superiority on generalization of exponential moving average strategy that is adopted by RMSProp and Adam. To the best of knowledge, it is the first work to study the convergent direction of adaptive optimizations on non-linear deep neural networksThu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/wang21q.html
http://proceedings.mlr.press/v139/wang21q.htmlConvexVST: A Convex Optimization Approach to Variance-stabilizing TransformationThe variance-stabilizing transformation (VST) problem is to transform heteroscedastic data to homoscedastic data so that they are more tractable for subsequent analysis. However, most of the existing approaches focus on finding an analytical solution for a certain parametric distribution, which severely limits the applications, because simple distributions cannot faithfully describe the real data while more complicated distributions cannot be analytically solved. In this paper, we converted the VST problem into a convex optimization problem, which can always be efficiently solved, identified the specific structure of the convex problem, which further improved the efficiency of the proposed algorithm, and showed that any finite discrete distributions and the discretized version of any continuous distributions from real data can be variance-stabilized in an easy and nonparametric way. We demonstrated the new approach on bioimaging data and achieved superior performance compared to peer algorithms in terms of not only the variance homoscedasticity but also the impact on subsequent analysis such as denoising. Source codes are available at https://github.com/yu-lab-vt/ConvexVST.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/wang21p.html
http://proceedings.mlr.press/v139/wang21p.htmlOptimal Non-Convex Exact Recovery in Stochastic Block Model via Projected Power MethodIn this paper, we study the problem of exact community recovery in the symmetric stochastic block model, where a graph of $n$ vertices is randomly generated by partitioning the vertices into $K \ge 2$ equal-sized communities and then connecting each pair of vertices with probability that depends on their community memberships. Although the maximum-likelihood formulation of this problem is discrete and non-convex, we propose to tackle it directly using projected power iterations with an initialization that satisfies a partial recovery condition. Such an initialization can be obtained by a host of existing methods. We show that in the logarithmic degree regime of the considered problem, the proposed method can exactly recover the underlying communities at the information-theoretic limit. Moreover, with a qualified initialization, it runs in $\mO(n\log^2n/\log\log n)$ time, which is competitive with existing state-of-the-art methods. We also present numerical results of the proposed method to support and complement our theoretical development.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/wang21o.html
http://proceedings.mlr.press/v139/wang21o.htmlA Modular Analysis of Provable Acceleration via Polyak’s Momentum: Training a Wide ReLU Network and a Deep Linear NetworkIncorporating a so-called “momentum” dynamic in gradient descent methods is widely used in neural net training as it has been broadly observed that, at least empirically, it often leads to significantly faster convergence. At the same time, there are very few theoretical guarantees in the literature to explain this apparent acceleration effect. Even for the classical strongly convex quadratic problems, several existing results only show Polyak’s momentum has an accelerated linear rate asymptotically. In this paper, we first revisit the quadratic problems and show a non-asymptotic accelerated linear rate of Polyak’s momentum. Then, we provably show that Polyak’s momentum achieves acceleration for training a one-layer wide ReLU network and a deep linear network, which are perhaps the two most popular canonical models for studying optimization and deep learning in the literature. Prior works (Du et al. 2019) and (Wu et al. 2019) showed that using vanilla gradient descent, and with an use of over-parameterization, the error decays as $(1- \Theta(\frac{1}{ \kappa’}))^t$ after $t$ iterations, where $\kappa’$ is the condition number of a Gram Matrix. Our result shows that with the appropriate choice of parameters Polyak’s momentum has a rate of $(1-\Theta(\frac{1}{\sqrt{\kappa’}}))^t$. For the deep linear network, prior work (Hu et al. 2020) showed that vanilla gradient descent has a rate of $(1-\Theta(\frac{1}{\kappa}))^t$, where $\kappa$ is the condition number of a data matrix. Our result shows an acceleration rate $(1- \Theta(\frac{1}{\sqrt{\kappa}}))^t$ is achievable by Polyak’s momentum. This work establishes that momentum does indeed speed up neural net training.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/wang21n.html
http://proceedings.mlr.press/v139/wang21n.htmlRobust Inference for High-Dimensional Linear Models via Residual RandomizationWe propose a residual randomization procedure designed for robust inference using Lasso estimates in the high-dimensional setting. Compared to earlier work that focuses on sub-Gaussian errors, the proposed procedure is designed to work robustly in settings that also include heavy-tailed covariates and errors. Moreover, our procedure can be valid under clustered errors, which is important in practice, but has been largely overlooked by earlier work. Through extensive simulations, we illustrate our method’s wider range of applicability as suggested by theory. In particular, we show that our method outperforms state-of-art methods in challenging, yet more realistic, settings where the distribution of covariates is heavy-tailed or the sample size is small, while it remains competitive in standard, “well behaved" settings previously studied in the literature.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/wang21m.html
http://proceedings.mlr.press/v139/wang21m.htmlDeep Generative Learning via Schrödinger BridgeWe propose to learn a generative model via entropy interpolation with a Schr{ö}dinger Bridge. The generative learning task can be formulated as interpolating between a reference distribution and a target distribution based on the Kullback-Leibler divergence. At the population level, this entropy interpolation is characterized via an SDE on [0,1] with a time-varying drift term. At the sample level, we derive our Schr{ö}dinger Bridge algorithm by plugging the drift term estimated by a deep score estimator and a deep density ratio estimator into the Euler-Maruyama method. Under some mild smoothness assumptions of the target distribution, we prove the consistency of both the score estimator and the density ratio estimator, and then establish the consistency of the proposed Schr{ö}dinger Bridge approach. Our theoretical results guarantee that the distribution learned by our approach converges to the target distribution. Experimental results on multimodal synthetic data and benchmark data support our theoretical findings and indicate that the generative model via Schr{ö}dinger Bridge is comparable with state-of-the-art GANs, suggesting a new formulation of generative learning. We demonstrate its usefulness in image interpolation and image inpainting.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/wang21l.html
http://proceedings.mlr.press/v139/wang21l.htmlSG-PALM: a Fast Physically Interpretable Tensor Graphical ModelWe propose a new graphical model inference procedure, called SG-PALM, for learning conditional dependency structure of high-dimensional tensor-variate data. Unlike most other tensor graphical models the proposed model is interpretable and computationally scalable to high dimension. Physical interpretability follows from the Sylvester generative (SG) model on which SG-PALM is based: the model is exact for any observation process that is a solution of a partial differential equation of Poisson type. Scalability follows from the fast proximal alternating linearized minimization (PALM) procedure that SG-PALM uses during training. We establish that SG-PALM converges linearly (i.e., geometric convergence rate) to a global optimum of its objective function. We demonstrate scalability and accuracy of SG-PALM for an important but challenging climate prediction problem: spatio-temporal forecasting of solar flares from multimodal imaging data.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/wang21k.html
http://proceedings.mlr.press/v139/wang21k.htmlGlobal Convergence of Policy Gradient for Linear-Quadratic Mean-Field Control/Game in Continuous TimeRecent years have witnessed the success of multi-agent reinforcement learning, which has motivated new research directions for mean-field control (MFC) and mean-field game (MFG), as the multi-agent system can be well approximated by a mean-field problem when the number of agents grows to be very large. In this paper, we study the policy gradient (PG) method for the linear-quadratic mean-field control and game, where we assume each agent has identical linear state transitions and quadratic cost functions. While most recent works on policy gradient for MFC and MFG are based on discrete-time models, we focus on a continuous-time model where some of our analyzing techniques could be valuable to the interested readers. For both the MFC and the MFG, we provide PG update and show that it converges to the optimal solution at a linear rate, which is verified by a synthetic simulation. For the MFG, we also provide sufficient conditions for the existence and uniqueness of the Nash equilibrium.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/wang21j.html
http://proceedings.mlr.press/v139/wang21j.htmlAlphaNet: Improved Training of Supernets with Alpha-DivergenceWeight-sharing neural architecture search (NAS) is an effective technique for automating efficient neural architecture design. Weight-sharing NAS builds a supernet that assembles all the architectures as its sub-networks and jointly trains the supernet with the sub-networks. The success of weight-sharing NAS heavily relies on distilling the knowledge of the supernet to the sub-networks. However, we find that the widely used distillation divergence, i.e., KL divergence, may lead to student sub-networks that over-estimate or under-estimate the uncertainty of the teacher supernet, leading to inferior performance of the sub-networks. In this work, we propose to improve the supernet training with a more generalized alpha-divergence. By adaptively selecting the alpha-divergence, we simultaneously prevent the over-estimation or under-estimation of the uncertainty of the teacher model. We apply the proposed alpha-divergence based supernets training to both slimmable neural networks and weight-sharing NAS, and demonstrate significant improvements. Specifically, our discovered model family, AlphaNet, outperforms prior-art models on a wide range of FLOPs regimes, including BigNAS, Once-for-All networks, and AttentiveNAS. We achieve ImageNet top-1 accuracy of 80.0% with only 444M FLOPs. Our code and pretrained models are available at https://github.com/facebookresearch/AlphaNet.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/wang21i.html
http://proceedings.mlr.press/v139/wang21i.htmlLabel Distribution Learning MachineAlthough Label Distribution Learning (LDL) has witnessed extensive classification applications, it faces the challenge of objective mismatch – the objective of LDL mismatches that of classification, which has seldom been noticed in existing studies. Our goal is to solve the objective mismatch and improve the classification performance of LDL. Specifically, we extend the margin theory to LDL and propose a new LDL method called \textbf{L}abel \textbf{D}istribution \textbf{L}earning \textbf{M}achine (LDLM). First, we define the label distribution margin and propose the \textbf{S}upport \textbf{V}ector \textbf{R}egression \textbf{M}achine (SVRM) to learn the optimal label. Second, we propose the adaptive margin loss to learn label description degrees. In theoretical analysis, we develop a generalization theory for the SVRM and analyze the generalization of LDLM. Experimental results validate the better classification performance of LDLM.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/wang21h.html
http://proceedings.mlr.press/v139/wang21h.htmlSelf-Tuning for Data-Efficient Deep LearningDeep learning has made revolutionary advances to diverse applications in the presence of large-scale labeled datasets. However, it is prohibitively time-costly and labor-expensive to collect sufficient labeled data in most realistic scenarios. To mitigate the requirement for labeled data, semi-supervised learning (SSL) focuses on simultaneously exploring both labeled and unlabeled data, while transfer learning (TL) popularizes a favorable practice of fine-tuning a pre-trained model to the target data. A dilemma is thus encountered: Without a decent pre-trained model to provide an implicit regularization, SSL through self-training from scratch will be easily misled by inaccurate pseudo-labels, especially in large-sized label space; Without exploring the intrinsic structure of unlabeled data, TL through fine-tuning from limited labeled data is at risk of under-transfer caused by model shift. To escape from this dilemma, we present Self-Tuning to enable data-efficient deep learning by unifying the exploration of labeled and unlabeled data and the transfer of a pre-trained model, as well as a Pseudo Group Contrast (PGC) mechanism to mitigate the reliance on pseudo-labels and boost the tolerance to false labels. Self-Tuning outperforms its SSL and TL counterparts on five tasks by sharp margins, e.g. it doubles the accuracy of fine-tuning on Cars with $15%$ labels.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/wang21g.html
http://proceedings.mlr.press/v139/wang21g.htmlExplainable Automated Graph Representation Learning with Hyperparameter ImportanceCurrent graph representation (GR) algorithms require huge demand of human experts in hyperparameter tuning, which significantly limits their practical applications, leading to an urge for automated graph representation without human intervention. Although automated machine learning (AutoML) serves as a good candidate for automatic hyperparameter tuning, little literature has been reported on automated graph presentation learning and the only existing work employs a black-box strategy, lacking insights into explaining the relative importance of different hyperparameters. To address this issue, we study explainable automated graph representation with hyperparameter importance in this paper. We propose an explainable AutoML approach for graph representation (e-AutoGR) which utilizes explainable graph features during performance estimation and learns decorrelated importance weights for different hyperparameters in affecting the model performance through a non-linear decorrelated weighting regression. These learned importance weights can in turn help to provide more insights in hyperparameter search procedure. We theoretically prove the soundness of the decorrelated weighting algorithm. Extensive experiments on real-world datasets demonstrate the superiority of our proposed e-AutoGR model against state-of-the-art methods in terms of both model performance and hyperparameter importance explainability.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/wang21f.html
http://proceedings.mlr.press/v139/wang21f.htmlAccelerate CNNs from Three Dimensions: A Comprehensive Pruning FrameworkMost neural network pruning methods, such as filter-level and layer-level prunings, prune the network model along one dimension (depth, width, or resolution) solely to meet a computational budget. However, such a pruning policy often leads to excessive reduction of that dimension, thus inducing a huge accuracy loss. To alleviate this issue, we argue that pruning should be conducted along three dimensions comprehensively. For this purpose, our pruning framework formulates pruning as an optimization problem. Specifically, it first casts the relationships between a certain model’s accuracy and depth/width/resolution into a polynomial regression and then maximizes the polynomial to acquire the optimal values for the three dimensions. Finally, the model is pruned along the three optimal dimensions accordingly. In this framework, since collecting too much data for training the regression is very time-costly, we propose two approaches to lower the cost: 1) specializing the polynomial to ensure an accurate regression even with less training data; 2) employing iterative pruning and fine-tuning to collect the data faster. Extensive experiments show that our proposed algorithm surpasses state-of-the-art pruning algorithms and even neural architecture search-based algorithms.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/wang21e.html
http://proceedings.mlr.press/v139/wang21e.htmlFast Algorithms for Stackelberg Prediction Game with Least Squares LossThe Stackelberg prediction game (SPG) has been extensively used to model the interactions between the learner and data provider in the training process of various machine learning algorithms. Particularly, SPGs played prominent roles in cybersecurity applications, such as intrusion detection, banking fraud detection, spam filtering, and malware detection. Often formulated as NP-hard bi-level optimization problems, it is generally computationally intractable to find global solutions to SPGs. As an interesting progress in this area, a special class of SPGs with the least squares loss (SPG-LS) have recently been shown polynomially solvable by a bisection method. However, in each iteration of this method, a semidefinite program (SDP) needs to be solved. The resulted high computational costs prevent its applications for large-scale problems. In contrast, we propose a novel approach that reformulates a SPG-LS as a single SDP of a similar form and the same dimension as those solved in the bisection method. Our SDP reformulation is, evidenced by our numerical experiments, orders of magnitude faster than the existing bisection method. We further show that the obtained SDP can be reduced to a second order cone program (SOCP). This allows us to provide real-time response to large-scale SPG-LS problems. Numerical results on both synthetic and real world datasets indicate that the proposed SOCP method is up to 20,000+ times faster than the state of the art.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/wang21d.html
http://proceedings.mlr.press/v139/wang21d.htmlA Proxy Variable View of Shared ConfoundingCausal inference from observational data can be biased by unobserved confounders. Confounders{—}the variables that affect both the treatments and the outcome{—}induce spurious non-causal correlations between the two. Without additional conditions, unobserved confounders generally make causal quantities hard to identify. In this paper, we focus on the setting where there are many treatments with shared confounding, and we study under what conditions is causal identification possible. The key observation is that we can view subsets of treatments as proxies of the unobserved confounder and identify the intervention distributions of the rest. Moreover, while existing identification formulas for proxy variables involve solving integral equations, we show that one can circumvent the need for such solutions by directly modeling the data. Finally, we extend these results to an expanded class of causal graphs, those with other confounders and selection variables.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/wang21c.html
http://proceedings.mlr.press/v139/wang21c.htmlFairness of Exposure in Stochastic BanditsContextual bandit algorithms have become widely used for recommendation in online systems (e.g. marketplaces, music streaming, news), where they now wield substantial influence on which items get shown to users. This raises questions of fairness to the items — and to the sellers, artists, and writers that benefit from this exposure. We argue that the conventional bandit formulation can lead to an undesirable and unfair winner-takes-all allocation of exposure. To remedy this problem, we propose a new bandit objective that guarantees merit-based fairness of exposure to the items while optimizing utility to the users. We formulate fairness regret and reward regret in this setting and present algorithms for both stochastic multi-armed bandits and stochastic linear bandits. We prove that the algorithms achieve sublinear fairness regret and reward regret. Beyond the theoretical analysis, we also provide empirical evidence that these algorithms can allocate exposure to different arms effectively.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/wang21b.html
http://proceedings.mlr.press/v139/wang21b.htmlTowards Better Laplacian Representation in Reinforcement Learning with Generalized Graph DrawingThe Laplacian representation recently gains increasing attention for reinforcement learning as it provides succinct and informative representation for states, by taking the eigenvectors of the Laplacian matrix of the state-transition graph as state embeddings. Such representation captures the geometry of the underlying state space and is beneficial to RL tasks such as option discovery and reward shaping. To approximate the Laplacian representation in large (or even continuous) state spaces, recent works propose to minimize a spectral graph drawing objective, which however has infinitely many global minimizers other than the eigenvectors. As a result, their learned Laplacian representation may differ from the ground truth. To solve this problem, we reformulate the graph drawing objective into a generalized form and derive a new learning objective, which is proved to have eigenvectors as its unique global minimizer. It enables learning high-quality Laplacian representations that faithfully approximate the ground truth. We validate this via comprehensive experiments on a set of gridworld and continuous control environments. Moreover, we show that our learned Laplacian representations lead to more exploratory options and better reward shaping.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/wang21ae.html
http://proceedings.mlr.press/v139/wang21ae.htmlBridging Multi-Task Learning and Meta-Learning: Towards Efficient Training and Effective AdaptationMulti-task learning (MTL) aims to improve the generalization of several related tasks by learning them jointly. As a comparison, in addition to the joint training scheme, modern meta-learning allows unseen tasks with limited labels during the test phase, in the hope of fast adaptation over them. Despite the subtle difference between MTL and meta-learning in the problem formulation, both learning paradigms share the same insight that the shared structure between existing training tasks could lead to better generalization and adaptation. In this paper, we take one important step further to understand the close connection between these two learning paradigms, through both theoretical analysis and empirical investigation. Theoretically, we first demonstrate that MTL shares the same optimization formulation with a class of gradient-based meta-learning (GBML) algorithms. We then prove that for over-parameterized neural networks with sufficient depth, the learned predictive functions of MTL and GBML are close. In particular, this result implies that the predictions given by these two models are similar over the same unseen task. Empirically, we corroborate our theoretical findings by showing that, with proper implementation, MTL is competitive against state-of-the-art GBML algorithms on a set of few-shot image classification benchmarks. Since existing GBML algorithms often involve costly second-order bi-level optimization, our first-order MTL method is an order of magnitude faster on large-scale datasets such as mini-ImageNet. We believe this work could help bridge the gap between these two learning paradigms, and provide a computationally efficient alternative to GBML that also supports fast task adaptation.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/wang21ad.html
http://proceedings.mlr.press/v139/wang21ad.htmlGuarantees for Tuning the Step Size using a Learning-to-Learn ApproachChoosing the right parameters for optimization algorithms is often the key to their success in practice. Solving this problem using a learning-to-learn approach—using meta-gradient descent on a meta-objective based on the trajectory that the optimizer generates—was recently shown to be effective. However, the meta-optimization problem is difficult. In particular, the meta-gradient can often explode/vanish, and the learned optimizer may not have good generalization performance if the meta-objective is not chosen carefully. In this paper we give meta-optimization guarantees for the learning-to-learn approach on a simple problem of tuning the step size for quadratic loss. Our results show that the naïve objective suffers from meta-gradient explosion/vanishing problem. Although there is a way to design the meta-objective so that the meta-gradient remains polynomially bounded, computing the meta-gradient directly using backpropagation leads to numerical issues. We also characterize when it is necessary to compute the meta-objective on a separate validation set to ensure the generalization performance of the learned optimizer. Finally, we verify our results empirically and show that a similar phenomenon appears even for more complicated learned optimizers parametrized by neural networks.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/wang21ac.html
http://proceedings.mlr.press/v139/wang21ac.htmlEvolving Attention with Residual ConvolutionsTransformer is a ubiquitous model for natural language processing and has attracted wide attentions in computer vision. The attention maps are indispensable for a transformer model to encode the dependencies among input tokens. However, they are learned independently in each layer and sometimes fail to capture precise patterns. In this paper, we propose a novel and generic mechanism based on evolving attention to improve the performance of transformers. On one hand, the attention maps in different layers share common knowledge, thus the ones in preceding layers can instruct the attention in succeeding layers through residual connections. On the other hand, low-level and high-level attentions vary in the level of abstraction, so we adopt convolutional layers to model the evolutionary process of attention maps. The proposed evolving attention mechanism achieves significant performance improvement over various state-of-the-art models for multiple tasks, including image classification, natural language understanding and machine translation.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/wang21ab.html
http://proceedings.mlr.press/v139/wang21ab.htmlLearning to Weight Imperfect DemonstrationsThis paper investigates how to weight imperfect expert demonstrations for generative adversarial imitation learning (GAIL). The agent is expected to perform behaviors demonstrated by experts. But in many applications, experts could also make mistakes and their demonstrations would mislead or slow the learning process of the agent. Recently, existing methods for imitation learning from imperfect demonstrations mostly focus on using the preference or confidence scores to distinguish imperfect demonstrations. However, these auxiliary information needs to be collected with the help of an oracle, which is usually hard and expensive to afford in practice. In contrast, this paper proposes a method of learning to weight imperfect demonstrations in GAIL without imposing extensive prior information. We provide a rigorous mathematical analysis, presenting that the weights of demonstrations can be exactly determined by combining the discriminator and agent policy in GAIL. Theoretical analysis suggests that with the estimated weights the agent can learn a better policy beyond those plain expert demonstrations. Experiments in the Mujoco and Atari environments demonstrate that the proposed algorithm outperforms baseline methods in handling imperfect expert demonstrations.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/wang21aa.html
http://proceedings.mlr.press/v139/wang21aa.htmlZero-Shot Knowledge Distillation from a Decision-Based Black-Box ModelKnowledge distillation (KD) is a successful approach for deep neural network acceleration, with which a compact network (student) is trained by mimicking the softmax output of a pre-trained high-capacity network (teacher). In tradition, KD usually relies on access to the training samples and the parameters of the white-box teacher to acquire the transferred knowledge. However, these prerequisites are not always realistic due to storage costs or privacy issues in real-world applications. Here we propose the concept of decision-based black-box (DB3) knowledge distillation, with which the student is trained by distilling the knowledge from a black-box teacher (parameters are not accessible) that only returns classes rather than softmax outputs. We start with the scenario when the training set is accessible. We represent a sample’s robustness against other classes by computing its distances to the teacher’s decision boundaries and use it to construct the soft label for each training sample. After that, the student can be trained via standard KD. We then extend this approach to a more challenging scenario in which even accessing the training data is not feasible. We propose to generate pseudo samples that are distinguished by the decision boundaries of the DB3 teacher to the largest extent and construct soft labels for these samples, which are used as the transfer set. We evaluate our approaches on various benchmark networks and datasets and experiment results demonstrate their effectiveness.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/wang21a.html
http://proceedings.mlr.press/v139/wang21a.htmlThink Global and Act Local: Bayesian Optimisation over High-Dimensional Categorical and Mixed Search SpacesHigh-dimensional black-box optimisation remains an important yet notoriously challenging problem. Despite the success of Bayesian optimisation methods on continuous domains, domains that are categorical, or that mix continuous and categorical variables, remain challenging. We propose a novel solution—we combine local optimisation with a tailored kernel design, effectively handling high-dimensional categorical and mixed search spaces, whilst retaining sample efficiency. We further derive convergence guarantee for the proposed approach. Finally, we demonstrate empirically that our method outperforms the current baselines on a variety of synthetic and real-world tasks in terms of performance, computational costs, or both.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/wan21b.html
http://proceedings.mlr.press/v139/wan21b.htmlLearning and Planning in Average-Reward Markov Decision ProcessesWe introduce learning and planning algorithms for average-reward MDPs, including 1) the first general proven-convergent off-policy model-free control algorithm without reference states, 2) the first proven-convergent off-policy model-free prediction algorithm, and 3) the first off-policy learning algorithm that converges to the actual value function rather than to the value function plus an offset. All of our algorithms are based on using the temporal-difference error rather than the conventional error when updating the estimate of the average reward. Our proof techniques are a slight generalization of those by Abounadi, Bertsekas, and Borkar (2001). In experiments with an Access-Control Queuing Task, we show some of the difficulties that can arise when using methods that rely on reference states and argue that our new algorithms are significantly easier to use.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/wan21a.html
http://proceedings.mlr.press/v139/wan21a.htmlTask-Optimal Exploration in Linear Dynamical SystemsExploration in unknown environments is a fundamental problem in reinforcement learning and control. In this work, we study task-guided exploration and determine what precisely an agent must learn about their environment in order to complete a particular task. Formally, we study a broad class of decision-making problems in the setting of linear dynamical systems, a class that includes the linear quadratic regulator problem. We provide instance- and task-dependent lower bounds which explicitly quantify the difficulty of completing a task of interest. Motivated by our lower bound, we propose a computationally efficient experiment-design based exploration algorithm. We show that it optimally explores the environment, collecting precisely the information needed to complete the task, and provide finite-time bounds guaranteeing that it achieves the instance- and task-optimal sample complexity, up to constant factors. Through several examples of the linear quadratic regulator problem, we show that performing task-guided exploration provably improves on exploration schemes which do not take into account the task of interest. Along the way, we establish that certainty equivalence decision making is instance- and task-optimal, and obtain the first algorithm for the linear quadratic regulator problem which is instance-optimal. We conclude with several experiments illustrating the effectiveness of our approach in practice.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/wagenmaker21a.html
http://proceedings.mlr.press/v139/wagenmaker21a.htmlSafe Reinforcement Learning Using Advantage-Based InterventionMany sequential decision problems involve finding a policy that maximizes total reward while obeying safety constraints. Although much recent research has focused on the development of safe reinforcement learning (RL) algorithms that produce a safe policy after training, ensuring safety during training as well remains an open problem. A fundamental challenge is performing exploration while still satisfying constraints in an unknown Markov decision process (MDP). In this work, we address this problem for the chance-constrained setting.We propose a new algorithm, SAILR, that uses an intervention mechanism based on advantage functions to keep the agent safe throughout training and optimizes the agent’s policy using off-the-shelf RL algorithms designed for unconstrained MDPs. Our method comes with strong guarantees on safety during "both" training and deployment (i.e., after training and without the intervention mechanism) and policy performance compared to the optimal safety-constrained policy. In our experiments, we show that SAILR violates constraints far less during training than standard safe RL and constrained MDP approaches and converges to a well-performing policy that can be deployed safely without intervention. Our code is available at https://github.com/nolanwagener/safe_rl.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/wagener21a.html
http://proceedings.mlr.press/v139/wagener21a.htmlWhitening and Second Order Optimization Both Make Information in the Dataset Unusable During Training, and Can Reduce or Prevent GeneralizationMachine learning is predicated on the concept of generalization: a model achieving low error on a sufficiently large training set should also perform well on novel samples from the same distribution. We show that both data whitening and second order optimization can harm or entirely prevent generalization. In general, model training harnesses information contained in the sample-sample second moment matrix of a dataset. For a general class of models, namely models with a fully connected first layer, we prove that the information contained in this matrix is the only information which can be used to generalize. Models trained using whitened data, or with certain second order optimization schemes, have less access to this information, resulting in reduced or nonexistent generalization ability. We experimentally verify these predictions for several architectures, and further demonstrate that generalization continues to be harmed even when theoretical requirements are relaxed. However, we also show experimentally that regularized second order optimization can provide a practical tradeoff, where training is accelerated but less information is lost, and generalization can in some circumstances even improve.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/wadia21a.html
http://proceedings.mlr.press/v139/wadia21a.htmlPrincipal Component Hierarchy for Sparse Quadratic ProgramsWe propose a novel approximation hierarchy for cardinality-constrained, convex quadratic programs that exploits the rank-dominating eigenvectors of the quadratic matrix. Each level of approximation admits a min-max characterization whose objective function can be optimized over the binary variables analytically, while preserving convexity in the continuous variables. Exploiting this property, we propose two scalable optimization algorithms, coined as the “best response" and the “dual program", that can efficiently screen the potential indices of the nonzero elements of the original program. We show that the proposed methods are competitive with the existing screening methods in the current sparse regression literature, and it is particularly fast on instances with high number of measurements in experiments with both synthetic and real datasets.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/vreugdenhil21a.html
http://proceedings.mlr.press/v139/vreugdenhil21a.htmlObject Segmentation Without Labels with Large-Scale Generative ModelsThe recent rise of unsupervised and self-supervised learning has dramatically reduced the dependency on labeled data, providing high-quality representations for transfer on downstream tasks. Furthermore, recent works also employed these representations in a fully unsupervised setup for image classification, reducing the need for human labels on the fine-tuning stage as well. This work demonstrates that large-scale unsupervised models can also perform a more challenging object segmentation task, requiring neither pixel-level nor image-level labeling. Namely, we show that recent unsupervised GANs allow to differentiate between foreground/background pixels, providing high-quality saliency masks. By extensive comparison on common benchmarks, we outperform existing unsupervised alternatives for object segmentation, achieving new state-of-the-art.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/voynov21a.html
http://proceedings.mlr.press/v139/voynov21a.htmlEfficient Training of Robust Decision Trees Against Adversarial ExamplesCurrent state-of-the-art algorithms for training robust decision trees have high runtime costs and require hours to run. We present GROOT, an efficient algorithm for training robust decision trees and random forests that runs in a matter of seconds to minutes. Where before the worst-case Gini impurity was computed iteratively, we find that we can solve this function analytically to improve time complexity from O(n) to O(1) in terms of n samples. Our results on both single trees and ensembles on 14 structured datasets as well as on MNIST and Fashion-MNIST demonstrate that GROOT runs several orders of magnitude faster than the state-of-the-art works and also shows better performance in terms of adversarial accuracy on structured data.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/vos21a.html
http://proceedings.mlr.press/v139/vos21a.htmlNeuro-algorithmic Policies Enable Fast Combinatorial GeneralizationAlthough model-based and model-free approaches to learning the control of systems have achieved impressive results on standard benchmarks, generalization to task variations is still lacking. Recent results suggest that generalization for standard architectures improves only after obtaining exhaustive amounts of data. We give evidence that generalization capabilities are in many cases bottlenecked by the inability to generalize on the combinatorial aspects of the problem. We show that, for a certain subclass of the MDP framework, this can be alleviated by a neuro-algorithmic policy architecture that embeds a time-dependent shortest path solver in a deep neural network. Trained end-to-end via blackbox-differentiation, this method leads to considerable improvement in generalization capabilities in the low-data regime.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/vlastelica21a.html
http://proceedings.mlr.press/v139/vlastelica21a.htmlOnline Graph Dictionary LearningDictionary learning is a key tool for representation learning, that explains the data as linear combination of few basic elements. Yet, this analysis is not amenable in the context of graph learning, as graphs usually belong to different metric spaces. We fill this gap by proposing a new online Graph Dictionary Learning approach, which uses the Gromov Wasserstein divergence for the data fitting term. In our work, graphs are encoded through their nodes’ pairwise relations and modeled as convex combination of graph atoms, i.e. dictionary elements, estimated thanks to an online stochastic algorithm, which operates on a dataset of unregistered graphs with potentially different number of nodes. Our approach naturally extends to labeled graphs, and is completed by a novel upper bound that can be used as a fast approximation of Gromov Wasserstein in the embedding space. We provide numerical evidences showing the interest of our approach for unsupervised embedding of graph datasets and for online graph subspace estimation and tracking.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/vincent-cuaz21a.html
http://proceedings.mlr.press/v139/vincent-cuaz21a.htmlUnbiased Gradient Estimation in Unrolled Computation Graphs with Persistent Evolution StrategiesUnrolled computation graphs arise in many scenarios, including training RNNs, tuning hyperparameters through unrolled optimization, and training learned optimizers. Current approaches to optimizing parameters in such computation graphs suffer from high variance gradients, bias, slow updates, or large memory usage. We introduce a method called Persistent Evolution Strategies (PES), which divides the computation graph into a series of truncated unrolls, and performs an evolution strategies-based update step after each unroll. PES eliminates bias from these truncations by accumulating correction terms over the entire sequence of unrolls. PES allows for rapid parameter updates, has low memory usage, is unbiased, and has reasonable variance characteristics. We experimentally demonstrate the advantages of PES compared to several other methods for gradient estimation on synthetic tasks, and show its applicability to training learned optimizers and tuning hyperparameters.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/vicol21a.html
http://proceedings.mlr.press/v139/vicol21a.htmlSparsifying Networks via Subdifferential InclusionSparsifying deep neural networks is of paramount interest in many areas, especially when those networks have to be implemented on low-memory devices. In this article, we propose a new formulation of the problem of generating sparse weights for a pre-trained neural network. By leveraging the properties of standard nonlinear activation functions, we show that the problem is equivalent to an approximate subdifferential inclusion problem. The accuracy of the approximation controls the sparsity. We show that the proposed approach is valid for a broad class of activation functions (ReLU, sigmoid, softmax). We propose an iterative optimization algorithm to induce sparsity whose convergence is guaranteed. Because of the algorithm flexibility, the sparsity can be ensured from partial training data in a minibatch manner. To demonstrate the effectiveness of our method, we perform experiments on various networks in different applicative contexts: image classification, speech recognition, natural language processing, and time-series forecasting.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/verma21b.html
http://proceedings.mlr.press/v139/verma21b.htmlTowards Domain-Agnostic Contrastive LearningDespite recent successes, most contrastive self-supervised learning methods are domain-specific, relying heavily on data augmentation techniques that require knowledge about a particular domain, such as image cropping and rotation. To overcome such limitation, we propose a domain-agnostic approach to contrastive learning, named DACL, that is applicable to problems where domain-specific data augmentations are not readily available. Key to our approach is the use of Mixup noise to create similar and dissimilar examples by mixing data samples differently either at the input or hidden-state levels. We theoretically analyze our method and show advantages over the Gaussian-noise based contrastive learning approach. To demonstrate the effectiveness of DACL, we conduct experiments across various domains such as tabular data, images, and graphs. Our results show that DACL not only outperforms other domain-agnostic noising methods, such as Gaussian-noise, but also combines well with domain-specific methods, such as SimCLR, to improve self-supervised visual representation learning.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/verma21a.html
http://proceedings.mlr.press/v139/verma21a.htmlCURI: A Benchmark for Productive Concept Learning Under UncertaintyHumans can learn and reason under substantial uncertainty in a space of infinitely many compositional, productive concepts. For example, if a scene with two blue spheres qualifies as “daxy,” one can reason that the underlying concept may require scenes to have “only blue spheres” or “only spheres” or “only two objects.” In contrast, standard benchmarks for compositional reasoning do not explicitly capture a notion of reasoning under uncertainty or evaluate compositional concept acquisition. We introduce a new benchmark, Compositional Reasoning Under Uncertainty (CURI) that instantiates a series of few-shot, meta-learning tasks in a productive concept space to evaluate different aspects of systematic generalization under uncertainty, including splits that test abstract understandings of disentangling, productive generalization, learning boolean operations, variable binding, etc. Importantly, we also contribute a model-independent “compositionality gap” to evaluate the difficulty of generalizing out-of-distribution along each of these axes, allowing objective comparison of the difficulty of each compositional split. Evaluations across a range of modeling choices and splits reveal substantial room for improvement on the proposed benchmark.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/vedantam21a.html
http://proceedings.mlr.press/v139/vedantam21a.htmlActive Deep Probabilistic SubsamplingSubsampling a signal of interest can reduce costly data transfer, battery drain, radiation exposure and acquisition time in a wide range of problems. The recently proposed Deep Probabilistic Subsampling (DPS) method effectively integrates subsampling in an end-to-end deep learning model, but learns a static pattern for all datapoints. We generalize DPS to a sequential method that actively picks the next sample based on the information acquired so far; dubbed Active-DPS (A-DPS). We validate that A-DPS improves over DPS for MNIST classification at high subsampling rates. Moreover, we demonstrate strong performance in active acquisition Magnetic Resonance Image (MRI) reconstruction, outperforming DPS and other deep learning methods.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/van-gorp21a.html
http://proceedings.mlr.press/v139/van-gorp21a.htmlLTL2Action: Generalizing LTL Instructions for Multi-Task RLWe address the problem of teaching a deep reinforcement learning (RL) agent to follow instructions in multi-task environments. Instructions are expressed in a well-known formal language {–} linear temporal logic (LTL) {–} and can specify a diversity of complex, temporally extended behaviours, including conditionals and alternative realizations. Our proposed learning approach exploits the compositional syntax and the semantics of LTL, enabling our RL agent to learn task-conditioned policies that generalize to new instructions, not observed during training. To reduce the overhead of learning LTL semantics, we introduce an environment-agnostic LTL pretraining scheme which improves sample-efficiency in downstream environments. Experiments on discrete and continuous domains target combinatorial task sets of up to $\sim10^{39}$ unique tasks and demonstrate the strength of our approach in learning to solve (unseen) tasks, given LTL instructions.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/vaezipoor21a.html
http://proceedings.mlr.press/v139/vaezipoor21a.htmlSGLB: Stochastic Gradient Langevin BoostingThis paper introduces Stochastic Gradient Langevin Boosting (SGLB) - a powerful and efficient machine learning framework that may deal with a wide range of loss functions and has provable generalization guarantees. The method is based on a special form of the Langevin diffusion equation specifically designed for gradient boosting. This allows us to theoretically guarantee the global convergence even for multimodal loss functions, while standard gradient boosting algorithms can guarantee only local optimum. We also empirically show that SGLB outperforms classic gradient boosting when applied to classification tasks with 0-1 loss function, which is known to be multimodal.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/ustimenko21a.html
http://proceedings.mlr.press/v139/ustimenko21a.htmlFast Projection Onto Convex Smooth ConstraintsThe Euclidean projection onto a convex set is an important problem that arises in numerous constrained optimization tasks. Unfortunately, in many cases, computing projections is computationally demanding. In this work, we focus on projection problems where the constraints are smooth and the number of constraints is significantly smaller than the dimension. The runtime of existing approaches to solving such problems is either cubic in the dimension or polynomial in the inverse of the target accuracy. Conversely, we propose a simple and efficient primal-dual approach, with a runtime that scales only linearly with the dimension, and only logarithmically in the inverse of the target accuracy. We empirically demonstrate its performance, and compare it with standard baselines.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/usmanova21a.html
http://proceedings.mlr.press/v139/usmanova21a.htmlA Framework for Private Matrix Analysis in Sliding Window ModelWe perform a rigorous study of private matrix analysis when only the last $W$ updates to matrices are considered useful for analysis. We show the existing framework in the non-private setting is not robust to noise required for privacy. We then propose a framework robust to noise and use it to give first efficient $o(W)$ space differentially private algorithms for spectral approximation, principal component analysis (PCA), multi-response linear regression, sparse PCA, and non-negative PCA. Prior to our work, no such result was known for sparse and non-negative differentially private PCA even in the static data setting. We also give a lower bound to demonstrate the cost of privacy in the sliding window model.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/upadhyay21a.html
http://proceedings.mlr.press/v139/upadhyay21a.htmlPixelTransformer: Sample Conditioned Signal GenerationWe propose a generative model that can infer a distribution for the underlying spatial signal conditioned on sparse samples e.g. plausible images given a few observed pixels. In contrast to sequential autoregressive generative models, our model allows conditioning on arbitrary samples and can answer distributional queries for any location. We empirically validate our approach across three image datasets and show that we learn to generate diverse and meaningful samples, with the distribution variance reducing given more observed pixels. We also show that our approach is applicable beyond images and can allow generating other types of spatial outputs e.g. polynomials, 3D shapes, and videos.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/tulsiani21a.html
http://proceedings.mlr.press/v139/tulsiani21a.htmlCumulants of Hawkes Processes are Robust to Observation NoiseMultivariate Hawkes processes (MHPs) are widely used in a variety of fields to model the occurrence of causally related discrete events in continuous time. Most state-of-the-art approaches address the problem of learning MHPs from perfect traces without noise. In practice, the process through which events are collected might introduce noise in the timestamps. In this work, we address the problem of learning the causal structure of MHPs when the observed timestamps of events are subject to random and unknown shifts, also known as random translations. We prove that the cumulants of MHPs are invariant to random translations, and therefore can be used to learn their underlying causal structure. Furthermore, we empirically characterize the effect of random translations on state-of-the-art learning methods. We show that maximum likelihood-based estimators are brittle, while cumulant-based estimators remain stable even in the presence of significant time shifts.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/trouleau21a.html
http://proceedings.mlr.press/v139/trouleau21a.htmlProvable Meta-Learning of Linear RepresentationsMeta-learning, or learning-to-learn, seeks to design algorithms that can utilize previous experience to rapidly learn new skills or adapt to new environments. Representation learning—a key tool for performing meta-learning—learns a data representation that can transfer knowledge across multiple tasks, which is essential in regimes where data is scarce. Despite a recent surge of interest in the practice of meta-learning, the theoretical underpinnings of meta-learning algorithms are lacking, especially in the context of learning transferable representations. In this paper, we focus on the problem of multi-task linear regression—in which multiple linear regression models share a common, low-dimensional linear representation. Here, we provide provably fast, sample-efficient algorithms to address the dual challenges of (1) learning a common set of features from multiple, related tasks, and (2) transferring this knowledge to new, unseen tasks. Both are central to the general problem of meta-learning. Finally, we complement these results by providing information-theoretic lower bounds on the sample complexity of learning these linear features.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/tripuraneni21a.html
http://proceedings.mlr.press/v139/tripuraneni21a.htmlLearning a Universal Template for Few-shot Dataset GeneralizationFew-shot dataset generalization is a challenging variant of the well-studied few-shot classification problem where a diverse training set of several datasets is given, for the purpose of training an adaptable model that can then learn classes from \emph{new datasets} using only a few examples. To this end, we propose to utilize the diverse training set to construct a \emph{universal template}: a partial model that can define a wide array of dataset-specialized models, by plugging in appropriate components. For each new few-shot classification problem, our approach therefore only requires inferring a small number of parameters to insert into the universal template. We design a separate network that produces an initialization of those parameters for each given task, and we then fine-tune its proposed initialization via a few steps of gradient descent. Our approach is more parameter-efficient, scalable and adaptable compared to previous methods, and achieves the state-of-the-art on the challenging Meta-Dataset benchmark.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/triantafillou21a.html
http://proceedings.mlr.press/v139/triantafillou21a.htmlA New Formalism, Method and Open Issues for Zero-Shot CoordinationIn many coordination problems, independently reasoning humans are able to discover mutually compatible policies. In contrast, independently trained self-play policies are often mutually incompatible. Zero-shot coordination (ZSC) has recently been proposed as a new frontier in multi-agent reinforcement learning to address this fundamental issue. Prior work approaches the ZSC problem by assuming players can agree on a shared learning algorithm but not on labels for actions and observations, and proposes other-play as an optimal solution. However, until now, this “label-free” problem has only been informally defined. We formalize this setting as the label-free coordination (LFC) problem by defining the label-free coordination game. We show that other-play is not an optimal solution to the LFC problem as it fails to consistently break ties between incompatible maximizers of the other-play objective. We introduce an extension of the algorithm, other-play with tie-breaking, and prove that it is optimal in the LFC problem and an equilibrium in the LFC game. Since arbitrary tie-breaking is precisely what the ZSC setting aims to prevent, we conclude that the LFC problem does not reflect the aims of ZSC. To address this, we introduce an alternative informal operationalization of ZSC as a starting point for future work.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/treutlein21a.html
http://proceedings.mlr.press/v139/treutlein21a.htmlOn Disentangled Representations Learned from Correlated DataThe focus of disentanglement approaches has been on identifying independent factors of variation in data. However, the causal variables underlying real-world observations are often not statistically independent. In this work, we bridge the gap to real-world scenarios by analyzing the behavior of the most prominent disentanglement approaches on correlated data in a large-scale empirical study (including 4260 models). We show and quantify that systematically induced correlations in the dataset are being learned and reflected in the latent representations, which has implications for downstream applications of disentanglement such as fairness. We also demonstrate how to resolve these latent correlations, either using weak supervision during training or by post-hoc correcting a pre-trained model with a small number of labels.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/trauble21a.html
http://proceedings.mlr.press/v139/trauble21a.htmlSMG: A Shuffling Gradient-Based Method with MomentumWe combine two advanced ideas widely used in optimization for machine learning: \textit{shuffling} strategy and \textit{momentum} technique to develop a novel shuffling gradient-based method with momentum, coined \textbf{S}huffling \textbf{M}omentum \textbf{G}radient (SMG), for non-convex finite-sum optimization problems. While our method is inspired by momentum techniques, its update is fundamentally different from existing momentum-based methods. We establish state-of-the-art convergence rates of SMG for any shuffling strategy using either constant or diminishing learning rate under standard assumptions (i.e. \textit{$L$-smoothness} and \textit{bounded variance}). When the shuffling strategy is fixed, we develop another new algorithm that is similar to existing momentum methods, and prove the same convergence rates for this algorithm under the $L$-smoothness and bounded gradient assumptions. We demonstrate our algorithms via numerical simulations on standard datasets and compare them with existing shuffling methods. Our tests have shown encouraging performance of the new algorithms.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/tran21b.html
http://proceedings.mlr.press/v139/tran21b.htmlSparse within Sparse Gaussian Processes using Neighbor InformationApproximations to Gaussian processes (GPs) based on inducing variables, combined with variational inference techniques, enable state-of-the-art sparse approaches to infer GPs at scale through mini-batch based learning. In this work, we further push the limits of scalability of sparse GPs by allowing large number of inducing variables without imposing a special structure on the inducing inputs. In particular, we introduce a novel hierarchical prior, which imposes sparsity on the set of inducing variables. We treat our model variationally, and we experimentally show considerable computational gains compared to standard sparse GPs when sparsity on the inducing variables is realized considering the nearest inducing inputs of a random mini-batch of the data. We perform an extensive experimental validation that demonstrates the effectiveness of our approach compared to the state-of-the-art. Our approach enables the possibility to use sparse GPs using a large number of inducing points without incurring a prohibitive computational cost.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/tran21a.html
http://proceedings.mlr.press/v139/tran21a.htmlBayesian Optimistic Optimisation with Exponentially Decaying RegretBayesian optimisation (BO) is a well known algorithm for finding the global optimum of expensive, black-box functions. The current practical BO algorithms have regret bounds ranging from $\mathcal{O}(\frac{logN}{\sqrt{N}})$ to $\mathcal O(e^{-\sqrt{N}})$, where $N$ is the number of evaluations. This paper explores the possibility of improving the regret bound in the noise-free setting by intertwining concepts from BO and optimistic optimisation methods which are based on partitioning the search space. We propose the BOO algorithm, a first practical approach which can achieve an exponential regret bound with order $\mathcal O(N^{-\sqrt{N}})$ under the assumption that the objective function is sampled from a Gaussian process with a Matérn kernel with smoothness parameter $\nu > 4 +\frac{D}{2}$, where $D$ is the number of dimensions. We perform experiments on optimisation of various synthetic functions and machine learning hyperparameter tuning tasks and show that our algorithm outperforms baselines.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/tran-the21a.html
http://proceedings.mlr.press/v139/tran-the21a.htmlConservative Objective Models for Effective Offline Model-Based OptimizationIn this paper, we aim to solve data-driven model-based optimization (MBO) problems, where the goal is to find a design input that maximizes an unknown objective function provided access to only a static dataset of inputs and their corresponding objective values. Such data-driven optimization procedures are the only practical methods in many real-world domains where active data collection is expensive (e.g., when optimizing over proteins) or dangerous (e.g., when optimizing over aircraft designs, actively evaluating malformed aircraft designs is unsafe). Typical methods for MBO that optimize the input against a learned model of the unknown score function are affected by erroneous overestimation in the learned model caused due to distributional shift, that drives the optimizer to low-scoring or invalid inputs. To overcome this, we propose conservative objective models (COMs), a method that learns a model of the objective function which lower bounds the actual value of the ground-truth objective on out-of-distribution inputs and uses it for optimization. In practice, COMs outperform a number existing methods on a wide range of MBO problems, including optimizing controller parameters, robot morphologies, and superconducting materials.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/trabucco21a.html
http://proceedings.mlr.press/v139/trabucco21a.htmlTraining data-efficient image transformers & distillation through attentionRecently, neural networks purely based on attention were shown to address image understanding tasks such as image classification. These high-performing vision transformers are pre-trained with hundreds of millions of images using a large infrastructure, thereby limiting their adoption. In this work, we produce competitive convolution-free transformers trained on ImageNet only using a single computer in less than 3 days. Our reference vision transformer (86M parameters) achieves top-1 accuracy of 83.1% (single-crop) on ImageNet with no external data. We also introduce a teacher-student strategy specific to transformers. It relies on a distillation token ensuring that the student learns from the teacher through attention, typically from a convnet teacher. The learned transformers are competitive (85.2% top-1 acc.) with the state of the art on ImageNet, and similarly when transferred to other tasks. We will share our code and models.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/touvron21a.html
http://proceedings.mlr.press/v139/touvron21a.htmlDiffusion Earth Mover’s Distance and Distribution EmbeddingsWe propose a new fast method of measuring distances between large numbers of related high dimensional datasets called the Diffusion Earth Mover’s Distance (EMD). We model the datasets as distributions supported on common data graph that is derived from the affinity matrix computed on the combined data. In such cases where the graph is a discretization of an underlying Riemannian closed manifold, we prove that Diffusion EMD is topologically equivalent to the standard EMD with a geodesic ground distance. Diffusion EMD can be computed in {Õ}(n) time and is more accurate than similarly fast algorithms such as tree-based EMDs. We also show Diffusion EMD is fully differentiable, making it amenable to future uses in gradient-descent frameworks such as deep neural networks. Finally, we demonstrate an application of Diffusion EMD to single cell data collected from 210 COVID-19 patient samples at Yale New Haven Hospital. Here, Diffusion EMD can derive distances between patients on the manifold of cells at least two orders of magnitude faster than equally accurate methods. This distance matrix between patients can be embedded into a higher level patient manifold which uncovers structure and heterogeneity in patients. More generally, Diffusion EMD is applicable to all datasets that are massively collected in parallel in many medical and biological systems.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/tong21a.html
http://proceedings.mlr.press/v139/tong21a.htmlDeep Continuous NetworksCNNs and computational models of biological vision share some fundamental principles, which opened new avenues of research. However, fruitful cross-field research is hampered by conventional CNN architectures being based on spatially and depthwise discrete representations, which cannot accommodate certain aspects of biological complexity such as continuously varying receptive field sizes and dynamics of neuronal responses. Here we propose deep continuous networks (DCNs), which combine spatially continuous filters, with the continuous depth framework of neural ODEs. This allows us to learn the spatial support of the filters during training, as well as model the continuous evolution of feature maps, linking DCNs closely to biological models. We show that DCNs are versatile and highly applicable to standard image classification and reconstruction problems, where they improve parameter and data efficiency, and allow for meta-parametrization. We illustrate the biological plausibility of the scale distributions learned by DCNs and explore their performance in a neuroscientifically inspired pattern completion task. Finally, we investigate an efficient implementation of DCNs by changing input contrast.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/tomen21a.html
http://proceedings.mlr.press/v139/tomen21a.htmlProbabilistic Programs with Stochastic ConditioningWe tackle the problem of conditioning probabilistic programs on distributions of observable variables. Probabilistic programs are usually conditioned on samples from the joint data distribution, which we refer to as deterministic conditioning. However, in many real-life scenarios, the observations are given as marginal distributions, summary statistics, or samplers. Conventional probabilistic programming systems lack adequate means for modeling and inference in such scenarios. We propose a generalization of deterministic conditioning to stochastic conditioning, that is, conditioning on the marginal distribution of a variable taking a particular form. To this end, we first define the formal notion of stochastic conditioning and discuss its key properties. We then show how to perform inference in the presence of stochastic conditioning. We demonstrate potential usage of stochastic conditioning on several case studies which involve various kinds of stochastic conditioning and are difficult to solve otherwise. Although we present stochastic conditioning in the context of probabilistic programming, our formalization is general and applicable to other settings.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/tolpin21a.html
http://proceedings.mlr.press/v139/tolpin21a.htmlNonparametric Decomposition of Sparse TensorsTensor decomposition is a powerful framework for multiway data analysis. Despite the success of existing approaches, they ignore the sparse nature of the tensor data in many real-world applications, explicitly or implicitly assuming dense tensors. To address this model misspecification and to exploit the sparse tensor structures, we propose Nonparametric dEcomposition of Sparse Tensors (\ours), which can capture both the sparse structure properties and complex relationships between the tensor nodes to enhance the embedding estimation. Specifically, we first use completely random measures to construct tensor-valued random processes. We prove that the entry growth is much slower than that of the corresponding tensor size, which implies sparsity. Given finite observations (\ie projections), we then propose two nonparametric decomposition models that couple Dirichlet processes and Gaussian processes to jointly sample the sparse entry indices and the entry values (the latter as a nonlinear mapping of the embeddings), so as to encode both the structure properties and nonlinear relationships of the tensor nodes into the embeddings. Finally, we use the stick-breaking construction and random Fourier features to develop a scalable, stochastic variational learning algorithm. We show the advantage of our approach in sparse tensor generation, and entry index and value prediction in several real-world applications.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/tillinghast21a.html
http://proceedings.mlr.press/v139/tillinghast21a.htmlBORE: Bayesian Optimization by Density-Ratio EstimationBayesian optimization (BO) is among the most effective and widely-used blackbox optimization methods. BO proposes solutions according to an explore-exploit trade-off criterion encoded in an acquisition function, many of which are computed from the posterior predictive of a probabilistic surrogate model. Prevalent among these is the expected improvement (EI). The need to ensure analytical tractability of the predictive often poses limitations that can hinder the efficiency and applicability of BO. In this paper, we cast the computation of EI as a binary classification problem, building on the link between class-probability estimation and density-ratio estimation, and the lesser-known link between density-ratios and EI. By circumventing the tractability constraints, this reformulation provides numerous advantages, not least in terms of expressiveness, versatility, and scalability.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/tiao21a.html
http://proceedings.mlr.press/v139/tiao21a.htmlOnline Learning in Unknown Markov GamesWe study online learning in unknown Markov games, a problem that arises in episodic multi-agent reinforcement learning where the actions of the opponents are unobservable. We show that in this challenging setting, achieving sublinear regret against the best response in hindsight is statistically hard. We then consider a weaker notion of regret by competing with the \emph{minimax value} of the game, and present an algorithm that achieves a sublinear $\tilde{\mathcal{O}}(K^{2/3})$ regret after $K$ episodes. This is the first sublinear regret bound (to our knowledge) for online learning in unknown Markov games. Importantly, our regret bound is independent of the size of the opponents’ action spaces. As a result, even when the opponents’ actions are fully observable, our regret bound improves upon existing analysis (e.g., (Xie et al., 2020)) by an exponential factor in the number of opponents.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/tian21b.html
http://proceedings.mlr.press/v139/tian21b.htmlUnderstanding self-supervised learning dynamics without contrastive pairsWhile contrastive approaches of self-supervised learning (SSL) learn representations by minimizing the distance between two augmented views of the same data point (positive pairs) and maximizing views from different data points (negative pairs), recent \emph{non-contrastive} SSL (e.g., BYOL and SimSiam) show remarkable performance {\it without} negative pairs, with an extra learnable predictor and a stop-gradient operation. A fundamental question rises: why they do not collapse into trivial representation? In this paper, we answer this question via a simple theoretical study and propose a novel approach, \ourmethod{}, that \emph{directly} sets the linear predictor based on the statistics of its inputs, rather than trained with gradient update. On ImageNet, it performs comparably with more complex two-layer non-linear predictors that employ BatchNorm and outperforms linear predictor by $2.5%$ in 300-epoch training (and $5%$ in 60-epoch). \ourmethod{} is motivated by our theoretical study of the nonlinear learning dynamics of non-contrastive SSL in simple linear networks. Our study yields conceptual insights into how non-contrastive SSL methods learn, how they avoid representational collapse, and how multiple factors, like predictor networks, stop-gradients, exponential moving averages, and weight decay all come into play. Our simple theory recapitulates the results of real-world ablation studies in both STL-10 and ImageNet. Code is released\footnote{\url{https://github.com/facebookresearch/luckmatters/tree/master/ssl}}.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/tian21a.html
http://proceedings.mlr.press/v139/tian21a.htmlEfficient Generative Modelling of Protein Structure Fragments using a Deep Markov ModelFragment libraries are often used in protein structure prediction, simulation and design as a means to significantly reduce the vast conformational search space. Current state-of-the-art methods for fragment library generation do not properly account for aleatory and epistemic uncertainty, respectively due to the dynamic nature of proteins and experimental errors in protein structures. Additionally, they typically rely on information that is not generally or readily available, such as homologous sequences, related protein structures and other complementary information. To address these issues, we developed BIFROST, a novel take on the fragment library problem based on a Deep Markov Model architecture combined with directional statistics for angular degrees of freedom, implemented in the deep probabilistic programming language Pyro. BIFROST is a probabilistic, generative model of the protein backbone dihedral angles conditioned solely on the amino acid sequence. BIFROST generates fragment libraries with a quality on par with current state-of-the-art methods at a fraction of the run-time, while requiring considerably less information and allowing efficient evaluation of probabilities.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/thygesen21a.html
http://proceedings.mlr.press/v139/thygesen21a.htmlMonte Carlo Variational Auto-EncodersVariational auto-encoders (VAE) are popular deep latent variable models which are trained by maximizing an Evidence Lower Bound (ELBO). To obtain tighter ELBO and hence better variational approximations, it has been proposed to use importance sampling to get a lower variance estimate of the evidence. However, importance sampling is known to perform poorly in high dimensions. While it has been suggested many times in the literature to use more sophisticated algorithms such as Annealed Importance Sampling (AIS) and its Sequential Importance Sampling (SIS) extensions, the potential benefits brought by these advanced techniques have never been realized for VAE: the AIS estimate cannot be easily differentiated, while SIS requires the specification of carefully chosen backward Markov kernels. In this paper, we address both issues and demonstrate the performance of the resulting Monte Carlo VAEs on a variety of applications.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/thin21a.html
http://proceedings.mlr.press/v139/thin21a.htmlResource Allocation in Multi-armed Bandit Exploration: Overcoming Sublinear Scaling with Adaptive ParallelismWe study exploration in stochastic multi-armed bandits when we have access to a divisible resource that can be allocated in varying amounts to arm pulls. We focus in particular on the allocation of distributed computing resources, where we may obtain results faster by allocating more resources per pull, but might have reduced throughput due to nonlinear scaling. For example, in simulation-based scientific studies, an expensive simulation can be sped up by running it on multiple cores. This speed-up however, is partly offset by the communication among cores, which results in lower throughput than if fewer cores were allocated to run more trials in parallel. In this paper, we explore these trade-offs in two settings. First, in a fixed confidence setting, we need to find the best arm with a given target success probability as quickly as possible. We propose an algorithm which trades off between information accumulation and throughput and show that the time taken can be upper bounded by the solution of a dynamic program whose inputs are the gaps between the sub-optimal and optimal arms. We also prove a matching hardness result. Second, we present an algorithm for a fixed deadline setting, where we are given a time deadline and need to maximize the probability of finding the best arm. We corroborate our theoretical insights with simulation experiments that show that the algorithms consistently match or outperform baseline algorithms on a variety of problem instances.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/thananjeyan21a.html
http://proceedings.mlr.press/v139/thananjeyan21a.htmlUnderstanding Invariance via Feedforward Inversion of Discriminatively Trained ClassifiersA discriminatively trained neural net classifier can fit the training data perfectly if all information about its input other than class membership has been discarded prior to the output layer. Surprisingly, past research has discovered that some extraneous visual detail remains in the unnormalized logits. This finding is based on inversion techniques that map deep embeddings back to images. We explore this phenomenon further using a novel synthesis of methods, yielding a feedforward inversion model that produces remarkably high fidelity reconstructions, qualitatively superior to those of past efforts. When applied to an adversarially robust classifier model, the reconstructions contain sufficient local detail and global structure that they might be confused with the original image in a quick glance, and the object category can clearly be gleaned from the reconstruction. Our approach is based on BigGAN (Brock, 2019), with conditioning on logits instead of one-hot class labels. We use our reconstruction model as a tool for exploring the nature of representations, including: the influence of model architecture and training objectives (specifically robust losses), the forms of invariance that networks achieve, representational differences between correctly and incorrectly classified images, and the effects of manipulating logits and images. We believe that our method can inspire future investigations into the nature of information flow in a neural net and can provide diagnostics for improving discriminative models. We provide pre-trained models and visualizations at \url{https://sites.google.com/view/understanding-invariance/home}.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/teterwak21a.html
http://proceedings.mlr.press/v139/teterwak21a.htmlMoreau-Yosida $f$-divergencesVariational representations of $f$-divergences are central to many machine learning algorithms, with Lipschitz constrained variants recently gaining attention. Inspired by this, we define the Moreau-Yosida approximation of $f$-divergences with respect to the Wasserstein-$1$ metric. The corresponding variational formulas provide a generalization of a number of recent results, novel special cases of interest and a relaxation of the hard Lipschitz constraint. Additionally, we prove that the so-called tight variational representation of $f$-divergences can be to be taken over the quotient space of Lipschitz functions, and give a characterization of functions achieving the supremum in the variational representation. On the practical side, we propose an algorithm to calculate the tight convex conjugate of $f$-divergences compatible with automatic differentiation frameworks. As an application of our results, we propose the Moreau-Yosida $f$-GAN, providing an implementation of the variational formulas for the Kullback-Leibler, reverse Kullback-Leibler, $\chi^2$, reverse $\chi^2$, squared Hellinger, Jensen-Shannon, Jeffreys, triangular discrimination and total variation divergences as GANs trained on CIFAR-10, leading to competitive results and a simple solution to the problem of uniqueness of the optimal critic.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/terjek21a.html
http://proceedings.mlr.press/v139/terjek21a.htmlT-SCI: A Two-Stage Conformal Inference Algorithm with Guaranteed Coverage for Cox-MLPIt is challenging to deal with censored data, where we only have access to the incomplete information of survival time instead of its exact value. Fortunately, under linear predictor assumption, people can obtain guaranteed coverage for the confidence interval of survival time using methods like Cox Regression. However, when relaxing the linear assumption with neural networks (e.g., Cox-MLP \citep{katzman2018deepsurv,kvamme2019time}), we lose the guaranteed coverage. To recover the guaranteed coverage without linear assumption, we propose two algorithms based on conformal inference. In the first algorithm \emph{WCCI}, we revisit weighted conformal inference and introduce a new non-conformity score based on partial likelihood. We then propose a two-stage algorithm \emph{T-SCI}, where we run WCCI in the first stage and apply quantile conformal inference to calibrate the results in the second stage. Theoretical analysis shows that T-SCI returns guaranteed coverage under milder assumptions than WCCI. We conduct extensive experiments on synthetic data and real data using different methods, which validate our analysis.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/teng21a.html
http://proceedings.mlr.press/v139/teng21a.htmlOmniNet: Omnidirectional Representations from TransformersThis paper proposes Omnidirectional Representations from Transformers (OMNINET). In OmniNet, instead of maintaining a strictly horizon-tal receptive field, each token is allowed to attend to all tokens in the entire network. This process can also be interpreted as a form of extreme or intensive attention mechanism that has the receptive field of the entire width and depth of the network. To this end, the omnidirectional attention is learned via a meta-learner, which is essentially another self-attention based model. In order to mitigate the computationally expensive costs of full receptive field attention, we leverage efficient self-attention models such as kernel-based, low-rank attention and/or Big Bird as the meta-learner. Extensive experiments are conducted on autoregressive language modeling(LM1B, C4), Machine Translation, Long Range Arena (LRA), and Image Recognition.The experiments show that OmniNet achieves considerable improvements across these tasks, including achieving state-of-the-art performance on LM1B,WMT’14 En-De/En-Fr, and Long Range Arena.Moreover, using omnidirectional representation in Vision Transformers leads to significant improvements on image recognition tasks on both few-shot learning and fine-tuning setups.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/tay21b.html
http://proceedings.mlr.press/v139/tay21b.htmlSynthesizer: Rethinking Self-Attention for Transformer ModelsThe dot product self-attention is known to be central and indispensable to state-of-the-art Transformer models. But is it really required? This paper investigates the true importance and contribution of the dot product-based self-attention mechanism on the performance of Transformer models. Via extensive experiments, we find that (1) random alignment matrices surprisingly perform quite competitively and (2) learning attention weights from token-token (query-key) interactions is useful but not that important after all. To this end, we propose \textsc{Synthesizer}, a model that learns synthetic attention weights without token-token interactions. In our experiments, we first show that simple Synthesizers achieve highly competitive performance when compared against vanilla Transformer models across a range of tasks, including machine translation, language modeling, text generation and GLUE/SuperGLUE benchmarks. When composed with dot product attention, we find that Synthesizers consistently outperform Transformers. Moreover, we conduct additional comparisons of Synthesizers against Dynamic Convolutions, showing that simple Random Synthesizer is not only $60%$ faster but also improves perplexity by a relative $3.5%$. Finally, we show that simple factorized Synthesizers can outperform Linformers on encoding only tasks.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/tay21a.html
http://proceedings.mlr.press/v139/tay21a.htmlA Language for Counterfactual Generative ModelsWe present Omega, a probabilistic programming language with support for counterfactual inference. Counterfactual inference means to observe some fact in the present, and infer what would have happened had some past intervention been taken, e.g. “given that medication was not effective at dose x, what is the probability that it would have been effective at dose 2x?.” We accomplish this by introducing a new operator to probabilistic programming akin to Pearl’s do, define its formal semantics, provide an implementation, and demonstrate its utility through examples in a variety of simulation models.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/tavares21a.html
http://proceedings.mlr.press/v139/tavares21a.htmlSequential Domain Adaptation by Synthesizing Distributionally Robust ExpertsLeast squares estimators, when trained on few target domain samples, may predict poorly. Supervised domain adaptation aims to improve the predictive accuracy by exploiting additional labeled training samples from a source distribution that is close to the target distribution. Given available data, we investigate novel strategies to synthesize a family of least squares estimator experts that are robust with regard to moment conditions. When these moment conditions are specified using Kullback-Leibler or Wasserstein-type divergences, we can find the robust estimators efficiently using convex optimization. We use the Bernstein online aggregation algorithm on the proposed family of robust experts to generate predictions for the sequential stream of target test samples. Numerical experiments on real data show that the robust strategies systematically outperform non-robust interpolations of the empirical least squares estimators.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/taskesen21a.html
http://proceedings.mlr.press/v139/taskesen21a.htmlUnderstanding the Dynamics of Gradient Flow in Overparameterized Linear modelsWe provide a detailed analysis of the dynamics ofthe gradient flow in overparameterized two-layerlinear models. A particularly interesting featureof this model is that its nonlinear dynamics can beexactly solved as a consequence of a large num-ber of conservation laws that constrain the systemto follow particular trajectories. More precisely,the gradient flow preserves the difference of theGramian matrices of the input and output weights,and its convergence to equilibrium depends onboth the magnitude of that difference (which isfixed at initialization) and the spectrum of the data.In addition, and generalizing prior work, we proveour results without assuming small, balanced orspectral initialization for the weights. Moreover,we establish interesting mathematical connectionsbetween matrix factorization problems and differ-ential equations of the Riccati type.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/tarmoun21a.html
http://proceedings.mlr.press/v139/tarmoun21a.htmlREPAINT: Knowledge Transfer in Deep Reinforcement LearningAccelerating learning processes for complex tasks by leveraging previously learned tasks has been one of the most challenging problems in reinforcement learning, especially when the similarity between source and target tasks is low. This work proposes REPresentation And INstance Transfer (REPAINT) algorithm for knowledge transfer in deep reinforcement learning. REPAINT not only transfers the representation of a pre-trained teacher policy in the on-policy learning, but also uses an advantage-based experience selection approach to transfer useful samples collected following the teacher policy in the off-policy learning. Our experimental results on several benchmark tasks show that REPAINT significantly reduces the total training time in generic cases of task similarity. In particular, when the source tasks are dissimilar to, or sub-tasks of, the target tasks, REPAINT outperforms other baselines in both training-time reduction and asymptotic performance of return scores.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/tao21a.html
http://proceedings.mlr.press/v139/tao21a.htmlTaylor Expansion of Discount FactorsIn practical reinforcement learning (RL), the discount factor used for estimating value functions often differs from that used for defining the evaluation objective. In this work, we study the effect that this discrepancy of discount factors has during learning, and discover a family of objectives that interpolate value functions of two distinct discount factors. Our analysis suggests new ways for estimating value functions and performing policy optimization updates, which demonstrate empirical performance gains. This framework also leads to new insights on commonly-used deep RL heuristic modifications to policy optimization algorithms.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/tang21b.html
http://proceedings.mlr.press/v139/tang21b.html1-bit Adam: Communication Efficient Large-Scale Training with Adam’s Convergence SpeedScalable training of large models (like BERT and GPT-3) requires careful optimization rooted in model design, architecture, and system capabilities. From a system standpoint, communication has become a major bottleneck, especially on commodity systems with standard TCP interconnects that offer limited network bandwidth. Communication compression is an important technique to reduce training time on such systems. One of the most effective ways to compress communication is via error compensation compression, which offers robust convergence speed, even under 1-bit compression. However, state-of-the-art error compensation techniques only work with basic optimizers like SGD and momentum SGD, which are linearly dependent on the gradients. They do not work with non-linear gradient-based optimizers like Adam, which offer state-of-the-art convergence efficiency and accuracy for models like BERT. In this paper, we propose 1-bit Adam that reduces the communication volume by up to 5x, offers much better scalability, and provides the same convergence speed as uncompressed Adam. Our key finding is that Adam’s variance becomes stable (after a warmup phase) and can be used as a fixed precondition for the rest of the training (compression phase). We performed experiments on up to 256 GPUs and show that 1-bit Adam enables up to 3.3x higher throughput for BERT-Large pre-training and up to 2.9x higher throughput for SQuAD fine-tuning. In addition, we provide theoretical analysis for 1-bit Adam.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/tang21a.html
http://proceedings.mlr.press/v139/tang21a.htmlSGA: A Robust Algorithm for Partial Recovery of Tree-Structured Graphical Models with Noisy SamplesWe consider learning Ising tree models when the observations from the nodes are corrupted by independent but non-identically distributed noise with unknown statistics. Katiyar et al. (2020) showed that although the exact tree structure cannot be recovered, one can recover a partial tree structure; that is, a structure belonging to the equivalence class containing the true tree. This paper presents a systematic improvement of Katiyar et al. (2020). First, we present a novel impossibility result by deriving a bound on the necessary number of samples for partial recovery. Second, we derive a significantly improved sample complexity result in which the dependence on the minimum correlation $\rho_{\min}$ is $\rho_{\min}^{-8}$ instead of $\rho_{\min}^{-24}$. Finally, we propose Symmetrized Geometric Averaging (SGA), a more statistically robust algorithm for partial tree recovery. We provide error exponent analyses and extensive numerical results on a variety of trees to show that the sample complexity of SGA is significantly better than the algorithm of Katiyar et al. (2020). SGA can be readily extended to Gaussian models and is shown via numerical experiments to be similarly superior.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/tandon21a.html
http://proceedings.mlr.press/v139/tandon21a.htmlEfficientNetV2: Smaller Models and Faster TrainingThis paper introduces EfficientNetV2, a new family of convolutional networks that have faster training speed and better parameter efficiency than previous models. To develop these models, we use a combination of training-aware neural architecture search and scaling, to jointly optimize training speed and parameter efficiency. The models were searched from the search space enriched with new ops such as Fused-MBConv. Our experiments show that EfficientNetV2 models train much faster than state-of-the-art models while being up to 6.8x smaller. Our training can be further sped up by progressively increasing the image size during training, but it often causes a drop in accuracy. To compensate for this accuracy drop, we propose an improved method of progressive learning, which adaptively adjusts regularization (e.g. data augmentation) along with image size. With progressive learning, our EfficientNetV2 significantly outperforms previous models on ImageNet and CIFAR/Cars/Flowers datasets. By pretraining on the same ImageNet21k, our EfficientNetV2 achieves 87.3% top-1 accuracy on ImageNet ILSVRC2012, outperforming the recent ViT by 2.0% accuracy while training 5x-11x faster using the same computing resources.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/tan21a.html
http://proceedings.mlr.press/v139/tan21a.htmlSupervised Tree-Wasserstein DistanceTo measure the similarity of documents, the Wasserstein distance is a powerful tool, but it requires a high computational cost. Recently, for fast computation of the Wasserstein distance, methods for approximating the Wasserstein distance using a tree metric have been proposed. These tree-based methods allow fast comparisons of a large number of documents; however, they are unsupervised and do not learn task-specific distances. In this work, we propose the Supervised Tree-Wasserstein (STW) distance, a fast, supervised metric learning method based on the tree metric. Specifically, we rewrite the Wasserstein distance on the tree metric by the parent-child relationships of a tree, and formulate it as a continuous optimization problem using a contrastive loss. Experimentally, we show that the STW distance can be computed fast, and improves the accuracy of document classification tasks. Furthermore, the STW distance is formulated by matrix multiplications, runs on a GPU, and is suitable for batch processing. Therefore, we show that the STW distance is extremely efficient when comparing a large number of documents.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/takezawa21a.html
http://proceedings.mlr.press/v139/takezawa21a.htmlApproximation Theory Based Methods for RKHS BanditsThe RKHS bandit problem (also called kernelized multi-armed bandit problem) is an online optimization problem of non-linear functions with noisy feedback. Although the problem has been extensively studied, there are unsatisfactory results for some problems compared to the well-studied linear bandit case. Specifically, there is no general algorithm for the adversarial RKHS bandit problem. In addition, high computational complexity of existing algorithms hinders practical application. We address these issues by considering a novel amalgamation of approximation theory and the misspecified linear bandit problem. Using an approximation method, we propose efficient algorithms for the stochastic RKHS bandit problem and the first general algorithm for the adversarial RKHS bandit problem. Furthermore, we empirically show that one of our proposed methods has comparable cumulative regret to IGP-UCB and its running time is much shorter.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/takemori21a.html
http://proceedings.mlr.press/v139/takemori21a.htmlSinkhorn Label Allocation: Semi-Supervised Classification via Annealed Self-TrainingSelf-training is a standard approach to semi-supervised learning where the learner’s own predictions on unlabeled data are used as supervision during training. In this paper, we reinterpret this label assignment process as an optimal transportation problem between examples and classes, wherein the cost of assigning an example to a class is mediated by the current predictions of the classifier. This formulation facilitates a practical annealing strategy for label assignment and allows for the inclusion of prior knowledge on class proportions via flexible upper bound constraints. The solutions to these assignment problems can be efficiently approximated using Sinkhorn iteration, thus enabling their use in the inner loop of standard stochastic optimization algorithms. We demonstrate the effectiveness of our algorithm on the CIFAR-10, CIFAR-100, and SVHN datasets in comparison with FixMatch, a state-of-the-art self-training algorithm.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/tai21a.html
http://proceedings.mlr.press/v139/tai21a.htmlDriftSurf: Stable-State / Reactive-State Learning under Concept DriftWhen learning from streaming data, a change in the data distribution, also known as concept drift, can render a previously-learned model inaccurate and require training a new model. We present an adaptive learning algorithm that extends previous drift-detection-based methods by incorporating drift detection into a broader stable-state/reactive-state process. The advantage of our approach is that we can use aggressive drift detection in the stable state to achieve a high detection rate, but mitigate the false positive rate of standalone drift detection via a reactive state that reacts quickly to true drifts while eliminating most false positives. The algorithm is generic in its base learner and can be applied across a variety of supervised learning problems. Our theoretical analysis shows that the risk of the algorithm is (i) statistically better than standalone drift detection and (ii) competitive to an algorithm with oracle knowledge of when (abrupt) drifts occur. Experiments on synthetic and real datasets with concept drifts confirm our theoretical analysis.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/tahmasbi21a.html
http://proceedings.mlr.press/v139/tahmasbi21a.htmlRobust Representation Learning via Perceptual Similarity MetricsA fundamental challenge in artificial intelligence is learning useful representations of data that yield good performance on a downstream classification task, without overfitting to spurious input features. Extracting such task-relevant predictive information becomes particularly difficult for noisy and high-dimensional real-world data. In this work, we propose Contrastive Input Morphing (CIM), a representation learning framework that learns input-space transformations of the data to mitigate the effect of irrelevant input features on downstream performance. Our method leverages a perceptual similarity metric via a triplet loss to ensure that the transformation preserves task-relevant information. Empirically, we demonstrate the efficacy of our approach on various tasks which typically suffer from the presence of spurious correlations: classification with nuisance information, out-of-distribution generalization, and preservation of subgroup accuracies. We additionally show that CIM is complementary to other mutual information-based representation learning techniques, and demonstrate that it improves the performance of variational information bottleneck (VIB) when used in conjunction.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/taghanaki21a.html
http://proceedings.mlr.press/v139/taghanaki21a.htmlParallel tempering on optimized pathsParallel tempering (PT) is a class of Markov chain Monte Carlo algorithms that constructs a path of distributions annealing between a tractable reference and an intractable target, and then interchanges states along the path to improve mixing in the target. The performance of PT depends on how quickly a sample from the reference distribution makes its way to the target, which in turn depends on the particular path of annealing distributions. However, past work on PT has used only simple paths constructed from convex combinations of the reference and target log-densities. This paper begins by demonstrating that this path performs poorly in the setting where the reference and target are nearly mutually singular. To address this issue, we expand the framework of PT to general families of paths, formulate the choice of path as an optimization problem that admits tractable gradient estimates, and propose a flexible new family of spline interpolation paths for use in practice. Theoretical and empirical results both demonstrate that our proposed methodology breaks previously-established upper performance limits for traditional paths.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/syed21a.html
http://proceedings.mlr.press/v139/syed21a.htmlOf Moments and Matching: A Game-Theoretic Framework for Closing the Imitation GapWe provide a unifying view of a large family of previous imitation learning algorithms through the lens of moment matching. At its core, our classification scheme is based on whether the learner attempts to match (1) reward or (2) action-value moments of the expert’s behavior, with each option leading to differing algorithmic approaches. By considering adversarially chosen divergences between learner and expert behavior, we are able to derive bounds on policy performance that apply for all algorithms in each of these classes, the first to our knowledge. We also introduce the notion of moment recoverability, implicit in many previous analyses of imitation learning, which allows us to cleanly delineate how well each algorithmic family is able to mitigate compounding errors. We derive three novel algorithm templates (AdVIL, AdRIL, and DAeQuIL) with strong guarantees, simple implementation, and competitive empirical performance.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/swamy21a.html
http://proceedings.mlr.press/v139/swamy21a.htmlGeneralization Error Bound for Hyperbolic Ordinal EmbeddingHyperbolic ordinal embedding (HOE) represents entities as points in hyperbolic space so that they agree as well as possible with given constraints in the form of entity $i$ is more similar to entity $j$ than to entity $k$. It has been experimentally shown that HOE can obtain representations of hierarchical data such as a knowledge base and a citation network effectively, owing to hyperbolic space’s exponential growth property. However, its theoretical analysis has been limited to ideal noiseless settings, and its generalization error in compensation for hyperbolic space’s exponential representation ability has not been guaranteed. The difficulty is that existing generalization error bound derivations for ordinal embedding based on the Gramian matrix are not applicable in HOE, since hyperbolic space is not inner-product space. In this paper, through our novel characterization of HOE with decomposed Lorentz Gramian matrices, we provide a generalization error bound of HOE for the first time, which is at most exponential with respect to the embedding space’s radius. Our comparison between the bounds of HOE and Euclidean ordinal embedding shows that HOE’s generalization error comes at a reasonable cost considering its exponential representation ability.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/suzuki21a.html
http://proceedings.mlr.press/v139/suzuki21a.htmlModel-Targeted Poisoning Attacks with Provable ConvergenceIn a poisoning attack, an adversary who controls a small fraction of the training data attempts to select that data, so a model is induced that misbehaves in a particular way. We consider poisoning attacks against convex machine learning models and propose an efficient poisoning attack designed to induce a model specified by the adversary. Unlike previous model-targeted poisoning attacks, our attack comes with provable convergence to any attainable target model. We also provide a lower bound on the minimum number of poisoning points needed to achieve a given target model. Our method uses online convex optimization and finds poisoning points incrementally. This provides more flexibility than previous attacks which require an a priori assumption about the number of poisoning points. Our attack is the first model-targeted poisoning attack that provides provable convergence for convex models. In our experiments, it either exceeds or matches state-of-the-art attacks in terms of attack success rate and distance to the target model.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/suya21a.html
http://proceedings.mlr.press/v139/suya21a.htmlReinforcement Learning for Cost-Aware Markov Decision ProcessesRatio maximization has applications in areas as diverse as finance, reward shaping for reinforcement learning (RL), and the development of safe artificial intelligence, yet there has been very little exploration of RL algorithms for ratio maximization. This paper addresses this deficiency by introducing two new, model-free RL algorithms for solving cost-aware Markov decision processes, where the goal is to maximize the ratio of long-run average reward to long-run average cost. The first algorithm is a two-timescale scheme based on relative value iteration (RVI) Q-learning and the second is an actor-critic scheme. The paper proves almost sure convergence of the former to the globally optimal solution in the tabular case and almost sure convergence of the latter under linear function approximation for the critic. Unlike previous methods, the two algorithms provably converge for general reward and cost functions under suitable conditions. The paper also provides empirical results demonstrating promising performance and lending strong support to the theoretical results.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/suttle21a.html
http://proceedings.mlr.press/v139/suttle21a.htmlPAC-Learning for Strategic ClassificationThe study of strategic or adversarial manipulation of testing data to fool a classifier has attracted much recent attention. Most previous works have focused on two extreme situations where any testing data point either is completely adversarial or always equally prefers the positive label. In this paper, we generalize both of these through a unified framework for strategic classification and introduce the notion of strategic VC-dimension (SVC) to capture the PAC-learnability in our general strategic setup. SVC provably generalizes the recent concept of adversarial VC-dimension (AVC) introduced by Cullina et al. (2018). We instantiate our framework for the fundamental strategic linear classification problem. We fully characterize: (1) the statistical learnability of linear classifiers by pinning down its SVC; (2) it’s computational tractability by pinning down the complexity of the empirical risk minimization problem. Interestingly, the SVC of linear classifiers is always upper bounded by its standard VC-dimension. This characterization also strictly generalizes the AVC bound for linear classifiers in (Cullina et al., 2018).Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/sundaram21a.html
http://proceedings.mlr.press/v139/sundaram21a.htmlReasoning Over Virtual Knowledge Bases With Open Predicate RelationsWe present the Open Predicate Query Language (OPQL); a method for constructing a virtual KB (VKB) trained entirely from text. Large Knowledge Bases (KBs) are indispensable for a wide-range of industry applications such as question answering and recommendation. Typically, KBs encode world knowledge in a structured, readily accessible form derived from laborious human annotation efforts. Unfortunately, while they are extremely high precision, KBs are inevitably highly incomplete and automated methods for enriching them are far too inaccurate. Instead, OPQL constructs a VKB by encoding and indexing a set of relation mentions in a way that naturally enables reasoning and can be trained without any structured supervision. We demonstrate that OPQL outperforms prior VKB methods on two different KB reasoning tasks and, additionally, can be used as an external memory integrated into a language model (OPQL-LM) leading to improvements on two open-domain question answering tasks.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/sun21e.html
http://proceedings.mlr.press/v139/sun21e.htmlScalable Variational Gaussian Processes via Harmonic Kernel DecompositionWe introduce a new scalable variational Gaussian process approximation which provides a high fidelity approximation while retaining general applicability. We propose the harmonic kernel decomposition (HKD), which uses Fourier series to decompose a kernel as a sum of orthogonal kernels. Our variational approximation exploits this orthogonality to enable a large number of inducing points at a low computational cost. We demonstrate that, on a range of regression and classification problems, our approach can exploit input space symmetries such as translations and reflections, and it significantly outperforms standard variational methods in scalability and accuracy. Notably, our approach achieves state-of-the-art results on CIFAR-10 among pure GP models.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/sun21d.html
http://proceedings.mlr.press/v139/sun21d.htmlDFAC Framework: Factorizing the Value Function via Quantile Mixture for Multi-Agent Distributional Q-LearningIn fully cooperative multi-agent reinforcement learning (MARL) settings, the environments are highly stochastic due to the partial observability of each agent and the continuously changing policies of the other agents. To address the above issues, we integrate distributional RL and value function factorization methods by proposing a Distributional Value Function Factorization (DFAC) framework to generalize expected value function factorization methods to their distributional variants. DFAC extends the individual utility functions from deterministic variables to random variables, and models the quantile function of the total return as a quantile mixture. To validate DFAC, we demonstrate DFAC’s ability to factorize a simple two-step matrix game with stochastic rewards and perform experiments on all Super Hard tasks of StarCraft Multi-Agent Challenge, showing that DFAC is able to outperform expected value function factorization baselines.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/sun21c.html
http://proceedings.mlr.press/v139/sun21c.htmlWhat Makes for End-to-End Object Detection?Object detection has recently achieved a breakthrough for removing the last one non-differentiable component in the pipeline, Non-Maximum Suppression (NMS), and building up an end-to-end system. However, what makes for its one-to-one prediction has not been well understood. In this paper, we first point out that one-to-one positive sample assignment is the key factor, while, one-to-many assignment in previous detectors causes redundant predictions in inference. Second, we surprisingly find that even training with one-to-one assignment, previous detectors still produce redundant predictions. We identify that classification cost in matching cost is the main ingredient: (1) previous detectors only consider location cost, (2) by additionally introducing classification cost, previous detectors immediately produce one-to-one prediction during inference. We introduce the concept of score gap to explore the effect of matching cost. Classification cost enlarges the score gap by choosing positive samples as those of highest score in the training iteration and reducing noisy positive samples brought by only location cost. Finally, we demonstrate the advantages of end-to-end object detection on crowded scenes.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/sun21b.html
http://proceedings.mlr.press/v139/sun21b.htmlAutoSampling: Search for Effective Data Sampling SchedulesData sampling acts as a pivotal role in training deep learning models. However, an effective sampling schedule is difficult to learn due to its inherent high-dimension as a hyper-parameter. In this paper, we propose an AutoSampling method to automatically learn sampling schedules for model training, which consists of the multi-exploitation step aiming for optimal local sampling schedules and the exploration step for the ideal sampling distribution. More specifically, we achieve sampling schedule search with shortened exploitation cycle to provide enough supervision. In addition, we periodically estimate the sampling distribution from the learned sampling schedules and perturb it to search in the distribution space. The combination of two searches allows us to learn a robust sampling schedule. We apply our AutoSampling method to a variety of image classification tasks illustrating the effectiveness of the proposed method.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/sun21a.html
http://proceedings.mlr.press/v139/sun21a.htmlNondeterminism and Instability in Neural Network OptimizationNondeterminism in neural network optimization produces uncertainty in performance, making small improvements difficult to discern from run-to-run variability. While uncertainty can be reduced by training multiple model copies, doing so is time-consuming, costly, and harms reproducibility. In this work, we establish an experimental protocol for understanding the effect of optimization nondeterminism on model diversity, allowing us to isolate the effects of a variety of sources of nondeterminism. Surprisingly, we find that all sources of nondeterminism have similar effects on measures of model diversity. To explain this intriguing fact, we identify the instability of model training, taken as an end-to-end procedure, as the key determinant. We show that even one-bit changes in initial parameters result in models converging to vastly different values. Last, we propose two approaches for reducing the effects of instability on run-to-run variability.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/summers21a.html
http://proceedings.mlr.press/v139/summers21a.htmlNot All Memories are Created Equal: Learning to Forget by ExpiringAttention mechanisms have shown promising results in sequence modeling tasks that require long-term memory. Recent work investigated mechanisms to reduce the computational cost of preserving and storing memories. However, not all content in the past is equally important to remember. We propose Expire-Span, a method that learns to retain the most important information and expire the irrelevant information. This forgetting of memories enables Transformers to scale to attend over tens of thousands of previous timesteps efficiently, as not all states from previous timesteps are preserved. We demonstrate that Expire-Span can help models identify and retain critical information and show it can achieve strong performance on reinforcement learning tasks specifically designed to challenge this functionality. Next, we show that Expire-Span can scale to memories that are tens of thousands in size, setting a new state of the art on incredibly long context tasks such as character-level language modeling and a frame-by-frame moving objects task. Finally, we analyze the efficiency of Expire-Span compared to existing approaches and demonstrate that it trains faster and uses less memory.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/sukhbaatar21a.html
http://proceedings.mlr.press/v139/sukhbaatar21a.htmlMore Powerful and General Selective Inference for Stepwise Feature Selection using Homotopy MethodConditional selective inference (SI) has been actively studied as a new statistical inference framework for data-driven hypotheses. The basic idea of conditional SI is to make inferences conditional on the selection event characterized by a set of linear and/or quadratic inequalities. Conditional SI has been mainly studied in the context of feature selection such as stepwise feature selection (SFS). The main limitation of the existing conditional SI methods is the loss of power due to over-conditioning, which is required for computational tractability. In this study, we develop a more powerful and general conditional SI method for SFS using the homotopy method which enables us to overcome this limitation. The homotopy-based SI is especially effective for more complicated feature selection algorithms. As an example, we develop a conditional SI method for forward-backward SFS with AIC-based stopping criteria and show that it is not adversely affected by the increased complexity of the algorithm. We conduct several experiments to demonstrate the effectiveness and efficiency of the proposed method.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/sugiyama21a.html
http://proceedings.mlr.press/v139/sugiyama21a.htmlK-shot NAS: Learnable Weight-Sharing for NAS with K-shot SupernetsIn one-shot weight sharing for NAS, the weights of each operation (at each layer) are supposed to be identical for all architectures (paths) in the supernet. However, this rules out the possibility of adjusting operation weights to cater for different paths, which limits the reliability of the evaluation results. In this paper, instead of counting on a single supernet, we introduce $K$-shot supernets and take their weights for each operation as a dictionary. The operation weight for each path is represented as a convex combination of items in a dictionary with a simplex code. This enables a matrix approximation of the stand-alone weight matrix with a higher rank ($K>1$). A \textit{simplex-net} is introduced to produce architecture-customized code for each path. As a result, all paths can adaptively learn how to share weights in the $K$-shot supernets and acquire corresponding weights for better evaluation. $K$-shot supernets and simplex-net can be iteratively trained, and we further extend the search to the channel dimension. Extensive experiments on benchmark datasets validate that K-shot NAS significantly improves the evaluation accuracy of paths and thus brings in impressive performance improvements.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/su21a.html
http://proceedings.mlr.press/v139/su21a.htmlDecoupling Representation Learning from Reinforcement LearningIn an effort to overcome limitations of reward-driven feature learning in deep reinforcement learning (RL) from images, we propose decoupling representation learning from policy learning. To this end, we introduce a new unsupervised learning (UL) task, called Augmented Temporal Contrast (ATC), which trains a convolutional encoder to associate pairs of observations separated by a short time difference, under image augmentations and using a contrastive loss. In online RL experiments, we show that training the encoder exclusively using ATC matches or outperforms end-to-end RL in most environments. Additionally, we benchmark several leading UL algorithms by pre-training encoders on expert demonstrations and using them, with weights frozen, in RL agents; we find that agents using ATC-trained encoders outperform all others. We also train multi-task encoders on data from multiple environments and show generalization to different downstream RL tasks. Finally, we ablate components of ATC, and introduce a new data augmentation to enable replay of (compressed) latent images from pre-trained encoders when RL requires augmentation. Our experiments span visually diverse RL benchmarks in DeepMind Control, DeepMind Lab, and Atari, and our complete code is available at \url{https://github.com/astooke/rlpyt/tree/master/rlpyt/ul}.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/stooke21a.html
http://proceedings.mlr.press/v139/stooke21a.htmlDecomposed Mutual Information Estimation for Contrastive Representation LearningRecent contrastive representation learning methods rely on estimating mutual information (MI) between multiple views of an underlying context. E.g., we can derive multiple views of a given image by applying data augmentation, or we can split a sequence into views comprising the past and future of some step in the sequence. Contrastive lower bounds on MI are easy to optimize, but have a strong underestimation bias when estimating large amounts of MI. We propose decomposing the full MI estimation problem into a sum of smaller estimation problems by splitting one of the views into progressively more informed subviews and by applying the chain rule on MI between the decomposed views. This expression contains a sum of unconditional and conditional MI terms, each measuring modest chunks of the total MI, which facilitates approximation via contrastive bounds. To maximize the sum, we formulate a contrastive lower bound on the conditional MI which can be approximated efficiently. We refer to our general approach as Decomposed Estimation of Mutual Information (DEMI). We show that DEMI can capture a larger amount of MI than standard non-decomposed contrastive bounds in a synthetic setting, and learns better representations in a vision domain and for dialogue generation.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/sordoni21a.html
http://proceedings.mlr.press/v139/sordoni21a.htmlCausal Curiosity: RL Agents Discovering Self-supervised Experiments for Causal Representation LearningHumans show an innate ability to learn the regularities of the world through interaction. By performing experiments in our environment, we are able to discern the causal factors of variation and infer how they affect the dynamics of our world. Analogously, here we attempt to equip reinforcement learning agents with the ability to perform experiments that facilitate a categorization of the rolled-out trajectories, and to subsequently infer the causal factors of the environment in a hierarchical manner. We introduce a novel intrinsic reward, called causal curiosity, and show that it allows our agents to learn optimal sequences of actions, and to discover causal factors in the dynamics. The learned behavior allows the agent to infer a binary quantized representation for the ground-truth causal factors in every environment. Additionally, we find that these experimental behaviors are semantically meaningful (e.g., to differentiate between heavy and light blocks, our agents learn to lift them), and are learnt in a self-supervised manner with approximately 2.5 times less data than conventional supervised planners. We show that these behaviors can be re-purposed and fine-tuned (e.g., from lifting to pushing or other downstream tasks). Finally, we show that the knowledge of causal factor representations aids zero-shot learning for more complex tasks.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/sontakke21a.html
http://proceedings.mlr.press/v139/sontakke21a.htmlOblivious Sketching-based Central Path Method for Linear ProgrammingIn this work, we propose a sketching-based central path method for solving linear programmings, whose running time matches the state of the art results [Cohen, Lee, Song STOC 19; Lee, Song, Zhang COLT 19]. Our method opens up the iterations of the central path method and deploys an "iterate and sketch" approach towards the problem by introducing a new coordinate-wise embedding technique, which may be of independent interest. Compare to previous methods, the work [Cohen, Lee, Song STOC 19] enjoys feasibility while being non-oblivious, and [Lee, Song, Zhang COLT 19] is oblivious but infeasible, and relies on $\mathit{dense}$ sketching matrices such as subsampled randomized Hadamard/Fourier transform matrices. Our method enjoys the benefits of being both oblivious and feasible, and can use $\mathit{sparse}$ sketching matrix [Nelson, Nguyen FOCS 13] to speed up the online matrix-vector multiplication. Our framework for solving LP naturally generalizes to a broader class of convex optimization problems including empirical risk minimization.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/song21e.html
http://proceedings.mlr.press/v139/song21e.htmlVariance Reduction via Primal-Dual Accelerated Dual Averaging for Nonsmooth Convex Finite-SumsStructured nonsmooth convex finite-sum optimization appears in many machine learning applications, including support vector machines and least absolute deviation. For the primal-dual formulation of this problem, we propose a novel algorithm called \emph{Variance Reduction via Primal-Dual Accelerated Dual Averaging (\vrpda)}. In the nonsmooth and general convex setting, \vrpda has the overall complexity $O(nd\log\min \{1/\epsilon, n\} + d/\epsilon )$ in terms of the primal-dual gap, where $n$ denotes the number of samples, $d$ the dimension of the primal variables, and $\epsilon$ the desired accuracy. In the nonsmooth and strongly convex setting, the overall complexity of \vrpda becomes $O(nd\log\min\{1/\epsilon, n\} + d/\sqrt{\epsilon})$ in terms of both the primal-dual gap and the distance between iterate and optimal solution. Both these results for \vrpda improve significantly on state-of-the-art complexity estimates—which are $O(nd\log \min\{1/\epsilon, n\} + \sqrt{n}d/\epsilon)$ for the nonsmooth and general convex setting and $O(nd\log \min\{1/\epsilon, n\} + \sqrt{n}d/\sqrt{\epsilon})$ for the nonsmooth and strongly convex setting—with a simpler and more straightforward algorithm and analysis. Moreover, both complexities are better than \emph{lower} bounds for general convex finite-sum optimization, because our approach makes use of additional, commonly occurring structure. Numerical experiments reveal competitive performance of \vrpda compared to state-of-the-art approaches.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/song21d.html
http://proceedings.mlr.press/v139/song21d.htmlFast Sketching of Polynomial Kernels of Polynomial DegreeKernel methods are fundamental in machine learning, and faster algorithms for kernel approximation provide direct speedups for many core tasks in machine learning. The polynomial kernel is especially important as other kernels can often be approximated by the polynomial kernel via a Taylor series expansion. Recent techniques in oblivious sketching reduce the dependence in the running time on the degree $q$ of the polynomial kernel from exponential to polynomial, which is useful for the Gaussian kernel, for which $q$ can be chosen to be polylogarithmic. However, for more slowly growing kernels, such as the neural tangent and arc cosine kernels, $q$ needs to be polynomial, and previous work incurs a polynomial factor slowdown in the running time. We give a new oblivious sketch which greatly improves upon this running time, by removing the dependence on $q$ in the leading order term. Combined with a novel sampling scheme, we give the fastest algorithms for approximating a large family of slow-growing kernels.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/song21c.html
http://proceedings.mlr.press/v139/song21c.htmlPC-MLP: Model-based Reinforcement Learning with Policy Cover Guided ExplorationModel-based Reinforcement Learning (RL) is a popular learning paradigm due to its potential sample efficiency compared to model-free RL. However, existing empirical model-based RL approaches lack the ability to explore. This work studies a computationally and statistically efficient model-based algorithm for both Kernelized Nonlinear Regulators (KNR) and linear Markov Decision Processes (MDPs). For both models, our algorithm guarantees polynomial sample complexity and only uses access to a planning oracle. Experimentally, we first demonstrate the flexibility and the efficacy of our algorithm on a set of exploration challenging control tasks where existing empirical model-based RL approaches completely fail. We then show that our approach retains excellent performance even in common dense reward control benchmarks that do not require heavy exploration.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/song21b.html
http://proceedings.mlr.press/v139/song21b.htmlAccelerating Feedforward Computation via Parallel Nonlinear Equation SolvingFeedforward computation, such as evaluating a neural network or sampling from an autoregressive model, is ubiquitous in machine learning. The sequential nature of feedforward computation, however, requires a strict order of execution and cannot be easily accelerated with parallel computing. To enable parallelization, we frame the task of feedforward computation as solving a system of nonlinear equations. We then propose to find the solution using a Jacobi or Gauss-Seidel fixed-point iteration method, as well as hybrid methods of both. Crucially, Jacobi updates operate independently on each equation and can be executed in parallel. Our method is guaranteed to give exactly the same values as the original feedforward computation with a reduced (or equal) number of parallelizable iterations, and hence reduced time given sufficient parallel computing power. Experimentally, we demonstrate the effectiveness of our approach in accelerating (i) backpropagation of RNNs, (ii) evaluation of DenseNets, and (iii) autoregressive sampling of MADE and PixelCNN++, with speedup factors between 2.1 and 26 under various settings.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/song21a.html
http://proceedings.mlr.press/v139/song21a.htmlShortest-Path Constrained Reinforcement Learning for Sparse Reward TasksWe propose the k-Shortest-Path (k-SP) constraint: a novel constraint on the agent’s trajectory that improves the sample efficiency in sparse-reward MDPs. We show that any optimal policy necessarily satisfies the k-SP constraint. Notably, the k-SP constraint prevents the policy from exploring state-action pairs along the non-k-SP trajectories (e.g., going back and forth). However, in practice, excluding state-action pairs may hinder the convergence of RL algorithms. To overcome this, we propose a novel cost function that penalizes the policy violating SP constraint, instead of completely excluding it. Our numerical experiment in a tabular RL setting demonstrates that the SP-constraint can significantly reduce the trajectory space of policy. As a result, our constraint enables more sample efficient learning by suppressing redundant exploration and exploitation. Our experiments on MiniGrid, DeepMind Lab, Atari, and Fetch show that the proposed method significantly improves proximal policy optimization (PPO) and outperforms existing novelty-seeking exploration methods including count-based exploration even in continuous control tasks, indicating that it improves the sample efficiency by preventing the agent from taking redundant actions.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/sohn21a.html
http://proceedings.mlr.press/v139/sohn21a.htmlMulti-Task Reinforcement Learning with Context-based Representationshttps://drive.google.com/file/d/1lRV72XaKoxZjgQrLXBJhsM82x54_1Vc4/view?usp=sharingThu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/sodhani21a.html
http://proceedings.mlr.press/v139/sodhani21a.htmlSkew Orthogonal ConvolutionsTraining convolutional neural networks with a Lipschitz constraint under the $l_{2}$ norm is useful for provable adversarial robustness, interpretable gradients, stable training, etc. While 1-Lipschitz networks can be designed by imposing a 1-Lipschitz constraint on each layer, training such networks requires each layer to be gradient norm preserving (GNP) to prevent gradients from vanishing. However, existing GNP convolutions suffer from slow training, lead to significant reduction in accuracy and provide no guarantees on their approximations. In this work, we propose a GNP convolution layer called \textbf{S}kew \textbf{O}rthogonal \textbf{C}onvolution (SOC) that uses the following mathematical property: when a matrix is {\it Skew-Symmetric}, its exponential function is an {\it orthogonal} matrix. To use this property, we first construct a convolution filter whose Jacobian is Skew-Symmetric. Then, we use the Taylor series expansion of the Jacobian exponential to construct the SOC layer that is orthogonal. To efficiently implement SOC, we keep a finite number of terms from the Taylor series and provide a provable guarantee on the approximation error. Our experiments on CIFAR-10 and CIFAR-100 show that SOC allows us to train provably Lipschitz, large convolutional neural networks significantly faster than prior works while achieving significant improvements for both standard and certified robust accuracies.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/singla21a.html
http://proceedings.mlr.press/v139/singla21a.htmlStructured World Belief for Reinforcement Learning in POMDPObject-centric world models provide structured representation of the scene and can be an important backbone in reinforcement learning and planning. However, existing approaches suffer in partially-observable environments due to the lack of belief states. In this paper, we propose Structured World Belief, a model for learning and inference of object-centric belief states. Inferred by Sequential Monte Carlo (SMC), our belief states provide multiple object-centric scene hypotheses. To synergize the benefits of SMC particles with object representations, we also propose a new object-centric dynamics model that considers the inductive bias of object permanence. This enables tracking of object states even when they are invisible for a long time. To further facilitate object tracking in this regime, we allow our model to attend flexibly to any spatial location in the image which was restricted in previous models. In experiments, we show that object-centric belief provides a more accurate and robust performance for filtering and generation. Furthermore, we show the efficacy of structured world belief in improving the performance of reinforcement learning, planning and supervised reasoning.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/singh21a.html
http://proceedings.mlr.press/v139/singh21a.htmlFlow-based Attribution in Graphical Models: A Recursive Shapley ApproachWe study the attribution problem in a graphical model, wherein the objective is to quantify how the effect of changes at the source nodes propagates through the graph. We develop a model-agnostic flow-based attribution method, called recursive Shapley value (RSV). RSV generalizes a number of existing node-based methods and uniquely satisfies a set of flow-based axioms. In addition to admitting a natural characterization for linear models and facilitating mediation analysis for non-linear models, RSV satisfies a mix of desirable properties discussed in the recent literature, including implementation invariance, sensitivity, monotonicity, and affine scale invariance.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/singal21a.html
http://proceedings.mlr.press/v139/singal21a.htmlGeometry of the Loss Landscape in Overparameterized Neural Networks: Symmetries and InvariancesWe study how permutation symmetries in overparameterized multi-layer neural networks generate ‘symmetry-induced’ critical points. Assuming a network with $ L $ layers of minimal widths $ r_1^*, \ldots, r_{L-1}^* $ reaches a zero-loss minimum at $ r_1^*! \cdots r_{L-1}^*! $ isolated points that are permutations of one another, we show that adding one extra neuron to each layer is sufficient to connect all these previously discrete minima into a single manifold. For a two-layer overparameterized network of width $ r^*+ h =: m $ we explicitly describe the manifold of global minima: it consists of $ T(r^*, m) $ affine subspaces of dimension at least $ h $ that are connected to one another. For a network of width $m$, we identify the number $G(r,m)$ of affine subspaces containing only symmetry-induced critical points that are related to the critical points of a smaller network of width $r<r^*$. Via a combinatorial analysis, we derive closed-form formulas for $ T $ and $ G $ and show that the number of symmetry-induced critical subspaces dominates the number of affine subspaces forming the global minima manifold in the mildly overparameterized regime (small $ h $) and vice versa in the vastly overparameterized regime ($h \gg r^*$). Our results provide new insights into the minimization of the non-convex loss function of overparameterized neural networks.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/simsek21a.html
http://proceedings.mlr.press/v139/simsek21a.htmlPopSkipJump: Decision-Based Attack for Probabilistic ClassifiersMost current classifiers are vulnerable to adversarial examples, small input perturbations that change the classification output. Many existing attack algorithms cover various settings, from white-box to black-box classifiers, but usually assume that the answers are deterministic and often fail when they are not. We therefore propose a new adversarial decision-based attack specifically designed for classifiers with probabilistic outputs. It is based on the HopSkipJump attack by Chen et al. (2019), a strong and query efficient decision-based attack originally designed for deterministic classifiers. Our P(robabilisticH)opSkipJump attack adapts its amount of queries to maintain HopSkipJump’s original output quality across various noise levels, while converging to its query efficiency as the noise level decreases. We test our attack on various noise models, including state-of-the-art off-the-shelf randomized defenses, and show that they offer almost no extra robustness to decision-based attacks. Code is available at https://github.com/cjsg/PopSkipJump.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/simon-gabriel21a.html
http://proceedings.mlr.press/v139/simon-gabriel21a.htmlDynamic Planning and Learning under Recovering RewardsMotivated by emerging applications such as live-streaming e-commerce, promotions and recommendations, we introduce a general class of multi-armed bandit problems that have the following two features: (i) the decision maker can pull and collect rewards from at most $K$ out of $N$ different arms in each time period; (ii) the expected reward of an arm immediately drops after it is pulled, and then non-parametrically recovers as the idle time increases. With the objective of maximizing expected cumulative rewards over $T$ time periods, we propose, construct and prove performance guarantees for a class of “Purely Periodic Policies”. For the offline problem when all model parameters are known, our proposed policy obtains an approximation ratio that is at the order of $1-\mathcal O(1/\sqrt{K})$, which is asymptotically optimal when $K$ grows to infinity. For the online problem when the model parameters are unknown and need to be learned, we design an Upper Confidence Bound (UCB) based policy that approximately has $\widetilde{\mathcal O}(N\sqrt{T})$ regret against the offline benchmark. Our framework and policy design may have the potential to be adapted into other offline planning and online learning applications with non-stationary and recovering rewards.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/simchi-levi21a.html
http://proceedings.mlr.press/v139/simchi-levi21a.htmlCollaborative Bayesian Optimization with Fair RegretBayesian optimization (BO) is a popular tool for optimizing complex and costly-to-evaluate black-box objective functions. To further reduce the number of function evaluations, any party performing BO may be interested to collaborate with others to optimize the same objective function concurrently. To do this, existing BO algorithms have considered optimizing a batch of input queries in parallel and provided theoretical bounds on their cumulative regret reflecting inefficiency. However, when the objective function values are correlated with real-world rewards (e.g., money), parties may be hesitant to collaborate if they risk incurring larger cumulative regret (i.e., smaller real-world reward) than others. This paper shows that fairness and efficiency are both necessary for the collaborative BO setting. Inspired by social welfare concepts from economics, we propose a new notion of regret capturing these properties and a collaborative BO algorithm whose convergence rate can be theoretically guaranteed by bounding the new regret, both of which share an adjustable parameter for trading off between fairness vs. efficiency. We empirically demonstrate the benefits (e.g., increased fairness) of our algorithm using synthetic and real-world datasets.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/sim21b.html
http://proceedings.mlr.press/v139/sim21b.htmlDirected Graph Embeddings in Pseudo-Riemannian ManifoldsThe inductive biases of graph representation learning algorithms are often encoded in the background geometry of their embedding space. In this paper, we show that general directed graphs can be effectively represented by an embedding model that combines three components: a pseudo-Riemannian metric structure, a non-trivial global topology, and a unique likelihood function that explicitly incorporates a preferred direction in embedding space. We demonstrate the representational capabilities of this method by applying it to the task of link prediction on a series of synthetic and real directed graphs from natural language applications and biology. In particular, we show that low-dimensional cylindrical Minkowski and anti-de Sitter spacetimes can produce equal or better graph representations than curved Riemannian manifolds of higher dimensions.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/sim21a.html
http://proceedings.mlr.press/v139/sim21a.htmlA Precise Performance Analysis of Support Vector RegressionIn this paper, we study the hard and soft support vector regression techniques applied to a set of $n$ linear measurements of the form $y_i=\boldsymbol{\beta}_\star^{T}{\bf x}_i +n_i$ where $\boldsymbol{\beta}_\star$ is an unknown vector, $\left\{{\bf x}_i\right\}_{i=1}^n$ are the feature vectors and $\left\{{n}_i\right\}_{i=1}^n$ model the noise. Particularly, under some plausible assumptions on the statistical distribution of the data, we characterize the feasibility condition for the hard support vector regression in the regime of high dimensions and, when feasible, derive an asymptotic approximation for its risk. Similarly, we study the test risk for the soft support vector regression as a function of its parameters. Our results are then used to optimally tune the parameters intervening in the design of hard and soft support vector regression algorithms. Based on our analysis, we illustrate that adding more samples may be harmful to the test performance of support vector regression, while it is always beneficial when the parameters are optimally selected. Such a result reminds a similar phenomenon observed in modern learning architectures according to which optimally tuned architectures present a decreasing test performance curve with respect to the number of samples.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/sifaou21a.html
http://proceedings.mlr.press/v139/sifaou21a.htmlOn Characterizing GAN Convergence Through Proximal Duality GapDespite the accomplishments of Generative Adversarial Networks (GANs) in modeling data distributions, training them remains a challenging task. A contributing factor to this difficulty is the non-intuitive nature of the GAN loss curves, which necessitates a subjective evaluation of the generated output to infer training progress. Recently, motivated by game theory, Duality Gap has been proposed as a domain agnostic measure to monitor GAN training. However, it is restricted to the setting when the GAN converges to a Nash equilibrium. But GANs need not always converge to a Nash equilibrium to model the data distribution. In this work, we extend the notion of duality gap to proximal duality gap that is applicable to the general context of training GANs where Nash equilibria may not exist. We show theoretically that the proximal duality gap can monitor the convergence of GANs to a broader spectrum of equilibria that subsumes Nash equilibria. We also theoretically establish the relationship between the proximal duality gap and the divergence between the real and generated data distributions for different GAN formulations. Our results provide new insights into the nature of GAN convergence. Finally, we validate experimentally the usefulness of proximal duality gap for monitoring and influencing GAN training.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/sidheekh21a.html
http://proceedings.mlr.press/v139/sidheekh21a.htmlTesting Group Fairness via Optimal Transport ProjectionsWe have developed a statistical testing framework to detect if a given machine learning classifier fails to satisfy a wide range of group fairness notions. Our test is a flexible, interpretable, and statistically rigorous tool for auditing whether exhibited biases are intrinsic to the algorithm or simply due to the randomness in the data. The statistical challenges, which may arise from multiple impact criteria that define group fairness and which are discontinuous on model parameters, are conveniently tackled by projecting the empirical measure to the set of group-fair probability models using optimal transport. This statistic is efficiently computed using linear programming, and its asymptotic distribution is explicitly obtained. The proposed framework can also be used to test for composite fairness hypotheses and fairness with multiple sensitive attributes. The optimal transport testing formulation improves interpretability by characterizing the minimal covariate perturbations that eliminate the bias observed in the audit.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/si21a.html
http://proceedings.mlr.press/v139/si21a.htmlAggregating From Multiple Target-Shifted SourcesMulti-source domain adaptation aims at leveraging the knowledge from multiple tasks for predicting a related target domain. Hence, a crucial aspect is to properly combine different sources based on their relations. In this paper, we analyzed the problem for aggregating source domains with different label distributions, where most recent source selection approaches fail. Our proposed algorithm differs from previous approaches in two key ways: the model aggregates multiple sources mainly through the similarity of semantic conditional distribution rather than marginal distribution; the model proposes a unified framework to select relevant sources for three popular scenarios, i.e., domain adaptation with limited label on target domain, unsupervised domain adaptation and label partial unsupervised domain adaption. We evaluate the proposed method through extensive experiments. The empirical results significantly outperform the baselines.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/shui21a.html
http://proceedings.mlr.press/v139/shui21a.htmlZoo-Tuning: Adaptive Transfer from A Zoo of ModelsWith the development of deep networks on various large-scale datasets, a large zoo of pretrained models are available. When transferring from a model zoo, applying classic single-model-based transfer learning methods to each source model suffers from high computational cost and cannot fully utilize the rich knowledge in the zoo. We propose \emph{Zoo-Tuning} to address these challenges, which learns to adaptively transfer the parameters of pretrained models to the target task. With the learnable channel alignment layer and adaptive aggregation layer, Zoo-Tuning \emph{adaptively aggregates channel aligned pretrained parameters to derive the target model}, which simultaneously promotes knowledge transfer and adapts source models to downstream tasks. The adaptive aggregation substantially reduces the computation cost at both training and inference. We further propose lite Zoo-Tuning with the temporal ensemble of batch average gating values to reduce the storage cost at the inference time. We evaluate our approach on a variety of tasks, including reinforcement learning, image classification, and facial landmark detection. Experiment results demonstrate that the proposed adaptive transfer learning approach can more effectively and efficiently transfer knowledge from a zoo of models.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/shu21b.html
http://proceedings.mlr.press/v139/shu21b.htmlAGENT: A Benchmark for Core Psychological ReasoningFor machine agents to successfully interact with humans in real-world settings, they will need to develop an understanding of human mental life. Intuitive psychology, the ability to reason about hidden mental variables that drive observable actions, comes naturally to people: even pre-verbal infants can tell agents from objects, expecting agents to act efficiently to achieve goals given constraints. Despite recent interest in machine agents that reason about other agents, it is not clear if such agents learn or hold the core psychology principles that drive human reasoning. Inspired by cognitive development studies on intuitive psychology, we present a benchmark consisting of a large dataset of procedurally generated 3D animations, AGENT (Action, Goal, Efficiency, coNstraint, uTility), structured around four scenarios (goal preferences, action efficiency, unobserved constraints, and cost-reward trade-offs) that probe key concepts of core intuitive psychology. We validate AGENT with human-ratings, propose an evaluation protocol emphasizing generalization, and compare two strong baselines built on Bayesian inverse planning and a Theory of Mind neural network. Our results suggest that to pass the designed tests of core intuitive psychology at human levels, a model must acquire or have built-in representations of how agents plan, combining utility computations and core knowledge of objects and physics.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/shu21a.html
http://proceedings.mlr.press/v139/shu21a.htmlLarge-Scale Meta-Learning with Continual Trajectory ShiftingMeta-learning of shared initialization parameters has shown to be highly effective in solving few-shot learning tasks. However, extending the framework to many-shot scenarios, which may further enhance its practicality, has been relatively overlooked due to the technical difficulties of meta-learning over long chains of inner-gradient steps. In this paper, we first show that allowing the meta-learners to take a larger number of inner gradient steps better captures the structure of heterogeneous and large-scale task distributions, thus results in obtaining better initialization points. Further, in order to increase the frequency of meta-updates even with the excessively long inner-optimization trajectories, we propose to estimate the required shift of the task-specific parameters with respect to the change of the initialization parameters. By doing so, we can arbitrarily increase the frequency of meta-updates and thus greatly improve the meta-level convergence as well as the quality of the learned initializations. We validate our method on a heterogeneous set of large-scale tasks, and show that the algorithm largely outperforms the previous first-order meta-learning methods in terms of both generalization performance and convergence, as well as multi-task learning and fine-tuning baselines.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/shin21a.html
http://proceedings.mlr.press/v139/shin21a.htmlGANMEX: One-vs-One Attributions using GAN-based Model ExplainabilityAttribution methods have been shown as promising approaches for identifying key features that led to learned model predictions. While most existing attribution methods rely on a baseline input for performing feature perturbations, limited research has been conducted to address the baseline selection issues. Poor choices of baselines limit the ability of one-vs-one explanations for multi-class classifiers, which means the attribution methods were not able to explain why an input belongs to its original class but not the other specified target class. Achieving one-vs-one explanation is crucial when certain classes are more similar than others, e.g. two bird types among multiple animals, by focusing on key differentiating features rather than shared features across classes. In this paper, we present GANMEX, a novel approach applying Generative Adversarial Networks (GAN) by incorporating the to-be-explained classifier as part of the adversarial networks. Our approach effectively selects the baseline as the closest realistic sample belong to the target class, which allows attribution methods to provide true one-vs-one explanations. We showed that GANMEX baselines improved the saliency maps and led to stronger performance on multiple evaluation metrics over the existing baselines. Existing attribution results are known for being insensitive to model randomization, and we demonstrated that GANMEX baselines led to better outcome under the cascading randomization of the model.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/shih21a.html
http://proceedings.mlr.press/v139/shih21a.htmlDeeply-Debiased Off-Policy Interval EstimationOff-policy evaluation learns a target policy’s value with a historical dataset generated by a different behavior policy. In addition to a point estimate, many applications would benefit significantly from having a confidence interval (CI) that quantifies the uncertainty of the point estimate. In this paper, we propose a novel procedure to construct an efficient, robust, and flexible CI on a target policy’s value. Our method is justified by theoretical results and numerical experiments. A Python implementation of the proposed procedure is available at https://github.com/ RunzheStat/D2OPE.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/shi21d.html
http://proceedings.mlr.press/v139/shi21d.htmlSegmenting Hybrid Trajectories using Latent ODEsSmooth dynamics interrupted by discontinuities are known as hybrid systems and arise commonly in nature. Latent ODEs allow for powerful representation of irregularly sampled time series but are not designed to capture trajectories arising from hybrid systems. Here, we propose the Latent Segmented ODE (LatSegODE), which uses Latent ODEs to perform reconstruction and changepoint detection within hybrid trajectories featuring jump discontinuities and switching dynamical modes. Where it is possible to train a Latent ODE on the smooth dynamical flows between discontinuities, we apply the pruned exact linear time (PELT) algorithm to detect changepoints where latent dynamics restart, thereby maximizing the joint probability of a piece-wise continuous latent dynamical representation. We propose usage of the marginal likelihood as a score function for PELT, circumventing the need for model-complexity-based penalization. The LatSegODE outperforms baselines in reconstructive and segmentation tasks including synthetic data sets of sine waves, Lotka Volterra dynamics, and UCI Character Trajectories.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/shi21c.html
http://proceedings.mlr.press/v139/shi21c.htmlLearning Gradient Fields for Molecular Conformation GenerationWe study a fundamental problem in computational chemistry known as molecular conformation generation, trying to predict stable 3D structures from 2D molecular graphs. Existing machine learning approaches usually first predict distances between atoms and then generate a 3D structure satisfying the distances, where noise in predicted distances may induce extra errors during 3D coordinate generation. Inspired by the traditional force field methods for molecular dynamics simulation, in this paper, we propose a novel approach called ConfGF by directly estimating the gradient fields of the log density of atomic coordinates. The estimated gradient fields allow directly generating stable conformations via Langevin dynamics. However, the problem is very challenging as the gradient fields are roto-translation equivariant. We notice that estimating the gradient fields of atomic coordinates can be translated to estimating the gradient fields of interatomic distances, and hence develop a novel algorithm based on recent score-based generative models to effectively estimate these gradients. Experimental results across multiple tasks show that ConfGF outperforms previous state-of-the-art baselines by a significant margin.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/shi21b.html
http://proceedings.mlr.press/v139/shi21b.htmlSparseBERT: Rethinking the Importance Analysis in Self-attentionTransformer-based models are popularly used in natural language processing (NLP). Its core component, self-attention, has aroused widespread interest. To understand the self-attention mechanism, a direct method is to visualize the attention map of a pre-trained model. Based on the patterns observed, a series of efficient Transformers with different sparse attention masks have been proposed. From a theoretical perspective, universal approximability of Transformer-based models is also recently proved. However, the above understanding and analysis of self-attention is based on a pre-trained model. To rethink the importance analysis in self-attention, we study the significance of different positions in attention matrix during pre-training. A surprising result is that diagonal elements in the attention map are the least important compared with other attention positions. We provide a proof showing that these diagonal elements can indeed be removed without deteriorating model performance. Furthermore, we propose a Differentiable Attention Mask (DAM) algorithm, which further guides the design of the SparseBERT. Extensive experiments verify our interesting findings and illustrate the effect of the proposed algorithm.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/shi21a.html
http://proceedings.mlr.press/v139/shi21a.htmlState Relevance for Off-Policy EvaluationImportance sampling-based estimators for off-policy evaluation (OPE) are valued for their simplicity, unbiasedness, and reliance on relatively few assumptions. However, the variance of these estimators is often high, especially when trajectories are of different lengths. In this work, we introduce Omitting-States-Irrelevant-to-Return Importance Sampling (OSIRIS), an estimator which reduces variance by strategically omitting likelihood ratios associated with certain states. We formalize the conditions under which OSIRIS is unbiased and has lower variance than ordinary importance sampling, and we demonstrate these properties empirically.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/shen21d.html
http://proceedings.mlr.press/v139/shen21d.htmlBackdoor Scanning for Deep Neural Networks through K-Arm OptimizationBack-door attack poses a severe threat to deep learning systems. It injects hidden malicious behaviors to a model such that any input stamped with a special pattern can trigger such behaviors. Detecting back-door is hence of pressing need. Many existing defense techniques use optimization to generate the smallest input pattern that forces the model to misclassify a set of benign inputs injected with the pattern to a target label. However, the complexity is quadratic to the number of class labels such that they can hardly handle models with many classes. Inspired by Multi-Arm Bandit in Reinforcement Learning, we propose a K-Arm optimization method for backdoor detection. By iteratively and stochastically selecting the most promising labels for optimization with the guidance of an objective function, we substantially reduce the complexity, allowing to handle models with many classes. Moreover, by iteratively refining the selection of labels to optimize, it substantially mitigates the uncertainty in choosing the right labels, improving detection accuracy. At the time of submission, the evaluation of our method on over 4000 models in the IARPA TrojAI competition from round 1 to the latest round 4 achieves top performance on the leaderboard. Our technique also supersedes five state-of-the-art techniques in terms of accuracy and the scanning time needed. The code of our work is available at https://github.com/PurduePAML/K-ARM_Backdoor_OptimizationThu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/shen21c.html
http://proceedings.mlr.press/v139/shen21c.htmlSample-Optimal PAC Learning of Halfspaces with Malicious NoiseWe study efficient PAC learning of homogeneous halfspaces in $\mathbb{R}^d$ in the presence of malicious noise of Valiant (1985). This is a challenging noise model and only until recently has near-optimal noise tolerance bound been established under the mild condition that the unlabeled data distribution is isotropic log-concave. However, it remains unsettled how to obtain the optimal sample complexity simultaneously. In this work, we present a new analysis for the algorithm of Awasthi et al. (2017) and show that it essentially achieves the near-optimal sample complexity bound of $\tilde{O}(d)$, improving the best known result of $\tilde{O}(d^2)$. Our main ingredient is a novel incorporation of a matrix Chernoff-type inequality to bound the spectrum of an empirical covariance matrix for well-behaved distributions, in conjunction with a careful exploration of the localization schemes of Awasthi et al. (2017). We further extend the algorithm and analysis to the more general and stronger nasty noise model of Bshouty et al. (2002), showing that it is still possible to achieve near-optimal noise tolerance and sample complexity in polynomial time.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/shen21b.html
http://proceedings.mlr.press/v139/shen21b.htmlOn the Power of Localized Perceptron for Label-Optimal Learning of Halfspaces with Adversarial NoiseWe study {\em online} active learning of homogeneous halfspaces in $\mathbb{R}^d$ with adversarial noise where the overall probability of a noisy label is constrained to be at most $\nu$. Our main contribution is a Perceptron-like online active learning algorithm that runs in polynomial time, and under the conditions that the marginal distribution is isotropic log-concave and $\nu = \Omega(\epsilon)$, where $\epsilon \in (0, 1)$ is the target error rate, our algorithm PAC learns the underlying halfspace with near-optimal label complexity of $\tilde{O}\big(d \cdot \polylog(\frac{1}{\epsilon})\big)$ and sample complexity of $\tilde{O}\big(\frac{d}{\epsilon} \big)$. Prior to this work, existing online algorithms designed for tolerating the adversarial noise are subject to either label complexity polynomial in $\frac{1}{\epsilon}$, or suboptimal noise tolerance, or restrictive marginal distributions. With the additional prior knowledge that the underlying halfspace is $s$-sparse, we obtain attribute-efficient label complexity of $\tilde{O}\big( s \cdot \polylog(d, \frac{1}{\epsilon}) \big)$ and sample complexity of $\tilde{O}\big(\frac{s}{\epsilon} \cdot \polylog(d) \big)$. As an immediate corollary, we show that under the agnostic model where no assumption is made on the noise rate $\nu$, our active learner achieves an error rate of $O(OPT) + \epsilon$ with the same running time and label and sample complexity, where $OPT$ is the best possible error rate achievable by any homogeneous halfspace.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/shen21a.html
http://proceedings.mlr.press/v139/shen21a.htmlPersonalized Federated Learning using HypernetworksPersonalized federated learning is tasked with training machine learning models for multiple clients, each with its own data distribution. The goal is to train personalized models collaboratively while accounting for data disparities across clients and reducing communication costs. We propose a novel approach to this problem using hypernetworks, termed pFedHN for personalized Federated HyperNetworks. In this approach, a central hypernetwork model is trained to generate a set of models, one model for each client. This architecture provides effective parameter sharing across clients while maintaining the capacity to generate unique and diverse personal models. Furthermore, since hypernetwork parameters are never transmitted, this approach decouples the communication cost from the trainable model size. We test pFedHN empirically in several personalized federated learning challenges and find that it outperforms previous methods. Finally, since hypernetworks share information across clients, we show that pFedHN can generalize better to new clients whose distributions differ from any client observed during training.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/shamsian21a.html
http://proceedings.mlr.press/v139/shamsian21a.htmlEquivariant Networks for Pixelized SpheresPixelizations of Platonic solids such as the cube and icosahedron have been widely used to represent spherical data, from climate records to Cosmic Microwave Background maps. Platonic solids have well-known global symmetries. Once we pixelize each face of the solid, each face also possesses its own local symmetries in the form of Euclidean isometries. One way to combine these symmetries is through a hierarchy. However, this approach does not adequately model the interplay between the two levels of symmetry transformations. We show how to model this interplay using ideas from group theory, identify the equivariant linear maps, and introduce equivariant padding that respects these symmetries. Deep networks that use these maps as their building blocks generalize gauge equivariant CNNs on pixelized spheres. These deep networks achieve state-of-the-art results on semantic segmentation for climate data and omnidirectional image processing. Code is available at https://git.io/JGiZA.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/shakerinava21a.html
http://proceedings.mlr.press/v139/shakerinava21a.htmlRRL: Resnet as representation for Reinforcement LearningThe ability to autonomously learn behaviors via direct interactions in uninstrumented environments can lead to generalist robots capable of enhancing productivity or providing care in unstructured settings like homes. Such uninstrumented settings warrant operations only using the robot’s proprioceptive sensor such as onboard cameras, joint encoders, etc which can be challenging for policy learning owing to the high dimensionality and partial observability issues. We propose RRL: Resnet as representation for Reinforcement Learning {–} a straightforward yet effective approach that can learn complex behaviors directly from proprioceptive inputs. RRL fuses features extracted from pre-trained Resnet into the standard reinforcement learning pipeline and delivers results comparable to learning directly from the state. In a simulated dexterous manipulation benchmark, where the state of the art methods fails to make significant progress, RRL delivers contact rich behaviors. The appeal of RRL lies in its simplicity in bringing together progress from the fields of Representation Learning, Imitation Learning, and Reinforcement Learning. Its effectiveness in learning behaviors directly from visual inputs with performance and sample efficiency matching learning directly from the state, even in complex high dimensional domains, is far from obvious.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/shah21a.html
http://proceedings.mlr.press/v139/shah21a.htmlOnline Submodular Resource Allocation with Applications to Rebalancing Shared Mobility SystemsMotivated by applications in shared mobility, we address the problem of allocating a group of agents to a set of resources to maximize a cumulative welfare objective. We model the welfare obtainable from each resource as a monotone DR-submodular function which is a-priori unknown and can only be learned by observing the welfare of selected allocations. Moreover, these functions can depend on time-varying contextual information. We propose a distributed scheme to maximize the cumulative welfare by designing a repeated game among the agents, who learn to act via regret minimization. We propose two design choices for the game rewards based on upper confidence bounds built around the unknown welfare functions. We analyze them theoretically, bounding the gap between the cumulative welfare of the game and the highest cumulative welfare obtainable in hindsight. Finally, we evaluate our approach in a realistic case study of rebalancing a shared mobility system (i.e., positioning vehicles in strategic areas). From observed trip data, our algorithm gradually learns the users’ demand pattern and improves the overall system operation.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/sessa21a.html
http://proceedings.mlr.press/v139/sessa21a.htmlState Entropy Maximization with Random Encoders for Efficient ExplorationRecent exploration methods have proven to be a recipe for improving sample-efficiency in deep reinforcement learning (RL). However, efficient exploration in high-dimensional observation spaces still remains a challenge. This paper presents Random Encoders for Efficient Exploration (RE3), an exploration method that utilizes state entropy as an intrinsic reward. In order to estimate state entropy in environments with high-dimensional observations, we utilize a k-nearest neighbor entropy estimator in the low-dimensional representation space of a convolutional encoder. In particular, we find that the state entropy can be estimated in a stable and compute-efficient manner by utilizing a randomly initialized encoder, which is fixed throughout training. Our experiments show that RE3 significantly improves the sample-efficiency of both model-free and model-based RL methods on locomotion and navigation tasks from DeepMind Control Suite and MiniGrid benchmarks. We also show that RE3 allows learning diverse behaviors without extrinsic rewards, effectively improving sample-efficiency in downstream tasks.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/seo21a.html
http://proceedings.mlr.press/v139/seo21a.htmlPure Exploration and Regret Minimization in Matching BanditsFinding an optimal matching in a weighted graph is a standard combinatorial problem. We consider its semi-bandit version where either a pair or a full matching is sampled sequentially. We prove that it is possible to leverage a rank-1 assumption on the adjacency matrix to reduce the sample complexity and the regret of off-the-shelf algorithms up to reaching a linear dependency in the number of vertices (up to to poly-log terms).Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/sentenac21a.html
http://proceedings.mlr.press/v139/sentenac21a.htmlTop-k eXtreme Contextual Bandits with Arm HierarchyMotivated by modern applications, such as online advertisement and recommender systems, we study the top-$k$ extreme contextual bandits problem, where the total number of arms can be enormous, and the learner is allowed to select $k$ arms and observe all or some of the rewards for the chosen arms. We first propose an algorithm for the non-extreme realizable setting, utilizing the Inverse Gap Weighting strategy for selecting multiple arms. We show that our algorithm has a regret guarantee of $O(k\sqrt{(A-k+1)T \log (|F|T)})$, where $A$ is the total number of arms and $F$ is the class containing the regression function, while only requiring $\tilde{O}(A)$ computation per time step. In the extreme setting, where the total number of arms can be in the millions, we propose a practically-motivated arm hierarchy model that induces a certain structure in mean rewards to ensure statistical and computational efficiency. The hierarchical structure allows for an exponential reduction in the number of relevant arms for each context, thus resulting in a regret guarantee of $O(k\sqrt{(\log A-k+1)T \log (|F|T)})$. Finally, we implement our algorithm using a hierarchical linear function class and show superior performance with respect to well-known benchmarks on simulated bandit feedback experiments using extreme multi-label classification datasets. On a dataset with three million arms, our reduction scheme has an average inference time of only 7.9 milliseconds, which is a 100x improvement.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/sen21a.html
http://proceedings.mlr.press/v139/sen21a.htmlLearning Intra-Batch Connections for Deep Metric LearningThe goal of metric learning is to learn a function that maps samples to a lower-dimensional space where similar samples lie closer than dissimilar ones. Particularly, deep metric learning utilizes neural networks to learn such a mapping. Most approaches rely on losses that only take the relations between pairs or triplets of samples into account, which either belong to the same class or two different classes. However, these methods do not explore the embedding space in its entirety. To this end, we propose an approach based on message passing networks that takes all the relations in a mini-batch into account. We refine embedding vectors by exchanging messages among all samples in a given batch allowing the training process to be aware of its overall structure. Since not all samples are equally important to predict a decision boundary, we use an attention mechanism during message passing to allow samples to weigh the importance of each neighbor accordingly. We achieve state-of-the-art results on clustering and image retrieval on the CUB-200-2011, Cars196, Stanford Online Products, and In-Shop Clothes datasets. To facilitate further research, we make available the code and the models at https://github.com/dvl-tum/intra_batch_connections.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/seidenschwarz21a.html
http://proceedings.mlr.press/v139/seidenschwarz21a.htmlConnecting Sphere Manifolds Hierarchically for RegularizationThis paper considers classification problems with hierarchically organized classes. We force the classifier (hyperplane) of each class to belong to a sphere manifold, whose center is the classifier of its super-class. Then, individual sphere manifolds are connected based on their hierarchical relations. Our technique replaces the last layer of a neural network by combining a spherical fully-connected layer with a hierarchical layer. This regularization is shown to improve the performance of widely used deep neural network architectures (ResNet and DenseNet) on publicly available datasets (CIFAR100, CUB200, Stanford dogs, Stanford cars, and Tiny-ImageNet).Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/scieur21a.html
http://proceedings.mlr.press/v139/scieur21a.htmlJust How Toxic is Data Poisoning? A Unified Benchmark for Backdoor and Data Poisoning AttacksData poisoning and backdoor attacks manipulate training data in order to cause models to fail during inference. A recent survey of industry practitioners found that data poisoning is the number one concern among threats ranging from model stealing to adversarial attacks. However, it remains unclear exactly how dangerous poisoning methods are and which ones are more effective considering that these methods, even ones with identical objectives, have not been tested in consistent or realistic settings. We observe that data poisoning and backdoor attacks are highly sensitive to variations in the testing setup. Moreover, we find that existing methods may not generalize to realistic settings. While these existing works serve as valuable prototypes for data poisoning, we apply rigorous tests to determine the extent to which we should fear them. In order to promote fair comparison in future work, we develop standardized benchmarks for data poisoning and backdoor attacks.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/schwarzschild21a.html
http://proceedings.mlr.press/v139/schwarzschild21a.htmlEquivariant message passing for the prediction of tensorial properties and molecular spectraMessage passing neural networks have become a method of choice for learning on graphs, in particular the prediction of chemical properties and the acceleration of molecular dynamics studies. While they readily scale to large training data sets, previous approaches have proven to be less data efficient than kernel methods. We identify limitations of invariant representations as a major reason and extend the message passing formulation to rotationally equivariant representations. On this basis, we propose the polarizable atom interaction neural network (PaiNN) and improve on common molecule benchmarks over previous networks, while reducing model size and inference time. We leverage the equivariant atomwise representations obtained by PaiNN for the prediction of tensorial properties. Finally, we apply this to the simulation of molecular spectra, achieving speedups of 4-5 orders of magnitude compared to the electronic structure reference.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/schutt21a.html
http://proceedings.mlr.press/v139/schutt21a.htmlDescending through a Crowded Valley - Benchmarking Deep Learning OptimizersChoosing the optimizer is considered to be among the most crucial design decisions in deep learning, and it is not an easy one. The growing literature now lists hundreds of optimization methods. In the absence of clear theoretical guidance and conclusive empirical evidence, the decision is often made based on anecdotes. In this work, we aim to replace these anecdotes, if not with a conclusive ranking, then at least with evidence-backed heuristics. To do so, we perform an extensive, standardized benchmark of fifteen particularly popular deep learning optimizers while giving a concise overview of the wide range of possible choices. Analyzing more than 50,000 individual runs, we contribute the following three points: (i) Optimizer performance varies greatly across tasks. (ii) We observe that evaluating multiple optimizers with default parameters works approximately as well as tuning the hyperparameters of a single, fixed optimizer. (iii) While we cannot discern an optimization method clearly dominating across all tested tasks, we identify a significantly reduced subset of specific optimizers and parameter choices that generally lead to competitive results in our experiments: Adam remains a strong contender, with newer methods failing to significantly and consistently outperform it. Our open-sourced results are available as challenging and well-tuned baselines for more meaningful evaluations of novel optimization methods without requiring any further computational efforts.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/schmidt21a.html
http://proceedings.mlr.press/v139/schmidt21a.htmlLinear Transformers Are Secretly Fast Weight ProgrammersWe show the formal equivalence of linearised self-attention mechanisms and fast weight controllers from the early ’90s, where a slow neural net learns by gradient descent to program the fast weights of another net through sequences of elementary programming instructions which are additive outer products of self-invented activation patterns (today called keys and values). Such Fast Weight Programmers (FWPs) learn to manipulate the contents of a finite memory and dynamically interact with it. We infer a memory capacity limitation of recent linearised softmax attention variants, and replace the purely additive outer products by a delta rule-like programming instruction, such that the FWP can more easily learn to correct the current mapping from keys to values. The FWP also learns to compute dynamically changing learning rates. We also propose a new kernel function to linearise attention which balances simplicity and effectiveness. We conduct experiments on synthetic retrieval problems as well as standard machine translation and language modelling tasks which demonstrate the benefits of our methods.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/schlag21a.html
http://proceedings.mlr.press/v139/schlag21a.htmlLow-Rank Sinkhorn FactorizationSeveral recent applications of optimal transport (OT) theory to machine learning have relied on regularization, notably entropy and the Sinkhorn algorithm. Because matrix-vector products are pervasive in the Sinkhorn algorithm, several works have proposed to \textit{approximate} kernel matrices appearing in its iterations using low-rank factors. Another route lies instead in imposing low-nonnegative rank constraints on the feasible set of couplings considered in OT problems, with no approximations on cost nor kernel matrices. This route was first explored by \citet{forrow2018statistical}, who proposed an algorithm tailored for the squared Euclidean ground cost, using a proxy objective that can be solved through the machinery of regularized 2-Wasserstein barycenters. Building on this, we introduce in this work a generic approach that aims at solving, in full generality, the OT problem under low-nonnegative rank constraints with arbitrary costs. Our algorithm relies on an explicit factorization of low-rank couplings as a product of \textit{sub-coupling} factors linked by a common marginal; similar to an NMF approach, we alternatively updates these factors. We prove the non-asymptotic stationary convergence of this algorithm and illustrate its efficiency on benchmark experiments.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/scetbon21a.html
http://proceedings.mlr.press/v139/scetbon21a.htmlA Representation Learning Perspective on the Importance of Train-Validation Splitting in Meta-LearningAn effective approach in meta-learning is to utilize multiple “train tasks” to learn a good initialization for model parameters that can help solve unseen “test tasks” with very few samples by fine-tuning from this initialization. Although successful in practice, theoretical understanding of such methods is limited. This work studies an important aspect of these methods: splitting the data from each task into train (support) and validation (query) sets during meta-training. Inspired by recent work (Raghu et al., 2020), we view such meta-learning methods through the lens of representation learning and argue that the train-validation split encourages the learned representation to be {\em low-rank} without compromising on expressivity, as opposed to the non-splitting variant that encourages high-rank representations. Since sample efficiency benefits from low-rankness, the splitting strategy will require very few samples to solve unseen test tasks. We present theoretical results that formalize this idea for linear representation learning on a subspace meta-learning instance, and experimentally verify this practical benefit of splitting in simulations and on standard meta-learning benchmarks.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/saunshi21a.html
http://proceedings.mlr.press/v139/saunshi21a.htmlE(n) Equivariant Graph Neural NetworksThis paper introduces a new model to learn graph neural networks equivariant to rotations, translations, reflections and permutations called E(n)-Equivariant Graph Neural Networks (EGNNs). In contrast with existing methods, our work does not require computationally expensive higher-order representations in intermediate layers while it still achieves competitive or better performance. In addition, whereas existing methods are limited to equivariance on 3 dimensional spaces, our model is easily scaled to higher-dimensional spaces. We demonstrate the effectiveness of our method on dynamical systems modelling, representation learning in graph autoencoders and predicting molecular properties.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/satorras21a.html
http://proceedings.mlr.press/v139/satorras21a.htmlTowards Understanding Learning in Neural Networks with Linear TeachersCan a neural network minimizing cross-entropy learn linearly separable data? Despite progress in the theory of deep learning, this question remains unsolved. Here we prove that SGD globally optimizes this learning problem for a two-layer network with Leaky ReLU activations. The learned network can in principle be very complex. However, empirical evidence suggests that it often turns out to be approximately linear. We provide theoretical support for this phenomenon by proving that if network weights converge to two weight clusters, this will imply an approximately linear decision boundary. Finally, we show a condition on the optimization that leads to weight clustering. We provide empirical results that validate our theoretical analysis.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/sarussi21a.html
http://proceedings.mlr.press/v139/sarussi21a.htmlRecomposing the Reinforcement Learning Building Blocks with HypernetworksThe Reinforcement Learning (RL) building blocks, i.e. $Q$-functions and policy networks, usually take elements from the cartesian product of two domains as input. In particular, the input of the $Q$-function is both the state and the action, and in multi-task problems (Meta-RL) the policy can take a state and a context. Standard architectures tend to ignore these variables’ underlying interpretations and simply concatenate their features into a single vector. In this work, we argue that this choice may lead to poor gradient estimation in actor-critic algorithms and high variance learning steps in Meta-RL algorithms. To consider the interaction between the input variables, we suggest using a Hypernetwork architecture where a primary network determines the weights of a conditional dynamic network. We show that this approach improves the gradient approximation and reduces the learning step variance, which both accelerates learning and improves the final performance. We demonstrate a consistent improvement across different locomotion tasks and different algorithms both in RL (TD3 and SAC) and in Meta-RL (MAML and PEARL).Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/sarafian21a.html
http://proceedings.mlr.press/v139/sarafian21a.htmlMeta-Learning Bidirectional Update RulesIn this paper, we introduce a new type of generalized neural network where neurons and synapses maintain multiple states. We show that classical gradient-based backpropagation in neural networks can be seen as a special case of a two-state network where one state is used for activations and another for gradients, with update rules derived from the chain rule. In our generalized framework, networks have neither explicit notion of nor ever receive gradients. The synapses and neurons are updated using a bidirectional Hebb-style update rule parameterized by a shared low-dimensional "genome". We show that such genomes can be meta-learned from scratch, using either conventional optimization techniques, or evolutionary strategies, such as CMA-ES. Resulting update rules generalize to unseen tasks and train faster than gradient descent based optimizers for several standard computer vision and synthetic tasks.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/sandler21a.html
http://proceedings.mlr.press/v139/sandler21a.htmlMomentum Residual Neural NetworksThe training of deep residual neural networks (ResNets) with backpropagation has a memory cost that increases linearly with respect to the depth of the network. A simple way to circumvent this issue is to use reversible architectures. In this paper, we propose to change the forward rule of a ResNet by adding a momentum term. The resulting networks, momentum residual neural networks (MomentumNets), are invertible. Unlike previous invertible architectures, they can be used as a drop-in replacement for any existing ResNet block. We show that MomentumNets can be interpreted in the infinitesimal step size regime as second-order ordinary differential equations (ODEs) and exactly characterize how adding momentum progressively increases the representation capabilities of MomentumNets: they can learn any linear mapping up to a multiplicative factor, while ResNets cannot. In a learning to optimize setting, where convergence to a fixed point is required, we show theoretically and empirically that our method succeeds while existing invertible architectures fail. We show on CIFAR and ImageNet that MomentumNets have the same accuracy as ResNets, while having a much smaller memory footprint, and show that pre-trained MomentumNets are promising for fine-tuning models.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/sander21a.html
http://proceedings.mlr.press/v139/sander21a.htmlAsymptotics of Ridge Regression in Convolutional ModelsUnderstanding generalization and estimation error of estimators for simple models such as linear and generalized linear models has attracted a lot of attention recently. This is in part due to an interesting observation made in machine learning community that highly over-parameterized neural networks achieve zero training error, and yet they are able to generalize well over the test samples. This phenomenon is captured by the so called double descent curve, where the generalization error starts decreasing again after the interpolation threshold. A series of recent works tried to explain such phenomenon for simple models. In this work, we analyze the asymptotics of estimation error in ridge estimators for convolutional linear models. These convolutional inverse problems, also known as deconvolution, naturally arise in different fields such as seismology, imaging, and acoustics among others. Our results hold for a large class of input distributions that include i.i.d. features as a special case. We derive exact formulae for estimation error of ridge estimators that hold in a certain high-dimensional regime. We show the double descent phenomenon in our experiments for convolutional models and show that our theoretical results match the experiments.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/sahraee-ardakan21a.html
http://proceedings.mlr.press/v139/sahraee-ardakan21a.htmlOptimal regret algorithm for Pseudo-1d Bandit Convex OptimizationWe study online learning with bandit feedback (i.e. learner has access to only zeroth-order oracle) where cost/reward functions $\f_t$ admit a "pseudo-1d" structure, i.e. $\f_t(\w) = \loss_t(\pred_t(\w))$ where the output of $\pred_t$ is one-dimensional. At each round, the learner observes context $\x_t$, plays prediction $\pred_t(\w_t; \x_t)$ (e.g. $\pred_t(\cdot)=⟨\x_t, \cdot⟩$) for some $\w_t \in \mathbb{R}^d$ and observes loss $\loss_t(\pred_t(\w_t))$ where $\loss_t$ is a convex Lipschitz-continuous function. The goal is to minimize the standard regret metric. This pseudo-1d bandit convex optimization problem (\SBCO) arises frequently in domains such as online decision-making or parameter-tuning in large systems. For this problem, we first show a regret lower bound of $\min(\sqrt{dT}, T^{3/4})$ for any algorithm, where $T$ is the number of rounds. We propose a new algorithm \sbcalg that combines randomized online gradient descent with a kernelized exponential weights method to exploit the pseudo-1d structure effectively, guaranteeing the {\em optimal} regret bound mentioned above, up to additional logarithmic factors. In contrast, applying state-of-the-art online convex optimization methods leads to $\tilde{O}\left(\min\left(d^{9.5}\sqrt{T},\sqrt{d}T^{3/4}\right)\right)$ regret, that is significantly suboptimal in terms of $d$.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/saha21c.html
http://proceedings.mlr.press/v139/saha21c.htmlDueling Convex OptimizationWe address the problem of convex optimization with preference (dueling) feedback. Like the traditional optimization objective, the goal is to find the optimal point with the least possible query complexity, however, without the luxury of even a zeroth order feedback. Instead, the learner can only observe a single noisy bit which is win-loss feedback for a pair of queried points based on their function values. % The problem is certainly of great practical relevance as in many real-world scenarios, such as recommender systems or learning from customer preferences, where the system feedback is often restricted to just one binary-bit preference information. % We consider the problem of online convex optimization (OCO) solely by actively querying $\{0,1\}$ noisy-comparison feedback of decision point pairs, with the objective of finding a near-optimal point (function minimizer) with the least possible number of queries. %a very general class of monotonic, non-decreasing transfer functions, and analyze the problem for any $d$-dimensional smooth convex function. % For the non-stationary OCO setup, where the underlying convex function may change over time, we prove an impossibility result towards achieving the above objective. We next focus only on the stationary OCO problem, and our main contribution lies in designing a normalized gradient descent based algorithm towards finding a $\epsilon$-best optimal point. Towards this, our algorithm is shown to yield a convergence rate of $\tilde O(\nicefrac{d\beta}{\epsilon \nu^2})$ ($\nu$ being the noise parameter) when the underlying function is $\beta$-smooth. Further we show an improved convergence rate of just $\tilde O(\nicefrac{d\beta}{\alpha \nu^2} \log \frac{1}{\epsilon})$ when the function is additionally also $\alpha$-strongly convex.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/saha21b.html
http://proceedings.mlr.press/v139/saha21b.htmlAdversarial Dueling BanditsWe introduce the problem of regret minimization in Adversarial Dueling Bandits. As in classic Dueling Bandits, the learner has to repeatedly choose a pair of items and observe only a relative binary ‘win-loss’ feedback for this pair, but here this feedback is generated from an arbitrary preference matrix, possibly chosen adversarially. Our main result is an algorithm whose $T$-round regret compared to the \emph{Borda-winner} from a set of $K$ items is $\tilde{O}(K^{1/3}T^{2/3})$, as well as a matching $\Omega(K^{1/3}T^{2/3})$ lower bound. We also prove a similar high probability regret bound. We further consider a simpler \emph{fixed-gap} adversarial setup, which bridges between two extreme preference feedback models for dueling bandits: stationary preferences and an arbitrary sequence of preferences. For the fixed-gap adversarial setup we give an $\smash{ \tilde{O}((K/\Delta^2)\log{T}) }$ regret algorithm, where $\Delta$ is the gap in Borda scores between the best item and all other items, and show a lower bound of $\Omega(K/\Delta^2)$ indicating that our dependence on the main problem parameters $K$ and $\Delta$ is tight (up to logarithmic factors). Finally, we corroborate the theoretical results with empirical evaluations.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/saha21a.html
http://proceedings.mlr.press/v139/saha21a.htmlStochastic Sign Descent Methods: New Algorithms and Better TheoryVarious gradient compression schemes have been proposed to mitigate the communication cost in distributed training of large scale machine learning models. Sign-based methods, such as signSGD (Bernstein et al., 2018), have recently been gaining popularity because of their simple compression rule and connection to adaptive gradient methods, like ADAM. In this paper, we analyze sign-based methods for non-convex optimization in three key settings: (i) standard single node, (ii) parallel with shared data and (iii) distributed with partitioned data. For single machine case, we generalize the previous analysis of signSGD relying on intuitive bounds on success probabilities and allowing even biased estimators. Furthermore, we extend the analysis to parallel setting within a parameter server framework, where exponentially fast noise reduction is guaranteed with respect to number of nodes, maintaining $1$-bit compression in both directions and using small mini-batch sizes. Next, we identify a fundamental issue with signSGD to converge in distributed environment. To resolve this issue, we propose a new sign-based method, {\em Stochastic Sign Descent with Momentum (SSDM)}, which converges under standard bounded variance assumption with the optimal asymptotic rate. We validate several aspects of our theoretical findings with numerical experiments.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/safaryan21a.html
http://proceedings.mlr.press/v139/safaryan21a.htmlUnsupervised Part Representation by Flow CapsulesCapsule networks aim to parse images into a hierarchy of objects, parts and relations. While promising, they remain limited by an inability to learn effective low level part descriptions. To address this issue we propose a way to learn primary capsule encoders that detect atomic parts from a single image. During training we exploit motion as a powerful perceptual cue for part definition, with an expressive decoder for part generation within a layered image model with occlusion. Experiments demonstrate robust part discovery in the presence of multiple objects, cluttered backgrounds, and occlusion. The learned part decoder is shown to infer the underlying shape masks, effectively filling in occluded regions of the detected shapes. We evaluate FlowCapsules on unsupervised part segmentation and unsupervised image classification.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/sabour21a.html
http://proceedings.mlr.press/v139/sabour21a.htmlTraining Data Subset Selection for Regression with Controlled Generalization ErrorData subset selection from a large number of training instances has been a successful approach toward efficient and cost-effective machine learning. However, models trained on a smaller subset may show poor generalization ability. In this paper, our goal is to design an algorithm for selecting a subset of the training data, so that the model can be trained quickly, without significantly sacrificing on accuracy. More specifically, we focus on data subset selection for $L_2$ regularized regression problems and provide a novel problem formulation which seeks to minimize the training loss with respect to both the trainable parameters and the subset of training data, subject to error bounds on the validation set. We tackle this problem using several technical innovations. First, we represent this problem with simplified constraints using the dual of the original training problem and show that the objective of this new representation is a monotone and $\alpha$-submodular function, for a wide variety of modeling choices. Such properties lead us to develop SELCON, an efficient majorization-minimization algorithm for data subset selection, that admits an approximation guarantee even when the training provides an imperfect estimate of the trained model. Finally, our experiments on several datasets show that SELCON trades off accuracy and efficiency more effectively than the current state-of-the-art.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/s21a.html
http://proceedings.mlr.press/v139/s21a.htmlModel-Based Reinforcement Learning via Latent-Space CollocationThe ability to plan into the future while utilizing only raw high-dimensional observations, such as images, can provide autonomous agents with broad and general capabilities. However, realistic tasks require performing temporally extended reasoning, and cannot be solved with only myopic, short-sighted planning. Recent work in model-based reinforcement learning (RL) has shown impressive results on tasks that require only short-horizon reasoning. In this work, we study how the long-horizon planning abilities can be improved with an algorithm that optimizes over sequences of states, rather than actions, which allows better credit assignment. To achieve this, we draw on the idea of collocation and adapt it to the image-based setting by leveraging probabilistic latent variable models, resulting in an algorithm that optimizes trajectories over latent variables. Our latent collocation method (LatCo) provides a general and effective visual planning approach, and significantly outperforms prior model-based approaches on challenging visual control tasks with sparse rewards and long-term goals. See the videos on the supplementary website \url{https://sites.google.com/view/latco-mbrl/.}Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/rybkin21b.html
http://proceedings.mlr.press/v139/rybkin21b.htmlSimple and Effective VAE Training with Calibrated DecodersVariational autoencoders (VAEs) provide an effective and simple method for modeling complex distributions. However, training VAEs often requires considerable hyperparameter tuning to determine the optimal amount of information retained by the latent variable. We study the impact of calibrated decoders, which learn the uncertainty of the decoding distribution and can determine this amount of information automatically, on the VAE performance. While many methods for learning calibrated decoders have been proposed, many of the recent papers that employ VAEs rely on heuristic hyperparameters and ad-hoc modifications instead. We perform the first comprehensive comparative analysis of calibrated decoder and provide recommendations for simple and effective VAE training. Our analysis covers a range of datasets and several single-image and sequential VAE models. We further propose a simple but novel modification to the commonly used Gaussian decoder, which computes the prediction variance analytically. We observe empirically that using heuristic modifications is not necessary with our method.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/rybkin21a.html
http://proceedings.mlr.press/v139/rybkin21a.htmlUnICORNN: A recurrent model for learning very long time dependenciesThe design of recurrent neural networks (RNNs) to accurately process sequential inputs with long-time dependencies is very challenging on account of the exploding and vanishing gradient problem. To overcome this, we propose a novel RNN architecture which is based on a structure preserving discretization of a Hamiltonian system of second-order ordinary differential equations that models networks of oscillators. The resulting RNN is fast, invertible (in time), memory efficient and we derive rigorous bounds on the hidden state gradients to prove the mitigation of the exploding and vanishing gradient problem. A suite of experiments are presented to demonstrate that the proposed RNN provides state of the art performance on a variety of learning tasks with (very) long-time dependencies.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/rusch21a.html
http://proceedings.mlr.press/v139/rusch21a.htmlTilting the playing field: Dynamical loss functions for machine learningWe show that learning can be improved by using loss functions that evolve cyclically during training to emphasize one class at a time. In underparameterized networks, such dynamical loss functions can lead to successful training for networks that fail to find deep minima of the standard cross-entropy loss. In overparameterized networks, dynamical loss functions can lead to better generalization. Improvement arises from the interplay of the changing loss landscape with the dynamics of the system as it evolves to minimize the loss. In particular, as the loss function oscillates, instabilities develop in the form of bifurcation cascades, which we study using the Hessian and Neural Tangent Kernel. Valleys in the landscape widen and deepen, and then narrow and rise as the loss landscape changes during a cycle. As the landscape narrows, the learning rate becomes too large and the network becomes unstable and bounces around the valley. This process ultimately pushes the system into deeper and wider regions of the loss landscape and is characterized by decreasing eigenvalues of the Hessian. This results in better regularized models with improved generalization performance.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/ruiz-garcia21a.html
http://proceedings.mlr.press/v139/ruiz-garcia21a.htmlOn Signal-to-Noise Ratio Issues in Variational Inference for Deep Gaussian ProcessesWe show that the gradient estimates used in training Deep Gaussian Processes (DGPs) with importance-weighted variational inference are susceptible to signal-to-noise ratio (SNR) issues. Specifically, we show both theoretically and via an extensive empirical evaluation that the SNR of the gradient estimates for the latent variable’s variational parameters decreases as the number of importance samples increases. As a result, these gradient estimates degrade to pure noise if the number of importance samples is too large. To address this pathology, we show how doubly-reparameterized gradient estimators, originally proposed for training variational autoencoders, can be adapted to the DGP setting and that the resultant estimators completely remedy the SNR issue, thereby providing more reliable training. Finally, we demonstrate that our fix can lead to consistent improvements in the predictive performance of DGP models.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/rudner21a.html
http://proceedings.mlr.press/v139/rudner21a.htmlImproving Lossless Compression Rates via Monte Carlo Bits-Back CodingLatent variable models have been successfully applied in lossless compression with the bits-back coding algorithm. However, bits-back suffers from an increase in the bitrate equal to the KL divergence between the approximate posterior and the true posterior. In this paper, we show how to remove this gap asymptotically by deriving bits-back coding algorithms from tighter variational bounds. The key idea is to exploit extended space representations of Monte Carlo estimators of the marginal likelihood. Naively applied, our schemes would require more initial bits than the standard bits-back coder, but we show how to drastically reduce this additional cost with couplings in the latent space. When parallel architectures can be exploited, our coders can achieve better rates than bits-back with little additional cost. We demonstrate improved lossless compression rates in a variety of settings, especially in out-of-distribution or sequential data compression.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/ruan21a.html
http://proceedings.mlr.press/v139/ruan21a.htmlAn Algorithm for Stochastic and Adversarial Bandits with Switching CostsWe propose an algorithm for stochastic and adversarial multiarmed bandits with switching costs, where the algorithm pays a price $\lambda$ every time it switches the arm being played. Our algorithm is based on adaptation of the Tsallis-INF algorithm of Zimmert and Seldin (2021) and requires no prior knowledge of the regime or time horizon. In the oblivious adversarial setting it achieves the minimax optimal regret bound of $ O( (\lambda K)^{1/3}T^{2/3} + \sqrt{KT})$, where $T$ is the time horizon and $K$ is the number of arms. In the stochastically constrained adversarial regime, which includes the stochastic regime as a special case, it achieves a regret bound of $O((\lambda K)^{2/3} T^{1/3} + \ln T)\sum_{i \neq i^*} \Delta_i^{-1})$, where $\Delta_i$ are suboptimality gaps and $i^*$ is the unique optimal arm. In the special case of $\lambda = 0$ (no switching costs), both bounds are minimax optimal within constants. We also explore variants of the problem, where switching cost is allowed to change over time. We provide experimental evaluation showing competitiveness of our algorithm with the relevant baselines in the stochastic, stochastically constrained adversarial, and adversarial regimes with fixed switching cost.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/rouyer21a.html
http://proceedings.mlr.press/v139/rouyer21a.htmlPACOH: Bayes-Optimal Meta-Learning with PAC-GuaranteesMeta-learning can successfully acquire useful inductive biases from data. Yet, its generalization properties to unseen learning tasks are poorly understood. Particularly if the number of meta-training tasks is small, this raises concerns about overfitting. We provide a theoretical analysis using the PAC-Bayesian framework and derive novel generalization bounds for meta-learning. Using these bounds, we develop a class of PAC-optimal meta-learning algorithms with performance guarantees and a principled meta-level regularization. Unlike previous PAC-Bayesian meta-learners, our method results in a standard stochastic optimization problem which can be solved efficiently and scales well.When instantiating our PAC-optimal hyper-posterior (PACOH) with Gaussian processes and Bayesian Neural Networks as base learners, the resulting methods yield state-of-the-art performance, both in terms of predictive accuracy and the quality of uncertainty estimates. Thanks to their principled treatment of uncertainty, our meta-learners can also be successfully employed for sequential decision problems.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/rothfuss21a.html
http://proceedings.mlr.press/v139/rothfuss21a.htmlMulti-group Agnostic PAC LearnabilityAn agnostic PAC learning algorithm finds a predictor that is competitive with the best predictor in a benchmark hypothesis class, where competitiveness is measured with respect to a given loss function. However, its predictions might be quite sub-optimal for structured subgroups of individuals, such as protected demographic groups. Motivated by such fairness concerns, we study “multi-group agnostic PAC learnability”: fixing a measure of loss, a benchmark class $\H$ and a (potentially) rich collection of subgroups $\G$, the objective is to learn a single predictor such that the loss experienced by every group $g \in \G$ is not much larger than the best possible loss for this group within $\H$. Under natural conditions, we provide a characterization of the loss functions for which such a predictor is guaranteed to exist. For any such loss function we construct a learning algorithm whose sample complexity is logarithmic in the size of the collection $\G$. Our results unify and extend previous positive and negative results from the multi-group fairness literature, which applied for specific loss functions.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/rothblum21a.html
http://proceedings.mlr.press/v139/rothblum21a.htmlSimultaneous Similarity-based Self-Distillation for Deep Metric LearningDeep Metric Learning (DML) provides a crucial tool for visual similarity and zero-shot retrieval applications by learning generalizing embedding spaces, although recent work in DML has shown strong performance saturation across training objectives. However, generalization capacity is known to scale with the embedding space dimensionality. Unfortunately, high dimensional embeddings also create higher retrieval cost for downstream applications. To remedy this, we propose S2SD - Simultaneous Similarity-based Self-distillation. S2SD extends DML with knowledge distillation from auxiliary, high-dimensional embedding and feature spaces to leverage complementary context during training while retaining test-time cost and with negligible changes to the training time. Experiments and ablations across different objectives and standard benchmarks show S2SD offering highly significant improvements of up to 7% in Recall@1, while also setting a new state-of-the-art.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/roth21a.html
http://proceedings.mlr.press/v139/roth21a.htmlBenchmarks, Algorithms, and Metrics for Hierarchical DisentanglementIn representation learning, there has been recent interest in developing algorithms to disentangle the ground-truth generative factors behind a dataset, and metrics to quantify how fully this occurs. However, these algorithms and metrics often assume that both representations and ground-truth factors are flat, continuous, and factorized, whereas many real-world generative processes involve rich hierarchical structure, mixtures of discrete and continuous variables with dependence between them, and even varying intrinsic dimensionality. In this work, we develop benchmarks, algorithms, and metrics for learning such hierarchical representations.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/ross21a.html
http://proceedings.mlr.press/v139/ross21a.htmlOn the Predictability of Pruning Across ScalesWe show that the error of iteratively magnitude-pruned networks empirically follows a scaling law with interpretable coefficients that depend on the architecture and task. We functionally approximate the error of the pruned networks, showing it is predictable in terms of an invariant tying width, depth, and pruning level, such that networks of vastly different pruned densities are interchangeable. We demonstrate the accuracy of this approximation over orders of magnitude in depth, width, dataset size, and density. We show that the functional form holds (generalizes) for large scale data (e.g., ImageNet) and architectures (e.g., ResNets). As neural networks become ever larger and costlier to train, our findings suggest a framework for reasoning conceptually and analytically about a standard method for unstructured pruning.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/rosenfeld21a.html
http://proceedings.mlr.press/v139/rosenfeld21a.htmlDiscretization Drift in Two-Player GamesGradient-based methods for two-player games produce rich dynamics that can solve challenging problems, yet can be difficult to stabilize and understand. Part of this complexity originates from the discrete update steps given by simultaneous or alternating gradient descent, which causes each player to drift away from the continuous gradient flow – a phenomenon we call discretization drift. Using backward error analysis, we derive modified continuous dynamical systems that closely follow the discrete dynamics. These modified dynamics provide an insight into the notorious challenges associated with zero-sum games, including Generative Adversarial Networks. In particular, we identify distinct components of the discretization drift that can alter performance and in some cases destabilize the game. Finally, quantifying discretization drift allows us to identify regularizers that explicitly cancel harmful forms of drift or strengthen beneficial forms of drift, and thus improve performance of GAN training.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/rosca21a.html
http://proceedings.mlr.press/v139/rosca21a.htmlTeachMyAgent: a Benchmark for Automatic Curriculum Learning in Deep RLTraining autonomous agents able to generalize to multiple tasks is a key target of Deep Reinforcement Learning (DRL) research. In parallel to improving DRL algorithms themselves, Automatic Curriculum Learning (ACL) study how teacher algorithms can train DRL agents more efficiently by adapting task selection to their evolving abilities. While multiple standard benchmarks exist to compare DRL agents, there is currently no such thing for ACL algorithms. Thus, comparing existing approaches is difficult, as too many experimental parameters differ from paper to paper. In this work, we identify several key challenges faced by ACL algorithms. Based on these, we present TeachMyAgent (TA), a benchmark of current ACL algorithms leveraging procedural task generation. It includes 1) challenge-specific unit-tests using variants of a procedural Box2D bipedal walker environment, and 2) a new procedural Parkour environment combining most ACL challenges, making it ideal for global performance assessment. We then use TeachMyAgent to conduct a comparative study of representative existing approaches, showcasing the competitiveness of some ACL algorithms that do not use expert knowledge. We also show that the Parkour environment remains an open problem. We open-source our environments, all studied ACL algorithms (collected from open-source code or re-implemented), and DRL students in a Python package available at https://github.com/flowersteam/TeachMyAgent.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/romac21a.html
http://proceedings.mlr.press/v139/romac21a.htmlRepresentation Matters: Assessing the Importance of Subgroup Allocations in Training DataCollecting more diverse and representative training data is often touted as a remedy for the disparate performance of machine learning predictors across subpopulations. However, a precise framework for understanding how dataset properties like diversity affect learning outcomes is largely lacking. By casting data collection as part of the learning process, we demonstrate that diverse representation in training data is key not only to increasing subgroup performances, but also to achieving population-level objectives. Our analysis and experiments describe how dataset compositions influence performance and provide constructive results for using trends in existing data, alongside domain knowledge, to help guide intentional, objective-aware dataset designThu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/rolf21a.html
http://proceedings.mlr.press/v139/rolf21a.htmlOn Linear Identifiability of Learned RepresentationsIdentifiability is a desirable property of a statistical model: it implies that the true model parameters may be estimated to any desired precision, given sufficient computational resources and data. We study identifiability in the context of representation learning: discovering nonlinear data representations that are optimal with respect to some downstream task. When parameterized as deep neural networks, such representation functions lack identifiability in parameter space, because they are over-parameterized by design. In this paper, building on recent advances in nonlinear Independent Components Analysis, we aim to rehabilitate identifiability by showing that a large family of discriminative models are in fact identifiable in function space, up to a linear indeterminacy. Many models for representation learning in a wide variety of domains have been identifiable in this sense, including text, images and audio, state-of-the-art at time of publication. We derive sufficient conditions for linear identifiability and provide empirical support for the result on both simulated and real-world data.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/roeder21a.html
http://proceedings.mlr.press/v139/roeder21a.htmlPrincipled Simplicial Neural Networks for Trajectory PredictionWe consider the construction of neural network architectures for data on simplicial complexes. In studying maps on the chain complex of a simplicial complex, we define three desirable properties of a simplicial neural network architecture: namely, permutation equivariance, orientation equivariance, and simplicial awareness. The first two properties respectively account for the fact that the node indexing and the simplex orientations in a simplicial complex are arbitrary. The last property encodes the desirable feature that the output of the neural network depends on the entire simplicial complex and not on a subset of its dimensions. Based on these properties, we propose a simple convolutional architecture, rooted in tools from algebraic topology, for the problem of trajectory prediction, and show that it obeys all three of these properties when an odd, nonlinear activation function is used. We then demonstrate the effectiveness of this architecture in extrapolating trajectories on synthetic and real datasets, with particular emphasis on the gains in generalizability to unseen trajectories.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/roddenberry21a.html
http://proceedings.mlr.press/v139/roddenberry21a.htmlBest Arm Identification in Graphical Bilinear BanditsWe introduce a new graphical bilinear bandit problem where a learner (or a \emph{central entity}) allocates arms to the nodes of a graph and observes for each edge a noisy bilinear reward representing the interaction between the two end nodes. We study the best arm identification problem in which the learner wants to find the graph allocation maximizing the sum of the bilinear rewards. By efficiently exploiting the geometry of this bandit problem, we propose a \emph{decentralized} allocation strategy based on random sampling with theoretical guarantees. In particular, we characterize the influence of the graph structure (e.g. star, complete or circle) on the convergence rate and propose empirical experiments that confirm this dependency.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/rizk21a.html
http://proceedings.mlr.press/v139/rizk21a.htmlSolving high-dimensional parabolic PDEs using the tensor train formatHigh-dimensional partial differential equations (PDEs) are ubiquitous in economics, science and engineering. However, their numerical treatment poses formidable challenges since traditional grid-based methods tend to be frustrated by the curse of dimensionality. In this paper, we argue that tensor trains provide an appealing approximation framework for parabolic PDEs: the combination of reformulations in terms of backward stochastic differential equations and regression-type methods in the tensor format holds the promise of leveraging latent low-rank structures enabling both compression and efficient computation. Following this paradigm, we develop novel iterative schemes, involving either explicit and fast or implicit and accurate updates. We demonstrate in a number of examples that our methods achieve a favorable trade-off between accuracy and computational efficiency in comparison with state-of-the-art neural network based approaches.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/richter21a.html
http://proceedings.mlr.press/v139/richter21a.htmlIntegrated Defense for Resilient Graph MatchingA recent study has shown that graph matching models are vulnerable to adversarial manipulation of their input which is intended to cause a mismatching. Nevertheless, there is still a lack of a comprehensive solution for further enhancing the robustness of graph matching against adversarial attacks. In this paper, we identify and study two types of unique topology attacks in graph matching: inter-graph dispersion and intra-graph assembly attacks. We propose an integrated defense model, IDRGM, for resilient graph matching with two novel defense techniques to defend against the above two attacks simultaneously. A detection technique of inscribed simplexes in the hyperspheres consisting of multiple matched nodes is proposed to tackle inter-graph dispersion attacks, in which the distances among the matched nodes in multiple graphs are maximized to form regular simplexes. A node separation method based on phase-type distribution and maximum likelihood estimation is developed to estimate the distribution of perturbed graphs and separate the nodes within the same graphs over a wide space, for defending intra-graph assembly attacks, such that the interference from the similar neighbors of the perturbed nodes is significantly reduced. We evaluate the robustness of our IDRGM model on real datasets against state-of-the-art algorithms.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/ren21c.html
http://proceedings.mlr.press/v139/ren21c.htmlInterpreting and Disentangling Feature Components of Various Complexity from DNNsThis paper aims to define, visualize, and analyze the feature complexity that is learned by a DNN. We propose a generic definition for the feature complexity. Given the feature of a certain layer in the DNN, our method decomposes and visualizes feature components of different complexity orders from the feature. The feature decomposition enables us to evaluate the reliability, the effectiveness, and the significance of over-fitting of these feature components. Furthermore, such analysis helps to improve the performance of DNNs. As a generic method, the feature complexity also provides new insights into existing deep-learning techniques, such as network compression and knowledge distillation.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/ren21b.html
http://proceedings.mlr.press/v139/ren21b.htmlLEGO: Latent Execution-Guided Reasoning for Multi-Hop Question Answering on Knowledge GraphsAnswering complex natural language questions on knowledge graphs (KGQA) is a challenging task. It requires reasoning with the input natural language questions as well as a massive, incomplete heterogeneous KG. Prior methods obtain an abstract structured query graph/tree from the input question and traverse the KG for answers following the query tree. However, they inherently cannot deal with missing links in the KG. Here we present LEGO, a Latent Execution-Guided reasOning framework to handle this challenge in KGQA. LEGO works in an iterative way, which alternates between (1) a Query Synthesizer, which synthesizes a reasoning action and grows the query tree step-by-step, and (2) a Latent Space Executor that executes the reasoning action in the latent embedding space to combat against the missing information in KG. To learn the synthesizer without step-wise supervision, we design a generic latent execution guided bottom-up search procedure to find good execution traces efficiently in the vast query space. Experimental results on several KGQA benchmarks demonstrate the effectiveness of our framework compared with previous state of the art.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/ren21a.html
http://proceedings.mlr.press/v139/ren21a.htmlSharf: Shape-conditioned Radiance Fields from a Single ViewWe present a method for estimating neural scenes representations of objects given only a single image. The core of our method is the estimation of a geometric scaffold for the object and its use as a guide for the reconstruction of the underlying radiance field. Our formulation is based on a generative process that first maps a latent code to a voxelized shape, and then renders it to an image, with the object appearance being controlled by a second latent code. During inference, we optimize both the latent codes and the networks to fit a test image of a new object. The explicit disentanglement of shape and appearance allows our model to be fine-tuned given a single image. We can then render new views in a geometrically consistent manner and they represent faithfully the input object. Additionally, our method is able to generalize to images outside of the training domain (more realistic renderings and even real photographs). Finally, the inferred geometric scaffold is itself an accurate estimate of the object’s 3D shape. We demonstrate in several experiments the effectiveness of our approach in both synthetic and real images.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/rematas21a.html
http://proceedings.mlr.press/v139/rematas21a.htmlClassifying high-dimensional Gaussian mixtures: Where kernel methods fail and neural networks succeedA recent series of theoretical works showed that the dynamics of neural networks with a certain initialisation are well-captured by kernel methods. Concurrent empirical work demonstrated that kernel methods can come close to the performance of neural networks on some image classification tasks. These results raise the question of whether neural networks only learn successfully if kernels also learn successfully, despite being the more expressive function class. Here, we show that two-layer neural networks with *only a few neurons* achieve near-optimal performance on high-dimensional Gaussian mixture classification while lazy training approaches such as random features and kernel methods do not. Our analysis is based on the derivation of a set of ordinary differential equations that exactly track the dynamics of the network and thus allow to extract the asymptotic performance of the network as a function of regularisation or signal-to-noise ratio. We also show how over-parametrising the neural network leads to faster convergence, but does not improve its final performance.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/refinetti21b.html
http://proceedings.mlr.press/v139/refinetti21b.htmlAlign, then memorise: the dynamics of learning with feedback alignmentDirect Feedback Alignment (DFA) is emerging as an efficient and biologically plausible alternative to backpropagation for training deep neural networks. Despite relying on random feedback weights for the backward pass, DFA successfully trains state-of-the-art models such as Transformers. On the other hand, it notoriously fails to train convolutional networks. An understanding of the inner workings of DFA to explain these diverging results remains elusive. Here, we propose a theory of feedback alignment algorithms. We first show that learning in shallow networks proceeds in two steps: an alignment phase, where the model adapts its weights to align the approximate gradient with the true gradient of the loss function, is followed by a memorisation phase, where the model focuses on fitting the data. This two-step process has a degeneracy breaking effect: out of all the low-loss solutions in the landscape, a net-work trained with DFA naturally converges to the solution which maximises gradient alignment. We also identify a key quantity underlying alignment in deep linear networks: the conditioning of the alignment matrices. The latter enables a detailed understanding of the impact of data structure on alignment, and suggests a simple explanation for the well-known failure of DFA to train convolutional neural networks. Numerical experiments on MNIST and CIFAR10 clearly demonstrate degeneracy breaking in deep non-linear networks and show that the align-then-memorize process occurs sequentially from the bottom layers of the network to the top.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/refinetti21a.html
http://proceedings.mlr.press/v139/refinetti21a.htmlImplicit Regularization in Tensor FactorizationRecent efforts to unravel the mystery of implicit regularization in deep learning have led to a theoretical focus on matrix factorization — matrix completion via linear neural network. As a step further towards practical deep learning, we provide the first theoretical analysis of implicit regularization in tensor factorization — tensor completion via certain type of non-linear neural network. We circumvent the notorious difficulty of tensor problems by adopting a dynamical systems perspective, and characterizing the evolution induced by gradient descent. The characterization suggests a form of greedy low tensor rank search, which we rigorously prove under certain conditions, and empirically demonstrate under others. Motivated by tensor rank capturing the implicit regularization of a non-linear neural network, we empirically explore it as a measure of complexity, and find that it captures the essence of datasets on which neural networks generalize. This leads us to believe that tensor rank may pave way to explaining both implicit regularization in deep learning, and the properties of real-world data translating this implicit regularization to generalization.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/razin21a.html
http://proceedings.mlr.press/v139/razin21a.htmlCross-domain Imitation from ObservationsImitation learning seeks to circumvent the difficulty in designing proper reward functions for training agents by utilizing expert behavior. With environments modeled as Markov Decision Processes (MDP), most of the existing imitation algorithms are contingent on the availability of expert demonstrations in the same MDP as the one in which a new imitation policy is to be learned. In this paper, we study the problem of how to imitate tasks when discrepancies exist between the expert and agent MDP. These discrepancies across domains could include differing dynamics, viewpoint, or morphology; we present a novel framework to learn correspondences across such domains. Importantly, in contrast to prior works, we use unpaired and unaligned trajectories containing only states in the expert domain, to learn this correspondence. We utilize a cycle-consistency constraint on both the state space and a domain agnostic latent space to do this. In addition, we enforce consistency on the temporal position of states via a normalized position estimator function, to align the trajectories across the two domains. Once this correspondence is found, we can directly transfer the demonstrations on one domain to the other and use it for imitation. Experiments across a wide variety of challenging domains demonstrate the efficacy of our approach.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/raychaudhuri21a.html
http://proceedings.mlr.press/v139/raychaudhuri21a.htmlDisentangling Sampling and Labeling Bias for Learning in Large-output SpacesNegative sampling schemes enable efficient training given a large number of classes, by offering a means to approximate a computationally expensive loss function that takes all labels into account. In this paper, we present a new connection between these schemes and loss modification techniques for countering label imbalance. We show that different negative sampling schemes implicitly trade-off performance on dominant versus rare labels. Further, we provide a unified means to explicitly tackle both sampling bias, arising from working with a subset of all labels, and labeling bias, which is inherent to the data due to label imbalance. We empirically verify our findings on long-tail classification and retrieval benchmarks.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/rawat21a.html
http://proceedings.mlr.press/v139/rawat21a.htmlEnhancing Robustness of Neural Networks through Fourier StabilizationDespite the considerable success of neural networks in security settings such as malware detection, such models have proved vulnerable to evasion attacks, in which attackers make slight changes to inputs (e.g., malware) to bypass detection. We propose a novel approach, Fourier stabilization, for designing evasion-robust neural networks with binary inputs. This approach, which is complementary to other forms of defense, replaces the weights of individual neurons with robust analogs derived using Fourier analytic tools. The choice of which neurons to stabilize in a neural network is then a combinatorial optimization problem, and we propose several methods for approximately solving it. We provide a formal bound on the per-neuron drop in accuracy due to Fourier stabilization, and experimentally demonstrate the effectiveness of the proposed approach in boosting robustness of neural networks in several detection settings. Moreover, we show that our approach effectively composes with adversarial training.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/raviv21a.html
http://proceedings.mlr.press/v139/raviv21a.htmlGenerative Particle Variational Inference via Estimation of Functional GradientsRecently, particle-based variational inference (ParVI) methods have gained interest because they can avoid arbitrary parametric assumptions that are common in variational inference. However, many ParVI approaches do not allow arbitrary sampling from the posterior, and the few that do allow such sampling suffer from suboptimality. This work proposes a new method for learning to approximately sample from the posterior distribution. We construct a neural sampler that is trained with the functional gradient of the KL-divergence between the empirical sampling distribution and the target distribution, assuming the gradient resides within a reproducing kernel Hilbert space. Our generative ParVI (GPVI) approach maintains the asymptotic performance of ParVI methods while offering the flexibility of a generative sampler. Through carefully constructed experiments, we show that GPVI outperforms previous generative ParVI methods such as amortized SVGD, and is competitive with ParVI as well as gold-standard approaches like Hamiltonian Monte Carlo for fitting both exactly known and intractable target distributions.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/ratzlaff21a.html
http://proceedings.mlr.press/v139/ratzlaff21a.htmlAutoregressive Denoising Diffusion Models for Multivariate Probabilistic Time Series ForecastingIn this work, we propose TimeGrad, an autoregressive model for multivariate probabilistic time series forecasting which samples from the data distribution at each time step by estimating its gradient. To this end, we use diffusion probabilistic models, a class of latent variable models closely connected to score matching and energy-based methods. Our model learns gradients by optimizing a variational bound on the data likelihood and at inference time converts white noise into a sample of the distribution of interest through a Markov chain using Langevin sampling. We demonstrate experimentally that the proposed autoregressive denoising diffusion model is the new state-of-the-art multivariate probabilistic forecasting method on real-world data sets with thousands of correlated dimensions. We hope that this method is a useful tool for practitioners and lays the foundation for future research in this area.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/rasul21a.html
http://proceedings.mlr.press/v139/rasul21a.htmlMSA TransformerUnsupervised protein language models trained across millions of diverse sequences learn structure and function of proteins. Protein language models studied to date have been trained to perform inference from individual sequences. The longstanding approach in computational biology has been to make inferences from a family of evolutionarily related sequences by fitting a model to each family independently. In this work we combine the two paradigms. We introduce a protein language model which takes as input a set of sequences in the form of a multiple sequence alignment. The model interleaves row and column attention across the input sequences and is trained with a variant of the masked language modeling objective across many protein families. The performance of the model surpasses current state-of-the-art unsupervised structure learning methods by a wide margin, with far greater parameter efficiency than prior state-of-the-art protein language models.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/rao21a.html
http://proceedings.mlr.press/v139/rao21a.htmlEnd-to-End Learning of Coherent Probabilistic Forecasts for Hierarchical Time SeriesThis paper presents a novel approach for hierarchical time series forecasting that produces coherent, probabilistic forecasts without requiring any explicit post-processing reconciliation. Unlike the state-of-the-art, the proposed method simultaneously learns from all time series in the hierarchy and incorporates the reconciliation step into a single trainable model. This is achieved by applying the reparameterization trick and casting reconciliation as an optimization problem with a closed-form solution. These model features make end-to-end learning of hierarchical forecasts possible, while accomplishing the challenging task of generating forecasts that are both probabilistic and coherent. Importantly, our approach also accommodates general aggregation constraints including grouped and temporal hierarchies. An extensive empirical evaluation on real-world hierarchical datasets demonstrates the advantages of the proposed approach over the state-of-the-art.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/rangapuram21a.html
http://proceedings.mlr.press/v139/rangapuram21a.htmlZero-Shot Text-to-Image GenerationText-to-image generation has traditionally focused on finding better modeling assumptions for training on a fixed dataset. These assumptions might involve complex architectures, auxiliary losses, or side information such as object part labels or segmentation masks supplied during training. We describe a simple approach for this task based on a transformer that autoregressively models the text and image tokens as a single stream of data. With sufficient data and scale, our approach is competitive with previous domain-specific models when evaluated in a zero-shot fashion.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/ramesh21a.html
http://proceedings.mlr.press/v139/ramesh21a.htmlDifferentially Private Sliced Wasserstein DistanceDeveloping machine learning methods that are privacy preserving is today a central topic of research, with huge practical impacts. Among the numerous ways to address privacy-preserving learning, we here take the perspective of computing the divergences between distributions under the Differential Privacy (DP) framework — being able to compute divergences between distributions is pivotal for many machine learning problems, such as learning generative models or domain adaptation problems. Instead of resorting to the popular gradient-based sanitization method for DP, we tackle the problem at its roots by focusing on the Sliced Wasserstein Distance and seamlessly making it differentially private. Our main contribution is as follows: we analyze the property of adding a Gaussian perturbation to the intrinsic randomized mechanism of the Sliced Wasserstein Distance, and we establish the sensitivity of the resulting differentially private mechanism. One of our important findings is that this DP mechanism transforms the Sliced Wasserstein distance into another distance, that we call the Smoothed Sliced Wasserstein Distance. This new differentially private distribution distance can be plugged into generative models and domain adaptation algorithms in a transparent way, and we empirically show that it yields highly competitive performance compared with gradient-based DP approaches from the literature, with almost no loss in accuracy for the domain adaptation problems that we consider.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/rakotomamonjy21a.html
http://proceedings.mlr.press/v139/rakotomamonjy21a.htmlHierarchical Clustering of Data Streams: Scalable Algorithms and Approximation GuaranteesWe investigate the problem of hierarchically clustering data streams containing metric data in R^d. We introduce a desirable invariance property for such algorithms, describe a general family of hyperplane-based methods enjoying this property, and analyze two scalable instances of this general family against recently popularized similarity/dissimilarity-based metrics for hierarchical clustering. We prove a number of new results related to the approximation ratios of these algorithms, improving in various ways over the literature on this subject. Finally, since our algorithms are principled but also very practical, we carry out an experimental comparison on both synthetic and real-world datasets showing competitive results against known baselines.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/rajagopalan21a.html
http://proceedings.mlr.press/v139/rajagopalan21a.htmlDecoupling Value and Policy for Generalization in Reinforcement LearningStandard deep reinforcement learning algorithms use a shared representation for the policy and value function, especially when training directly from images. However, we argue that more information is needed to accurately estimate the value function than to learn the optimal policy. Consequently, the use of a shared representation for the policy and value function can lead to overfitting. To alleviate this problem, we propose two approaches which are combined to create IDAAC: Invariant Decoupled Advantage Actor-Critic. First, IDAAC decouples the optimization of the policy and value function, using separate networks to model them. Second, it introduces an auxiliary loss which encourages the representation to be invariant to task-irrelevant properties of the environment. IDAAC shows good generalization to unseen environments, achieving a new state-of-the-art on the Procgen benchmark and outperforming popular methods on DeepMind Control tasks with distractors. Our implementation is available at https://github.com/rraileanu/idaac.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/raileanu21a.html
http://proceedings.mlr.press/v139/raileanu21a.htmlTowards Open Ad Hoc Teamwork Using Graph-based Policy LearningAd hoc teamwork is the challenging problem of designing an autonomous agent which can adapt quickly to collaborate with teammates without prior coordination mechanisms, including joint training. Prior work in this area has focused on closed teams in which the number of agents is fixed. In this work, we consider open teams by allowing agents with different fixed policies to enter and leave the environment without prior notification. Our solution builds on graph neural networks to learn agent models and joint-action value models under varying team compositions. We contribute a novel action-value computation that integrates the agent model and joint-action value model to produce action-value estimates. We empirically demonstrate that our approach successfully models the effects other agents have on the learner, leading to policies that robustly adapt to dynamic team compositions and significantly outperform several alternative methods.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/rahman21a.html
http://proceedings.mlr.press/v139/rahman21a.htmlA General Framework For Detecting Anomalous Inputs to DNN ClassifiersDetecting anomalous inputs, such as adversarial and out-of-distribution (OOD) inputs, is critical for classifiers (including deep neural networks or DNNs) deployed in real-world applications. While prior works have proposed various methods to detect such anomalous samples using information from the internal layer representations of a DNN, there is a lack of consensus on a principled approach for the different components of such a detection method. As a result, often heuristic and one-off methods are applied for different aspects of this problem. We propose an unsupervised anomaly detection framework based on the internal DNN layer representations in the form of a meta-algorithm with configurable components. We proceed to propose specific instantiations for each component of the meta-algorithm based on ideas grounded in statistical testing and anomaly detection. We evaluate the proposed methods on well-known image classification datasets with strong adversarial attacks and OOD inputs, including an adaptive attack that uses the internal layer representations of the DNN (often not considered in prior work). Comparisons with five recently-proposed competing detection methods demonstrates the effectiveness of our method in detecting adversarial and OOD inputs.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/raghuram21a.html
http://proceedings.mlr.press/v139/raghuram21a.htmlLearning Transferable Visual Models From Natural Language SupervisionState-of-the-art computer vision systems are trained to predict a fixed set of predetermined object categories. This restricted form of supervision limits their generality and usability since additional labeled data is needed to specify any other visual concept. Learning directly from raw text about images is a promising alternative which leverages a much broader source of supervision. We demonstrate that the simple pre-training task of predicting which caption goes with which image is an efficient and scalable way to learn SOTA image representations from scratch on a dataset of 400 million (image, text) pairs collected from the internet. After pre-training, natural language is used to reference learned visual concepts (or describe new ones) enabling zero-shot transfer of the model to downstream tasks. We study the performance of this approach by benchmarking on over 30 different existing computer vision datasets, spanning tasks such as OCR, action recognition in videos, geo-localization, and many types of fine-grained object classification. The model transfers non-trivially to most tasks and is often competitive with a fully supervised baseline without the need for any dataset specific training. For instance, we match the accuracy of the original ResNet-50 on ImageNet zero-shot without needing to use any of the 1.28 million training examples it was trained on.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/radford21a.html
http://proceedings.mlr.press/v139/radford21a.htmlOn Reward-Free RL with Kernel and Neural Function Approximations: Single-Agent MDP and Markov GameTo achieve sample efficiency in reinforcement learning (RL), it necessitates to efficiently explore the underlying environment. Under the offline setting, addressing the exploration challenge lies in collecting an offline dataset with sufficient coverage. Motivated by such a challenge, we study the reward-free RL problem, where an agent aims to thoroughly explore the environment without any pre-specified reward function. Then, given any extrinsic reward, the agent computes the optimal policy via offline RL with data collected in the exploration stage. Moreover, we tackle this problem under the context of function approximation, leveraging powerful function approximators. Specifically, we propose to explore via an optimistic variant of the value-iteration algorithm incorporating kernel and neural function approximations, where we adopt the associated exploration bonus as the exploration reward. Moreover, we design exploration and planning algorithms for both single-agent MDPs and zero-sum Markov games and prove that our methods can achieve $\widetilde{\mathcal{O}}(1 /\varepsilon^2)$ sample complexity for generating a $\varepsilon$-suboptimal policy or $\varepsilon$-approximate Nash equilibrium when given an arbitrary extrinsic reward. To the best of our knowledge, we establish the first provably efficient reward-free RL algorithm with kernel and neural function approximators.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/qiu21d.html
http://proceedings.mlr.press/v139/qiu21d.htmlOptimization Planning for 3D ConvNetsIt is not trivial to optimally learn a 3D Convolutional Neural Networks (3D ConvNets) due to high complexity and various options of the training scheme. The most common hand-tuning process starts from learning 3D ConvNets using short video clips and then is followed by learning long-term temporal dependency using lengthy clips, while gradually decaying the learning rate from high to low as training progresses. The fact that such process comes along with several heuristic settings motivates the study to seek an optimal "path" to automate the entire training. In this paper, we decompose the path into a series of training "states" and specify the hyper-parameters, e.g., learning rate and the length of input clips, in each state. The estimation of the knee point on the performance-epoch curve triggers the transition from one state to another. We perform dynamic programming over all the candidate states to plan the optimal permutation of states, i.e., optimization path. Furthermore, we devise a new 3D ConvNets with a unique design of dual-head classifier to improve spatial and temporal discrimination. Extensive experiments on seven public video recognition benchmarks demonstrate the advantages of our proposal. With the optimization planning, our 3D ConvNets achieves superior results when comparing to the state-of-the-art recognition methods. More remarkably, we obtain the top-1 accuracy of 80.5% and 82.7% on Kinetics-400 and Kinetics-600 datasets, respectively.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/qiu21c.html
http://proceedings.mlr.press/v139/qiu21c.htmlProvably Efficient Fictitious Play Policy Optimization for Zero-Sum Markov Games with Structured TransitionsWhile single-agent policy optimization in a fixed environment has attracted a lot of research attention recently in the reinforcement learning community, much less is known theoretically when there are multiple agents playing in a potentially competitive environment. We take steps forward by proposing and analyzing new fictitious play policy optimization algorithms for two-player zero-sum Markov games with structured but unknown transitions. We consider two classes of transition structures: factored independent transition and single-controller transition. For both scenarios, we prove tight $\widetilde{\mathcal{O}}(\sqrt{T})$ regret bounds after $T$ steps in a two-agent competitive game scenario. The regret of each player is measured against a potentially adversarial opponent who can choose a single best policy in hindsight after observing the full policy sequence. Our algorithms feature a combination of Upper Confidence Bound (UCB)-type optimism and fictitious play under the scope of simultaneous policy optimization in a non-stationary environment. When both players adopt the proposed algorithms, their overall optimality gap is $\widetilde{\mathcal{O}}(\sqrt{T})$.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/qiu21b.html
http://proceedings.mlr.press/v139/qiu21b.htmlNeural Transformation Learning for Deep Anomaly Detection Beyond ImagesData transformations (e.g. rotations, reflections, and cropping) play an important role in self-supervised learning. Typically, images are transformed into different views, and neural networks trained on tasks involving these views produce useful feature representations for downstream tasks, including anomaly detection. However, for anomaly detection beyond image data, it is often unclear which transformations to use. Here we present a simple end-to-end procedure for anomaly detection with learnable transformations. The key idea is to embed the transformed data into a semantic space such that the transformed data still resemble their untransformed form, while different transformations are easily distinguishable. Extensive experiments on time series show that our proposed method outperforms existing approaches in the one-vs.-rest setting and is competitive in the more challenging n-vs.-rest anomaly-detection task. On medical and cyber-security tabular data, our method learns domain-specific transformations and detects anomalies more accurately than previous work.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/qiu21a.html
http://proceedings.mlr.press/v139/qiu21a.htmlBudgeted Heterogeneous Treatment Effect EstimationHeterogeneous treatment effect (HTE) estimation is receiving increasing interest due to its important applications in fields such as healthcare, economics, and education. Current HTE estimation methods generally assume the existence of abundant observational data, though the acquisition of such data can be costly. In some real scenarios, it is easy to access the pre-treatment covariates and treatment assignments, but expensive to obtain the factual outcomes. To make HTE estimation more practical, in this paper, we examine the problem of estimating HTEs with a budget constraint on observational data, aiming to obtain accurate HTE estimates with limited costs. By deriving an informative generalization bound and connecting to active learning, we propose an effective and efficient method which is validated both theoretically and empirically.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/qin21b.html
http://proceedings.mlr.press/v139/qin21b.htmlDensity Constrained Reinforcement LearningWe study constrained reinforcement learning (CRL) from a novel perspective by setting constraints directly on state density functions, rather than the value functions considered by previous works. State density has a clear physical and mathematical interpretation, and is able to express a wide variety of constraints such as resource limits and safety requirements. Density constraints can also avoid the time-consuming process of designing and tuning cost functions required by value function-based constraints to encode system specifications. We leverage the duality between density functions and Q functions to develop an effective algorithm to solve the density constrained RL problem optimally and the constrains are guaranteed to be satisfied. We prove that the proposed algorithm converges to a near-optimal solution with a bounded error even when the policy update is imperfect. We use a set of comprehensive experiments to demonstrate the advantages of our approach over state-of-the-art CRL methods, with a wide range of density constrained tasks as well as standard CRL benchmarks such as Safety-Gym.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/qin21a.html
http://proceedings.mlr.press/v139/qin21a.htmlOneshot Differentially Private Top-k SelectionBeing able to efficiently and accurately select the top-$k$ elements with differential privacy is an integral component of various private data analysis tasks. In this paper, we present the oneshot Laplace mechanism, which generalizes the well-known Report Noisy Max \cite{dwork2014algorithmic} mechanism to reporting noisy top-$k$ elements. We show that the oneshot Laplace mechanism with a noise level of $\widetilde{O}(\sqrt{k}/\eps)$ is approximately differentially private. Compared to the previous peeling approach of running Report Noisy Max $k$ times, the oneshot Laplace mechanism only adds noises and computes the top $k$ elements once, hence much more efficient for large $k$. In addition, our proof of privacy relies on a novel coupling technique that bypasses the composition theorems so without the linear dependence on $k$ which is inherent to various composition theorems. Finally, we present a novel application of efficient top-$k$ selection in the classical problem of ranking from pairwise comparisons.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/qiao21b.html
http://proceedings.mlr.press/v139/qiao21b.htmlEfficient Differentiable Simulation of Articulated BodiesWe present a method for efficient differentiable simulation of articulated bodies. This enables integration of articulated body dynamics into deep learning frameworks, and gradient-based optimization of neural networks that operate on articulated bodies. We derive the gradients of the contact solver using spatial algebra and the adjoint method. Our approach is an order of magnitude faster than autodiff tools. By only saving the initial states throughout the simulation process, our method reduces memory requirements by two orders of magnitude. We demonstrate the utility of efficient differentiable dynamics for articulated bodies in a variety of applications. We show that reinforcement learning with articulated systems can be accelerated using gradients provided by our method. In applications to control and inverse problems, gradient-based optimization enabled by our work accelerates convergence by more than an order of magnitude.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/qiao21a.html
http://proceedings.mlr.press/v139/qiao21a.htmlGlobal Prosody Style Transfer Without Text TranscriptionsProsody plays an important role in characterizing the style of a speaker or an emotion, but most non-parallel voice or emotion style transfer algorithms do not convert any prosody information. Two major components of prosody are pitch and rhythm. Disentangling the prosody information, particularly the rhythm component, from the speech is challenging because it involves breaking the synchrony between the input speech and the disentangled speech representation. As a result, most existing prosody style transfer algorithms would need to rely on some form of text transcriptions to identify the content information, which confines their application to high-resource languages only. Recently, SpeechSplit has made sizeable progress towards unsupervised prosody style transfer, but it is unable to extract high-level global prosody style in an unsupervised manner. In this paper, we propose AutoPST, which can disentangle global prosody style from speech without relying on any text transcriptions. AutoPST is an Autoencoder-based Prosody Style Transfer framework with a thorough rhythm removal module guided by the self-expressive representation learning. Experiments on different style transfer tasks show that AutoPST can effectively convert prosody that correctly reflects the styles of the target domains.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/qian21b.html
http://proceedings.mlr.press/v139/qian21b.htmlA Probabilistic Approach to Neural Network PruningNeural network pruning techniques reduce the number of parameters without compromising predicting ability of a network. Many algorithms have been developed for pruning both over-parameterized fully-connected networks (FCN) and convolutional neural networks (CNN), but analytical studies of capabilities and compression ratios of such pruned sub-networks are lacking. We theoretically study the performance of two pruning techniques (random and magnitude-based) on FCN and CNN. Given a target network, we provide a universal approach to bound the gap between a pruned and the target network in a probabilistic sense, which is the first study of this nature. The results establish that there exist pruned networks with expressive power within any specified bound from the target network and with a significant compression ratio.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/qian21a.html
http://proceedings.mlr.press/v139/qian21a.htmlBANG: Bridging Autoregressive and Non-autoregressive Generation with Large Scale PretrainingIn this paper, we propose BANG, a new pretraining model to Bridge the gap between Autoregressive (AR) and Non-autoregressive (NAR) Generation. AR and NAR generation can be uniformly regarded as to what extent previous tokens can be attended, and BANG bridges AR and NAR generation through designing a novel model structure for large-scale pre-training. A pretrained BANG model can simultaneously support AR, NAR, and semi-NAR generation to meet different requirements. Experiments on question generation (SQuAD 1.1), summarization (XSum), and dialogue generation (PersonaChat) show that BANG improves NAR and semi-NAR performance significantly as well as attaining comparable performance with strong AR pretrained models. Compared with the semi-NAR strong baselines, BANG achieves absolute improvements of 14.01 and 5.24 in the overall scores of SQuAD 1.1 and XSum, respectively. In addition, BANG achieves absolute improvements of 10.73, 6.39, and 5.90 in the overall scores of SQuAD, XSUM, and PersonaChat compared with the NAR strong baselines, respectively. Our code will be made publicly available.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/qi21a.html
http://proceedings.mlr.press/v139/qi21a.htmlDense for the Price of Sparse: Improved Performance of Sparsely Initialized Networks via a Subspace OffsetThat neural networks may be pruned to high sparsities and retain high accuracy is well established. Recent research efforts focus on pruning immediately after initialization so as to allow the computational savings afforded by sparsity to extend to the training process. In this work, we introduce a new ‘DCT plus Sparse’ layer architecture, which maintains information propagation and trainability even with as little as 0.01% trainable parameters remaining. We show that standard training of networks built with these layers, and pruned at initialization, achieves state-of-the-art accuracy for extreme sparsities on a variety of benchmark network architectures and datasets. Moreover, these results are achieved using only simple heuristics to determine the locations of the trainable parameters in the network, and thus without having to initially store or compute with the full, unpruned network, as is required by competing prune-at-initialization algorithms. Switching from standard sparse layers to DCT plus Sparse layers does not increase the storage footprint of a network and incurs only a small additional computational overhead.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/price21a.html
http://proceedings.mlr.press/v139/price21a.htmlBias-Free Scalable Gaussian Processes via Randomized TruncationsScalable Gaussian Process methods are computationally attractive, yet introduce modeling biases that require rigorous study. This paper analyzes two common techniques: early truncated conjugate gradients (CG) and random Fourier features (RFF). We find that both methods introduce a systematic bias on the learned hyperparameters: CG tends to underfit while RFF tends to overfit. We address these issues using randomized truncation estimators that eliminate bias in exchange for increased variance. In the case of RFF, we show that the bias-to-variance conversion is indeed a trade-off: the additional variance proves detrimental to optimization. However, in the case of CG, our unbiased learning procedure meaningfully outperforms its biased counterpart with minimal additional computation. Our code is available at https://github.com/ cunningham-lab/RTGPS.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/potapczynski21a.html
http://proceedings.mlr.press/v139/potapczynski21a.htmlGrad-TTS: A Diffusion Probabilistic Model for Text-to-SpeechRecently, denoising diffusion probabilistic models and generative score matching have shown high potential in modelling complex data distributions while stochastic calculus has provided a unified point of view on these techniques allowing for flexible inference schemes. In this paper we introduce Grad-TTS, a novel text-to-speech model with score-based decoder producing mel-spectrograms by gradually transforming noise predicted by encoder and aligned with text input by means of Monotonic Alignment Search. The framework of stochastic differential equations helps us to generalize conventional diffusion probabilistic models to the case of reconstructing data from noise with different parameters and allows to make this reconstruction flexible by explicitly controlling trade-off between sound quality and inference speed. Subjective human evaluation shows that Grad-TTS is competitive with state-of-the-art text-to-speech approaches in terms of Mean Opinion Score.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/popov21a.html
http://proceedings.mlr.press/v139/popov21a.htmlGeomCA: Geometric Evaluation of Data RepresentationsEvaluating the quality of learned representations without relying on a downstream task remains one of the challenges in representation learning. In this work, we present Geometric Component Analysis (GeomCA) algorithm that evaluates representation spaces based on their geometric and topological properties. GeomCA can be applied to representations of any dimension, independently of the model that generated them. We demonstrate its applicability by analyzing representations obtained from a variety of scenarios, such as contrastive learning models, generative models and supervised learning models.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/poklukar21a.html
http://proceedings.mlr.press/v139/poklukar21a.htmlDG-LMC: A Turn-key and Scalable Synchronous Distributed MCMC Algorithm via Langevin Monte Carlo within GibbsPerforming reliable Bayesian inference on a big data scale is becoming a keystone in the modern era of machine learning. A workhorse class of methods to achieve this task are Markov chain Monte Carlo (MCMC) algorithms and their design to handle distributed datasets has been the subject of many works. However, existing methods are not completely either reliable or computationally efficient. In this paper, we propose to fill this gap in the case where the dataset is partitioned and stored on computing nodes within a cluster under a master/slaves architecture. We derive a user-friendly centralised distributed MCMC algorithm with provable scaling in high-dimensional settings. We illustrate the relevance of the proposed methodology on both synthetic and real data experiments.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/plassier21a.html
http://proceedings.mlr.press/v139/plassier21a.htmlTowards Practical Mean Bounds for Small SamplesHistorically, to bound the mean for small sample sizes, practitioners have had to choose between using methods with unrealistic assumptions about the unknown distribution (e.g., Gaussianity) and methods like Hoeffding’s inequality that use weaker assumptions but produce much looser (wider) intervals. In 1969, \citet{Anderson1969} proposed a mean confidence interval strictly better than or equal to Hoeffding’s whose only assumption is that the distribution’s support is contained in an interval $[a,b]$. For the first time since then, we present a new family of bounds that compares favorably to Anderson’s. We prove that each bound in the family has {\em guaranteed coverage}, i.e., it holds with probability at least $1-\alpha$ for all distributions on an interval $[a,b]$. Furthermore, one of the bounds is tighter than or equal to Anderson’s for all samples. In simulations, we show that for many distributions, the gain over Anderson’s bound is substantial.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/phan21a.html
http://proceedings.mlr.press/v139/phan21a.htmlMegaverse: Simulating Embodied Agents at One Million Experiences per SecondWe present Megaverse, a new 3D simulation platform for reinforcement learning and embodied AI research. The efficient design of our engine enables physics-based simulation with high-dimensional egocentric observations at more than 1,000,000 actions per second on a single 8-GPU node. Megaverse is up to 70x faster than DeepMind Lab in fully-shaded 3D scenes with interactive objects. We achieve this high simulation performance by leveraging batched simulation, thereby taking full advantage of the massive parallelism of modern GPUs. We use Megaverse to build a new benchmark that consists of several single-agent and multi-agent tasks covering a variety of cognitive challenges. We evaluate model-free RL on this benchmark to provide baselines and facilitate future research.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/petrenko21a.html
http://proceedings.mlr.press/v139/petrenko21a.htmlDifferentiable Sorting Networks for Scalable Sorting and Ranking SupervisionSorting and ranking supervision is a method for training neural networks end-to-end based on ordering constraints. That is, the ground truth order of sets of samples is known, while their absolute values remain unsupervised. For that, we propose differentiable sorting networks by relaxing their pairwise conditional swap operations. To address the problems of vanishing gradients and extensive blurring that arise with larger numbers of layers, we propose mapping activations to regions with moderate gradients. We consider odd-even as well as bitonic sorting networks, which outperform existing relaxations of the sorting operation. We show that bitonic sorting networks can achieve stable training on large input sets of up to 1024 elements.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/petersen21a.html
http://proceedings.mlr.press/v139/petersen21a.htmlSpectral Smoothing Unveils Phase Transitions in Hierarchical Variational AutoencodersVariational autoencoders with deep hierarchies of stochastic layers have been known to suffer from the problem of posterior collapse, where the top layers fall back to the prior and become independent of input. We suggest that the hierarchical VAE objective explicitly includes the variance of the function parameterizing the mean and variance of the latent Gaussian distribution which itself is often a high variance function. Building on this we generalize VAE neural networks by incorporating a smoothing parameter motivated by Gaussian analysis to reduce higher frequency components and consequently the variance in parameterizing functions and show that this can help to solve the problem of posterior collapse. We further show that under such smoothing the VAE loss exhibits a phase transition, where the top layer KL divergence sharply drops to zero at a critical value of the smoothing parameter that is similar for the same model across datasets. We validate the phenomenon across model configurations and datasets.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/pervez21a.html
http://proceedings.mlr.press/v139/pervez21a.htmlFrom Poincaré Recurrence to Convergence in Imperfect Information Games: Finding Equilibrium via RegularizationIn this paper we investigate the Follow the Regularized Leader dynamics in sequential imperfect information games (IIG). We generalize existing results of Poincar{é} recurrence from normal-form games to zero-sum two-player imperfect information games and other sequential game settings. We then investigate how adapting the reward (by adding a regularization term) of the game can give strong convergence guarantees in monotone games. We continue by showing how this reward adaptation technique can be leveraged to build algorithms that converge exactly to the Nash equilibrium. Finally, we show how these insights can be directly used to build state-of-the-art model-free algorithms for zero-sum two-player Imperfect Information Games (IIG).Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/perolat21a.html
http://proceedings.mlr.press/v139/perolat21a.htmlRissanen Data Analysis: Examining Dataset Characteristics via Description LengthWe introduce a method to determine if a certain capability helps to achieve an accurate model of given data. We view labels as being generated from the inputs by a program composed of subroutines with different capabilities, and we posit that a subroutine is useful if and only if the minimal program that invokes it is shorter than the one that does not. Since minimum program length is uncomputable, we instead estimate the labels’ minimum description length (MDL) as a proxy, giving us a theoretically-grounded method for analyzing dataset characteristics. We call the method Rissanen Data Analysis (RDA) after the father of MDL, and we showcase its applicability on a wide variety of settings in NLP, ranging from evaluating the utility of generating subquestions before answering a question, to analyzing the value of rationales and explanations, to investigating the importance of different parts of speech, and uncovering dataset gender bias.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/perez21a.html
http://proceedings.mlr.press/v139/perez21a.htmlModelling Behavioural Diversity for Learning in Open-Ended GamesPromoting behavioural diversity is critical for solving games with non-transitive dynamics where strategic cycles exist, and there is no consistent winner (e.g., Rock-Paper-Scissors). Yet, there is a lack of rigorous treatment for defining diversity and constructing diversity-aware learning dynamics. In this work, we offer a geometric interpretation of behavioural diversity in games and introduce a novel diversity metric based on \emph{determinantal point processes} (DPP). By incorporating the diversity metric into best-response dynamics, we develop \emph{diverse fictitious play} and \emph{diverse policy-space response oracle} for solving normal-form games and open-ended games. We prove the uniqueness of the diverse best response and the convergence of our algorithms on two-player games. Importantly, we show that maximising the DPP-based diversity metric guarantees to enlarge the \emph{gamescape} – convex polytopes spanned by agents’ mixtures of strategies. To validate our diversity-aware solvers, we test on tens of games that show strong non-transitivity. Results suggest that our methods achieve at least the same, and in most games, lower exploitability than PSRO solvers by finding effective and diverse strategies.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/perez-nieves21a.html
http://proceedings.mlr.press/v139/perez-nieves21a.htmlPrivacy-Preserving Video Classification with Convolutional Neural NetworksMany video classification applications require access to personal data, thereby posing an invasive security risk to the users’ privacy. We propose a privacy-preserving implementation of single-frame method based video classification with convolutional neural networks that allows a party to infer a label from a video without necessitating the video owner to disclose their video to other entities in an unencrypted manner. Similarly, our approach removes the requirement of the classifier owner from revealing their model parameters to outside entities in plaintext. To this end, we combine existing Secure Multi-Party Computation (MPC) protocols for private image classification with our novel MPC protocols for oblivious single-frame selection and secure label aggregation across frames. The result is an end-to-end privacy-preserving video classification pipeline. We evaluate our proposed solution in an application for private human emotion recognition. Our results across a variety of security settings, spanning honest and dishonest majority configurations of the computing parties, and for both passive and active adversaries, demonstrate that videos can be classified with state-of-the-art accuracy, and without leaking sensitive user information.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/pentyala21a.html
http://proceedings.mlr.press/v139/pentyala21a.htmlHow could Neural Networks understand Programs?Semantic understanding of programs is a fundamental problem for programming language processing (PLP). Recent works that learn representations of code based on pre-training techniques in NLP have pushed the frontiers in this direction. However, the semantics of PL and NL have essential differences. These being ignored, we believe it is difficult to build a model to better understand programs, by either directly applying off-the-shelf NLP pre-training techniques to the source code, or adding features to the model by the heuristic. In fact, the semantics of a program can be rigorously defined by formal semantics in PL theory. For example, the operational semantics, describes the meaning of a valid program as updating the environment (i.e., the memory address-value function) through fundamental operations, such as memory I/O and conditional branching. Inspired by this, we propose a novel program semantics learning paradigm, that the model should learn from information composed of (1) the representations which align well with the fundamental operations in operational semantics, and (2) the information of environment transition, which is indispensable for program understanding. To validate our proposal, we present a hierarchical Transformer-based pre-training model called OSCAR to better facilitate the understanding of programs. OSCAR learns from intermediate representation (IR) and an encoded representation derived from static analysis, which are used for representing the fundamental operations and approximating the environment transitions respectively. OSCAR empirically shows the outstanding capability of program semantics understanding on many practical software engineering tasks. Code and models are released at: \url{https://github.com/pdlan/OSCAR}.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/peng21b.html
http://proceedings.mlr.press/v139/peng21b.htmlHomomorphic Sensing: Sparsity and Noise\emph{Unlabeled sensing} is a recent problem encompassing many data science and engineering applications and typically formulated as solving linear equations whose right-hand side vector has undergone an unknown permutation. It was generalized to the \emph{homomorphic sensing} problem by replacing the unknown permutation with an unknown linear map from a given finite set of linear maps. In this paper we present tighter and simpler conditions for the homomorphic sensing problem to admit a unique solution. We show that this solution is locally stable under noise, while under a sparsity assumption it remains unique under less demanding conditions. Sparsity in the context of unlabeled sensing leads to the problem of \textit{unlabeled compressed sensing}, and a consequence of our general theory is the existence under mild conditions of a unique sparsest solution. On the algorithmic level, we solve unlabeled compressed sensing by an iterative algorithm validated by synthetic data experiments. Finally, under the unifying homomorphic sensing framework we connect unlabeled sensing to other important practical problems.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/peng21a.html
http://proceedings.mlr.press/v139/peng21a.htmlEnsemble Bootstrapping for Q-LearningQ-learning (QL), a common reinforcement learning algorithm, suffers from over-estimation bias due to the maximization term in the optimal Bellman operator. This bias may lead to sub-optimal behavior. Double-Q-learning tackles this issue by utilizing two estimators, yet results in an under-estimation bias. Similar to over-estimation in Q-learning, in certain scenarios, the under-estimation bias may degrade performance. In this work, we introduce a new bias-reduced algorithm called Ensemble Bootstrapped Q-Learning (EBQL), a natural extension of Double-Q-learning to ensembles. We analyze our method both theoretically and empirically. Theoretically, we prove that EBQL-like updates yield lower MSE when estimating the maximal mean of a set of independent random variables. Empirically, we show that there exist domains where both over and under-estimation result in sub-optimal performance. Finally, We demonstrate the superior performance of a deep RL variant of EBQL over other deep QL algorithms for a suite of ATARI games.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/peer21a.html
http://proceedings.mlr.press/v139/peer21a.htmlCombOptNet: Fit the Right NP-Hard Problem by Learning Integer Programming ConstraintsBridging logical and algorithmic reasoning with modern machine learning techniques is a fundamental challenge with potentially transformative impact. On the algorithmic side, many NP-hard problems can be expressed as integer programs, in which the constraints play the role of their ’combinatorial specification’. In this work, we aim to integrate integer programming solvers into neural network architectures as layers capable of learning both the cost terms and the constraints. The resulting end-to-end trainable architectures jointly extract features from raw data and solve a suitable (learned) combinatorial problem with state-of-the-art integer programming solvers. We demonstrate the potential of such layers with an extensive performance analysis on synthetic data and with a demonstration on a competitive computer vision keypoint matching benchmark.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/paulus21a.html
http://proceedings.mlr.press/v139/paulus21a.htmlPHEW : Constructing Sparse Networks that Learn Fast and Generalize Well without Training DataMethods that sparsify a network at initialization are important in practice because they greatly improve the efficiency of both learning and inference. Our work is based on a recently proposed decomposition of the Neural Tangent Kernel (NTK) that has decoupled the dynamics of the training process into a data-dependent component and an architecture-dependent kernel {–} the latter referred to as Path Kernel. That work has shown how to design sparse neural networks for faster convergence, without any training data, using the Synflow-L2 algorithm. We first show that even though Synflow-L2 is optimal in terms of convergence, for a given network density, it results in sub-networks with “bottleneck” (narrow) layers {–} leading to poor performance as compared to other data-agnostic methods that use the same number of parameters. Then we propose a new method to construct sparse networks, without any training data, referred to as Paths with Higher-Edge Weights (PHEW). PHEW is a probabilistic network formation method based on biased random walks that only depends on the initial weights. It has similar path kernel properties as Synflow-L2 but it generates much wider layers, resulting in better generalization and performance. PHEW achieves significant improvements over the data-independent SynFlow and SynFlow-L2 methods at a wide range of network densities.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/patil21a.html
http://proceedings.mlr.press/v139/patil21a.htmlOptimal Counterfactual Explanations in Tree EnsemblesCounterfactual explanations are usually generated through heuristics that are sensitive to the search’s initial conditions. The absence of guarantees of performance and robustness hinders trustworthiness. In this paper, we take a disciplined approach towards counterfactual explanations for tree ensembles. We advocate for a model-based search aiming at "optimal" explanations and propose efficient mixed-integer programming approaches. We show that isolation forests can be modeled within our framework to focus the search on plausible explanations with a low outlier score. We provide comprehensive coverage of additional constraints that model important objectives, heterogeneous data types, structural constraints on the feature space, along with resource and actionability restrictions. Our experimental analyses demonstrate that the proposed search approach requires a computational effort that is orders of magnitude smaller than previous mathematical programming algorithms. It scales up to large data sets and tree ensembles, where it provides, within seconds, systematic explanations grounded on well-defined models solved to optimality.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/parmentier21a.html
http://proceedings.mlr.press/v139/parmentier21a.htmlGenerative Adversarial Networks for Markovian Temporal Dynamics: Stochastic Continuous Data GenerationIn this paper, we present a novel generative adversarial network (GAN) that can describe Markovian temporal dynamics. To generate stochastic sequential data, we introduce a novel stochastic differential equation-based conditional generator and spatial-temporal constrained discriminator networks. To stabilize the learning dynamics of the min-max type of the GAN objective function, we propose well-posed constraint terms for both networks. We also propose a novel conditional Markov Wasserstein distance to induce a pathwise Wasserstein distance. The experimental results demonstrate that our method outperforms state-of-the-art methods using several different types of data.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/park21d.html
http://proceedings.mlr.press/v139/park21d.htmlConditional Distributional Treatment Effect with Kernel Conditional Mean Embeddings and U-Statistic RegressionWe propose to analyse the conditional distributional treatment effect (CoDiTE), which, in contrast to the more common conditional average treatment effect (CATE), is designed to encode a treatment’s distributional aspects beyond the mean. We first introduce a formal definition of the CoDiTE associated with a distance function between probability measures. Then we discuss the CoDiTE associated with the maximum mean discrepancy via kernel conditional mean embeddings, which, coupled with a hypothesis test, tells us whether there is any conditional distributional effect of the treatment. Finally, we investigate what kind of conditional distributional effect the treatment has, both in an exploratory manner via the conditional witness function, and in a quantitative manner via U-statistic regression, generalising the CATE to higher-order moments. Experiments on synthetic, semi-synthetic and real datasets demonstrate the merits of our approach.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/park21c.html
http://proceedings.mlr.press/v139/park21c.htmlUnsupervised Representation Learning via Neural Activation CodingWe present neural activation coding (NAC) as a novel approach for learning deep representations from unlabeled data for downstream applications. We argue that the deep encoder should maximize its nonlinear expressivity on the data for downstream predictors to take full advantage of its representation power. To this end, NAC maximizes the mutual information between activation patterns of the encoder and the data over a noisy communication channel. We show that learning for a noise-robust activation code increases the number of distinct linear regions of ReLU encoders, hence the maximum nonlinear expressivity. More interestingly, NAC learns both continuous and discrete representations of data, which we respectively evaluate on two downstream tasks: (i) linear classification on CIFAR-10 and ImageNet-1K and (ii) nearest neighbor retrieval on CIFAR-10 and FLICKR-25K. Empirical results show that NAC attains better or comparable performance on both tasks over recent baselines including SimCLR and DistillHash. In addition, NAC pretraining provides significant benefits to the training of deep generative models. Our code is available at https://github.com/yookoon/nac.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/park21b.html
http://proceedings.mlr.press/v139/park21b.htmlWasserstein Distributional Normalization For Robust Distributional Certification of Noisy Labeled DataWe propose a novel Wasserstein distributional normalization method that can classify noisy labeled data accurately. Recently, noisy labels have been successfully handled based on small-loss criteria, but have not been clearly understood from the theoretical point of view. In this paper, we address this problem by adopting distributionally robust optimization (DRO). In particular, we present a theoretical investigation of the distributional relationship between uncertain and certain samples based on the small-loss criteria. Our method takes advantage of this relationship to exploit useful information from uncertain samples. To this end, we normalize uncertain samples into the robustly certified region by introducing the non-parametric Ornstein-Ulenbeck type of Wasserstein gradient flows called Wasserstein distributional normalization, which is cheap and fast to implement. We verify that network confidence and distributional certification are fundamentally correlated and show the concentration inequality when the network escapes from over-parameterization. Experimental results demonstrate that our non-parametric classification method outperforms other parametric baselines on the Clothing1M and CIFAR-10/100 datasets when the data have diverse noisy labels.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/park21a.html
http://proceedings.mlr.press/v139/park21a.htmlLeveraging Good Representations in Linear Contextual BanditsThe linear contextual bandit literature is mostly focused on the design of efficient learning algorithms for a given representation. However, a contextual bandit problem may admit multiple linear representations, each one with different characteristics that directly impact the regret of the learning algorithm. In particular, recent works showed that there exist “good” representations for which constant problem-dependent regret can be achieved. In this paper, we first provide a systematic analysis of the different definitions of “good” representations proposed in the literature. We then propose a novel selection algorithm able to adapt to the best representation in a set of $M$ candidates. We show that the regret is indeed never worse than the regret obtained by running \textsc{LinUCB} on best representation (up to a $\ln M$ factor). As a result, our algorithm achieves constant regret if a “good” representation is available in the set. Furthermore, we show the algorithm may still achieve constant regret by implicitly constructing a “good” representation, even when none of the initial representations is “good”. Finally, we validate our theoretical findings in a number of standard contextual bandit problems.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/papini21a.html
http://proceedings.mlr.press/v139/papini21a.htmlLatent Space Energy-Based Model of Symbol-Vector Coupling for Text Generation and ClassificationWe propose a latent space energy-based prior model for text generation and classification. The model stands on a generator network that generates the text sequence based on a continuous latent vector. The energy term of the prior model couples a continuous latent vector and a symbolic one-hot vector, so that discrete category can be inferred from the observed example based on the continuous latent vector. Such a latent space coupling naturally enables incorporation of information bottleneck regularization to encourage the continuous latent vector to extract information from the observed example that is informative of the underlying category. In our learning method, the symbol-vector coupling, the generator network and the inference network are learned jointly. Our model can be learned in an unsupervised setting where no category labels are provided. It can also be learned in semi-supervised setting where category labels are provided for a subset of training examples. Our experiments demonstrate that the proposed model learns well-structured and meaningful latent space, which (1) guides the generator to generate text with high quality, diversity, and interpretability, and (2) effectively classifies text.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/pang21a.html
http://proceedings.mlr.press/v139/pang21a.htmlInference for Network Regression Models with Community StructureNetwork regression models, where the outcome comprises the valued edge in a network and the predictors are actor or dyad-level covariates, are used extensively in the social and biological sciences. Valid inference relies on accurately modeling the residual dependencies among the relations. Frequently homogeneity assumptions are placed on the errors which are commonly incorrect and ignore critical natural clustering of the actors. In this work, we present a novel regression modeling framework that models the errors as resulting from a community-based dependence structure and exploits the subsequent exchangeability properties of the error distribution to obtain parsimonious standard errors for regression parameters.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/pan21a.html
http://proceedings.mlr.press/v139/pan21a.htmlRNN with Particle Flow for Probabilistic Spatio-temporal ForecastingSpatio-temporal forecasting has numerous applications in analyzing wireless, traffic, and financial networks. Many classical statistical models often fall short in handling the complexity and high non-linearity present in time-series data. Recent advances in deep learning allow for better modelling of spatial and temporal dependencies. While most of these models focus on obtaining accurate point forecasts, they do not characterize the prediction uncertainty. In this work, we consider the time-series data as a random realization from a nonlinear state-space model and target Bayesian inference of the hidden states for probabilistic forecasting. We use particle flow as the tool for approximating the posterior distribution of the states, as it is shown to be highly effective in complex, high-dimensional settings. Thorough experimentation on several real world time-series datasets demonstrates that our approach provides better characterization of uncertainty while maintaining comparable accuracy to the state-of-the-art point forecasting methods.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/pal21b.html
http://proceedings.mlr.press/v139/pal21b.htmlOpening the Blackbox: Accelerating Neural Differential Equations by Regularizing Internal Solver HeuristicsDemocratization of machine learning requires architectures that automatically adapt to new problems. Neural Differential Equations (NDEs) have emerged as a popular modeling framework by removing the need for ML practitioners to choose the number of layers in a recurrent model. While we can control the computational cost by choosing the number of layers in standard architectures, in NDEs the number of neural network evaluations for a forward pass can depend on the number of steps of the adaptive ODE solver. But, can we force the NDE to learn the version with the least steps while not increasing the training cost? Current strategies to overcome slow prediction require high order automatic differentiation, leading to significantly higher training time. We describe a novel regularization method that uses the internal cost heuristics of adaptive differential equation solvers combined with discrete adjoint sensitivities to guide the training process towards learning NDEs that are easier to solve. This approach opens up the blackbox numerical analysis behind the differential equation solver’s algorithm and directly uses its local error estimates and stiffness heuristics as cheap and accurate cost estimates. We incorporate our method without any change in the underlying NDE framework and show that our method extends beyond Ordinary Differential Equations to accommodate Neural Stochastic Differential Equations. We demonstrate how our approach can halve the prediction time and, unlike other methods which can increase the training time by an order of magnitude, we demonstrate similar reduction in training times. Together this showcases how the knowledge embedded within state-of-the-art equation solvers can be used to enhance machine learning.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/pal21a.html
http://proceedings.mlr.press/v139/pal21a.htmlTraining Adversarially Robust Sparse Networks via Bayesian Connectivity SamplingDeep neural networks have been shown to be susceptible to adversarial attacks. This lack of adversarial robustness is even more pronounced when models are compressed in order to meet hardware limitations. Hence, if adversarial robustness is an issue, training of sparsely connected networks necessitates considering adversarially robust sparse learning. Motivated by the efficient and stable computational function of the brain in the presence of a highly dynamic synaptic connectivity structure, we propose an intrinsically sparse rewiring approach to train neural networks with state-of-the-art robust learning objectives under high sparsity. Importantly, in contrast to previously proposed pruning techniques, our approach satisfies global connectivity constraints throughout robust optimization, i.e., it does not require dense pre-training followed by pruning. Based on a Bayesian posterior sampling principle, a network rewiring process simultaneously learns the sparse connectivity structure and the robustness-accuracy trade-off based on the adversarial learning objective. Although our networks are sparsely connected throughout the whole training process, our experimental benchmark evaluations show that their performance is superior to recently proposed robustness-aware network pruning methods which start from densely connected networks.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/ozdenizci21a.html
http://proceedings.mlr.press/v139/ozdenizci21a.htmlVector Quantized Models for PlanningRecent developments in the field of model-based RL have proven successful in a range of environments, especially ones where planning is essential. However, such successes have been limited to deterministic fully-observed environments. We present a new approach that handles stochastic and partially-observable environments. Our key insight is to use discrete autoencoders to capture the multiple possible effects of an action in a stochastic environment. We use a stochastic variant of Monte Carlo tree search to plan over both the agent’s actions and the discrete latent variables representing the environment’s response. Our approach significantly outperforms an offline version of MuZero on a stochastic interpretation of chess where the opponent is considered part of the environment. We also show that our approach scales to DeepMind Lab, a first-person 3D environment with large visual observations and partial observability.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/ozair21a.html
http://proceedings.mlr.press/v139/ozair21a.htmlGeneralization Guarantees for Neural Architecture Search with Train-Validation SplitNeural Architecture Search (NAS) is a popular method for automatically designing optimized deep-learning architectures. NAS methods commonly use bilevel optimization where one optimizes the weights over the training data (lower-level problem) and hyperparameters - such as the architecture - over the validation data (upper-level problem). This paper explores the statistical aspects of such problems with train-validation splits. In practice, the lower-level problem is often overparameterized and can easily achieve zero loss. Thus, a-priori, it seems impossible to distinguish the right hyperparameters based on training loss alone which motivates a better understanding of train-validation split. To this aim, we first show that refined properties of the validation loss such as risk and hyper-gradients are indicative of those of the true test loss and help prevent overfitting with a near-minimal validation sample size. Importantly, this is established for continuous search spaces which are relevant for differentiable search schemes. We then establish generalization bounds for NAS problems with an emphasis on an activation search problem and gradient-based methods. Finally, we show rigorous connections between NAS and low-rank matrix learning which leads to algorithmic insights where the solution of the upper problem can be accurately learned via spectral methods to achieve near-minimal risk.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/oymak21a.html
http://proceedings.mlr.press/v139/oymak21a.htmlAutoencoder Image Interpolation by Shaping the Latent SpaceOne of the fascinating properties of deep learning is the ability of the network to reveal the underlying factors characterizing elements in datasets of different types. Autoencoders represent an effective approach for computing these factors. Autoencoders have been studied in the context of enabling interpolation between data points by decoding convex combinations of latent vectors. However, this interpolation often leads to artifacts or produces unrealistic results during reconstruction. We argue that these incongruities are due to the structure of the latent space and to the fact that such naively interpolated latent vectors deviate from the data manifold. In this paper, we propose a regularization technique that shapes the latent representation to follow a manifold that is consistent with the training images and that forces the manifold to be smooth and locally convex. This regularization not only enables faithful interpolation between data points, as we show herein but can also be used as a general regularization technique to avoid overfitting or to produce new samples for data augmentation.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/oring21a.html
http://proceedings.mlr.press/v139/oring21a.htmlSparsity-Agnostic Lasso BanditWe consider a stochastic contextual bandit problem where the dimension $d$ of the feature vectors is potentially large, however, only a sparse subset of features of cardinality $s_0 \ll d$ affect the reward function. Essentially all existing algorithms for sparse bandits require a priori knowledge of the value of the sparsity index $s_0$. This knowledge is almost never available in practice, and misspecification of this parameter can lead to severe deterioration in the performance of existing methods. The main contribution of this paper is to propose an algorithm that does not require prior knowledge of the sparsity index $s_0$ and establish tight regret bounds on its performance under mild conditions. We also comprehensively evaluate our proposed algorithm numerically and show that it consistently outperforms existing methods, even when the correct sparsity index is revealed to them but is kept hidden from our algorithm.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/oh21a.html
http://proceedings.mlr.press/v139/oh21a.htmlRegularizing towards Causal Invariance: Linear Models with ProxiesWe propose a method for learning linear models whose predictive performance is robust to causal interventions on unobserved variables, when noisy proxies of those variables are available. Our approach takes the form of a regularization term that trades off between in-distribution performance and robustness to interventions. Under the assumption of a linear structural causal model, we show that a single proxy can be used to create estimators that are prediction optimal under interventions of bounded strength. This strength depends on the magnitude of the measurement noise in the proxy, which is, in general, not identifiable. In the case of two proxy variables, we propose a modified estimator that is prediction optimal under interventions up to a known strength. We further show how to extend these estimators to scenarios where additional information about the "test time" intervention is available during training. We evaluate our theoretical findings in synthetic experiments and using real data of hourly pollution levels across several cities in China.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/oberst21a.html
http://proceedings.mlr.press/v139/oberst21a.htmlGlobal inducing point variational posteriors for Bayesian neural networks and deep Gaussian processesWe consider the optimal approximate posterior over the top-layer weights in a Bayesian neural network for regression, and show that it exhibits strong dependencies on the lower-layer weights. We adapt this result to develop a correlated approximate posterior over the weights at all layers in a Bayesian neural network. We extend this approach to deep Gaussian processes, unifying inference in the two model classes. Our approximate posterior uses learned "global” inducing points, which are defined only at the input layer and propagated through the network to obtain inducing inputs at subsequent layers. By contrast, standard, "local”, inducing point methods from the deep Gaussian process literature optimise a separate set of inducing inputs at every layer, and thus do not model correlations across layers. Our method gives state-of-the-art performance for a variational Bayesian method, without data augmentation or tempering, on CIFAR-10 of 86.7%, which is comparable to SGMCMC without tempering but with data augmentation (88% in Wenzel et al. 2020).Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/ober21a.html
http://proceedings.mlr.press/v139/ober21a.htmlPosterior Value Functions: Hindsight Baselines for Policy Gradient MethodsHindsight allows reinforcement learning agents to leverage new observations to make inferences about earlier states and transitions. In this paper, we exploit the idea of hindsight and introduce posterior value functions. Posterior value functions are computed by inferring the posterior distribution over hidden components of the state in previous timesteps and can be used to construct novel unbiased baselines for policy gradient methods. Importantly, we prove that these baselines reduce (and never increase) the variance of policy gradient estimators compared to traditional state value functions. While the posterior value function is motivated by partial observability, we extend these results to arbitrary stochastic MDPs by showing that hindsight-capable agents can model stochasticity in the environment as a special case of partial observability. Finally, we introduce a pair of methods for learning posterior value functions and prove their convergence.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/nota21a.html
http://proceedings.mlr.press/v139/nota21a.htmlAccuracy, Interpretability, and Differential Privacy via Explainable BoostingWe show that adding differential privacy to Explainable Boosting Machines (EBMs), a recent method for training interpretable ML models, yields state-of-the-art accuracy while protecting privacy. Our experiments on multiple classification and regression datasets show that DP-EBM models suffer surprisingly little accuracy loss even with strong differential privacy guarantees. In addition to high accuracy, two other benefits of applying DP to EBMs are: a) trained models provide exact global and local interpretability, which is often important in settings where differential privacy is needed; and b) the models can be edited after training without loss of privacy to correct errors which DP noise may have introduced.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/nori21a.html
http://proceedings.mlr.press/v139/nori21a.htmlThe Impact of Record Linkage on Learning from Feature Partitioned DataThere has been recently a significant boost to machine learning with distributed data, in particular with the success of federated learning. A common and very challenging setting is that of vertical or feature partitioned data, when multiple data providers hold different features about common entities. In general, training needs to be preceded by record linkage (RL), a step that finds the correspondence between the observations of the datasets. RL is prone to mistakes in the real world. Despite the importance of the problem, there has been so far no formal assessment of the way in which RL errors impact learning models. Work in the area either use heuristics or assume that the optimal RL is known in advance. In this paper, we provide the first assessment of the problem for supervised learning. For wide sets of losses, we provide technical conditions under which the classifier learned after noisy RL converges (with the data size) to the best classifier that would be learned from mistake-free RL. This yields new insights on the way the pipeline RL + ML operates, from the role of large margin classification on dampening the impact of RL mistakes to clues on how to further optimize RL as a preprocessing step to ML. Experiments on a large UCI benchmark validate those formal observations.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/nock21a.html
http://proceedings.mlr.press/v139/nock21a.htmlWGAN with an Infinitely Wide Generator Has No Spurious Stationary PointsGenerative adversarial networks (GAN) are a widely used class of deep generative models, but their minimax training dynamics are not understood very well. In this work, we show that GANs with a 2-layer infinite-width generator and a 2-layer finite-width discriminator trained with stochastic gradient ascent-descent have no spurious stationary points. We then show that when the width of the generator is finite but wide, there are no spurious stationary points within a ball whose radius becomes arbitrarily large (to cover the entire parameter space) as the width goes to infinity.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/no21a.html
http://proceedings.mlr.press/v139/no21a.htmlAsynchronous Decentralized Optimization With Implicit Stochastic Variance ReductionA novel asynchronous decentralized optimization method that follows Stochastic Variance Reduction (SVR) is proposed. Average consensus algorithms, such as Decentralized Stochastic Gradient Descent (DSGD), facilitate distributed training of machine learning models. However, the gradient will drift within the local nodes due to statistical heterogeneity of the subsets of data residing on the nodes and long communication intervals. To overcome the drift problem, (i) Gradient Tracking-SVR (GT-SVR) integrates SVR into DSGD and (ii) Edge-Consensus Learning (ECL) solves a model constrained minimization problem using a primal-dual formalism. In this paper, we reformulate the update procedure of ECL such that it implicitly includes the gradient modification of SVR by optimally selecting a constraint-strength control parameter. Through convergence analysis and experiments, we confirmed that the proposed ECL with Implicit SVR (ECL-ISVR) is stable and approximately reaches the reference performance obtained with computation on a single-node using full data set.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/niwa21a.html
http://proceedings.mlr.press/v139/niwa21a.htmlAdaXpert: Adapting Neural Architecture for Growing DataIn real-world applications, data often come in a growing manner, where the data volume and the number of classes may increase dynamically. This will bring a critical challenge for learning: given the increasing data volume or the number of classes, one has to instantaneously adjust the neural model capacity to obtain promising performance. Existing methods either ignore the growing nature of data or seek to independently search an optimal architecture for a given dataset, and thus are incapable of promptly adjusting the architectures for the changed data. To address this, we present a neural architecture adaptation method, namely Adaptation eXpert (AdaXpert), to efficiently adjust previous architectures on the growing data. Specifically, we introduce an architecture adjuster to generate a suitable architecture for each data snapshot, based on the previous architecture and the different extent between current and previous data distributions. Furthermore, we propose an adaptation condition to determine the necessity of adjustment, thereby avoiding unnecessary and time-consuming adjustments. Extensive experiments on two growth scenarios (increasing data volume and number of classes) demonstrate the effectiveness of the proposed method.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/niu21a.html
http://proceedings.mlr.press/v139/niu21a.htmlSmooth $p$-Wasserstein Distance: Structure, Empirical Approximation, and Statistical ApplicationsDiscrepancy measures between probability distributions, often termed statistical distances, are ubiquitous in probability theory, statistics and machine learning. To combat the curse of dimensionality when estimating these distances from data, recent work has proposed smoothing out local irregularities in the measured distributions via convolution with a Gaussian kernel. Motivated by the scalability of this framework to high dimensions, we investigate the structural and statistical behavior of the Gaussian-smoothed $p$-Wasserstein distance $\mathsf{W}_p^{(\sigma)}$, for arbitrary $p\geq 1$. After establishing basic metric and topological properties of $\mathsf{W}_p^{(\sigma)}$, we explore the asymptotic statistical properties of $\mathsf{W}_p^{(\sigma)}(\hat{\mu}_n,\mu)$, where $\hat{\mu}_n$ is the empirical distribution of $n$ independent observations from $\mu$. We prove that $\mathsf{W}_p^{(\sigma)}$ enjoys a parametric empirical convergence rate of $n^{-1/2}$, which contrasts the $n^{-1/d}$ rate for unsmoothed $\Wp$ when $d \geq 3$. Our proof relies on controlling $\mathsf{W}_p^{(\sigma)}$ by a $p$th-order smooth Sobolev distance $\mathsf{d}_p^{(\sigma)}$ and deriving the limit distribution of $\sqrt{n}\,\mathsf{d}_p^{(\sigma)}(\hat{\mu}_n,\mu)$ for all dimensions $d$. As applications, we provide asymptotic guarantees for two-sample testing and minimum distance estimation using $\mathsf{W}_p^{(\sigma)}$, with experiments for $p=2$ using a maximum mean discrepancy formulation of $\mathsf{d}_2^{(\sigma)}$.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/nietert21a.html
http://proceedings.mlr.press/v139/nietert21a.htmlImproved Denoising Diffusion Probabilistic ModelsDenoising diffusion probabilistic models (DDPM) are a class of generative models which have recently been shown to produce excellent samples. We show that with a few simple modifications, DDPMs can also achieve competitive log-likelihoods while maintaining high sample quality. Additionally, we find that learning variances of the reverse diffusion process allows sampling with an order of magnitude fewer forward passes with a negligible difference in sample quality, which is important for the practical deployment of these models. We additionally use precision and recall to compare how well DDPMs and GANs cover the target distribution. Finally, we show that the sample quality and likelihood of these models scale smoothly with model capacity and training compute, making them easily scalable. We release our code and pre-trained models at https://github.com/openai/improved-diffusion.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/nichol21a.html
http://proceedings.mlr.press/v139/nichol21a.htmlData Augmentation for Meta-LearningConventional image classifiers are trained by randomly sampling mini-batches of images. To achieve state-of-the-art performance, practitioners use sophisticated data augmentation schemes to expand the amount of training data available for sampling. In contrast, meta-learning algorithms sample support data, query data, and tasks on each training step. In this complex sampling scenario, data augmentation can be used not only to expand the number of images available per class, but also to generate entirely new classes/tasks. We systematically dissect the meta-learning pipeline and investigate the distinct ways in which data augmentation can be integrated at both the image and class levels. Our proposed meta-specific data augmentation significantly improves the performance of meta-learners on few-shot classification benchmarks.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/ni21a.html
http://proceedings.mlr.press/v139/ni21a.htmlDifferentially Private Densest Subgraph DetectionDensest subgraph detection is a fundamental graph mining problem, with a large number of applications. There has been a lot of work on efficient algorithms for finding the densest subgraph in massive networks. However, in many domains, the network is private, and returning a densest subgraph can reveal information about the network. Differential privacy is a powerful framework to handle such settings. We study the densest subgraph problem in the edge privacy model, in which the edges of the graph are private. We present the first sequential and parallel differentially private algorithms for this problem. We show that our algorithms have an additive approximation guarantee. We evaluate our algorithms on a large number of real-world networks, and observe a good privacy-accuracy tradeoff when the network has high density.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/nguyen21i.html
http://proceedings.mlr.press/v139/nguyen21i.htmlTemporal Predictive Coding For Model-Based Planning In Latent SpaceHigh-dimensional observations are a major challenge in the application of model-based reinforcement learning (MBRL) to real-world environments. To handle high-dimensional sensory inputs, existing approaches use representation learning to map high-dimensional observations into a lower-dimensional latent space that is more amenable to dynamics estimation and planning. In this work, we present an information-theoretic approach that employs temporal predictive coding to encode elements in the environment that can be predicted across time. Since this approach focuses on encoding temporally-predictable information, we implicitly prioritize the encoding of task-relevant components over nuisance information within the environment that are provably task-irrelevant. By learning this representation in conjunction with a recurrent state space model, we can then perform planning in latent space. We evaluate our model on a challenging modification of standard DMControl tasks where the background is replaced with natural videos that contain complex but irrelevant information to the planning task. Our experiments show that our model is superior to existing methods in the challenging complex-background setting while remaining competitive with current state-of-the-art models in the standard setting.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/nguyen21h.html
http://proceedings.mlr.press/v139/nguyen21h.htmlTight Bounds on the Smallest Eigenvalue of the Neural Tangent Kernel for Deep ReLU NetworksA recent line of work has analyzed the theoretical properties of deep neural networks via the Neural Tangent Kernel (NTK). In particular, the smallest eigenvalue of the NTK has been related to the memorization capacity, the global convergence of gradient descent algorithms and the generalization of deep nets. However, existing results either provide bounds in the two-layer setting or assume that the spectrum of the NTK matrices is bounded away from 0 for multi-layer networks. In this paper, we provide tight bounds on the smallest eigenvalue of NTK matrices for deep ReLU nets, both in the limiting case of infinite widths and for finite widths. In the finite-width setting, the network architectures we consider are fairly general: we require the existence of a wide layer with roughly order of $N$ neurons, $N$ being the number of data samples; and the scaling of the remaining layer widths is arbitrary (up to logarithmic factors). To obtain our results, we analyze various quantities of independent interest: we give lower bounds on the smallest singular value of hidden feature matrices, and upper bounds on the Lipschitz constant of input-output feature maps.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/nguyen21g.html
http://proceedings.mlr.press/v139/nguyen21g.htmlNonmyopic Multifidelity Acitve SearchActive search is a learning paradigm where we seek to identify as many members of a rare, valuable class as possible given a labeling budget. Previous work on active search has assumed access to a faithful (and expensive) oracle reporting experimental results. However, some settings offer access to cheaper surrogates such as computational simulation that may aid in the search. We propose a model of multifidelity active search, as well as a novel, computationally efficient policy for this setting that is motivated by state-of-the-art classical policies. Our policy is nonmyopic and budget aware, allowing for a dynamic tradeoff between exploration and exploitation. We evaluate the performance of our solution on real-world datasets and demonstrate significantly better performance than natural benchmarks.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/nguyen21f.html
http://proceedings.mlr.press/v139/nguyen21f.htmlInteractive Learning from Activity DescriptionWe present a novel interactive learning protocol that enables training request-fulfilling agents by verbally describing their activities. Unlike imitation learning (IL), our protocol allows the teaching agent to provide feedback in a language that is most appropriate for them. Compared with reward in reinforcement learning (RL), the description feedback is richer and allows for improved sample complexity. We develop a probabilistic framework and an algorithm that practically implements our protocol. Empirical results in two challenging request-fulfilling problems demonstrate the strengths of our approach: compared with RL baselines, it is more sample-efficient; compared with IL baselines, it achieves competitive success rates without requiring the teaching agent to be able to demonstrate the desired behavior using the learning agent’s actions. Apart from empirical evaluation, we also provide theoretical guarantees for our algorithm under certain assumptions about the teacher and the environment.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/nguyen21e.html
http://proceedings.mlr.press/v139/nguyen21e.htmlOptimal Transport Kernels for Sequential and Parallel Neural Architecture SearchNeural architecture search (NAS) automates the design of deep neural networks. One of the main challenges in searching complex and non-continuous architectures is to compare the similarity of networks that the conventional Euclidean metric may fail to capture. Optimal transport (OT) is resilient to such complex structure by considering the minimal cost for transporting a network into another. However, the OT is generally not negative definite which may limit its ability to build the positive-definite kernels required in many kernel-dependent frameworks. Building upon tree-Wasserstein (TW), which is a negative definite variant of OT, we develop a novel discrepancy for neural architectures, and demonstrate it within a Gaussian process surrogate model for the sequential NAS settings. Furthermore, we derive a novel parallel NAS, using quality k-determinantal point process on the GP posterior, to select diverse and high-performing architectures from a discrete set of candidates. Empirically, we demonstrate that our TW-based approaches outperform other baselines in both sequential and parallel NAS.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/nguyen21d.html
http://proceedings.mlr.press/v139/nguyen21d.htmlCross-model Back-translated Distillation for Unsupervised Machine TranslationRecent unsupervised machine translation (UMT) systems usually employ three main principles: initialization, language modeling and iterative back-translation, though they may apply them differently. Crucially, iterative back-translation and denoising auto-encoding for language modeling provide data diversity to train the UMT systems. However, the gains from these diversification processes has seemed to plateau. We introduce a novel component to the standard UMT framework called Cross-model Back-translated Distillation (CBD), that is aimed to induce another level of data diversification that existing principles lack. CBD is applicable to all previous UMT approaches. In our experiments, CBD achieves the state of the art in the WMT’14 English-French, WMT’16 English-German and English-Romanian bilingual unsupervised translation tasks, with 38.2, 30.1, and 36.3 BLEU respectively. It also yields 1.5–3.3 BLEU improvements in IWSLT English-French and English-German tasks. Through extensive experimental analyses, we show that CBD is effective because it embraces data diversity while other similar variants do not.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/nguyen21c.html
http://proceedings.mlr.press/v139/nguyen21c.htmlValue-at-Risk Optimization with Gaussian ProcessesValue-at-risk (VaR) is an established measure to assess risks in critical real-world applications with random environmental factors. This paper presents a novel VaR upper confidence bound (V-UCB) algorithm for maximizing the VaR of a black-box objective function with the first no-regret guarantee. To realize this, we first derive a confidence bound of VaR and then prove the existence of values of the environmental random variable (to be selected to achieve no regret) such that the confidence bound of VaR lies within that of the objective function evaluated at such values. Our V-UCB algorithm empirically demonstrates state-of-the-art performance in optimizing synthetic benchmark functions, a portfolio optimization problem, and a simulated robot task.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/nguyen21b.html
http://proceedings.mlr.press/v139/nguyen21b.htmlOn the Proof of Global Convergence of Gradient Descent for Deep ReLU Networks with Linear WidthsWe give a simple proof for the global convergence of gradient descent in training deep ReLU networks with the standard square loss, and show some of its improvements over the state-of-the-art. In particular, while prior works require all the hidden layers to be wide with width at least $\Omega(N^8)$ ($N$ being the number of training samples), we require a single wide layer of linear, quadratic or cubic width depending on the type of initialization. Unlike many recent proofs based on the Neural Tangent Kernel (NTK), our proof need not track the evolution of the entire NTK matrix, or more generally, any quantities related to the changes of activation patterns during training. Instead, we only need to track the evolution of the output at the last hidden layer, which can be done much more easily thanks to the Lipschitz property of ReLU. Some highlights of our setting: (i) all the layers are trained with standard gradient descent, (ii) the network has standard parameterization as opposed to the NTK one, and (iii) the network has a single wide layer as opposed to having all wide hidden layers as in most of NTK-related results.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/nguyen21a.html
http://proceedings.mlr.press/v139/nguyen21a.htmlIncentivizing Compliance with Algorithmic InstrumentsRandomized experiments can be susceptible to selection bias due to potential non-compliance by the participants. While much of the existing work has studied compliance as a static behavior, we propose a game-theoretic model to study compliance as dynamic behavior that may change over time. In rounds, a social planner interacts with a sequence of heterogeneous agents who arrive with their unobserved private type that determines both their prior preferences across the actions (e.g., control and treatment) and their baseline rewards without taking any treatment. The planner provides each agent with a randomized recommendation that may alter their beliefs and their action selection. We develop a novel recommendation mechanism that views the planner’s recommendation as a form of instrumental variable (IV) that only affects an agents’ action selection, but not the observed rewards. We construct such IVs by carefully mapping the history –the interactions between the planner and the previous agents– to a random recommendation. Even though the initial agents may be completely non-compliant, our mechanism can incentivize compliance over time, thereby enabling the estimation of the treatment effect of each treatment, and minimizing the cumulative regret of the planner whose goal is to identify the optimal treatment.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/ngo21a.html
http://proceedings.mlr.press/v139/ngo21a.htmlCausality-aware counterfactual confounding adjustment as an alternative to linear residualization in anticausal prediction tasks based on linear learnersLinear residualization is a common practice for confounding adjustment in machine learning applications. Recently, causality-aware predictive modeling has been proposed as an alternative causality-inspired approach for adjusting for confounders. In this paper, we compare the linear residualization approach against the causality-aware confounding adjustment in anticausal prediction tasks. Our comparisons include both the settings where the training and test sets come from the same distributions, as well as, when the training and test sets are shifted due to selection biases. In the absence of dataset shifts, we show that the causality-aware approach tends to (asymptotically) outperform the residualization adjustment in terms of predictive performance in linear learners. Importantly, our results still holds even when the true model generating the data is not linear. We illustrate our results in both regression and classification tasks. Furthermore, in the presence of dataset shifts in the joint distribution of the confounders and outcome variables, we show that the causality-aware approach is more stable than linear residualization.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/neto21a.html
http://proceedings.mlr.press/v139/neto21a.htmlPolicy Caches with Successor FeaturesTransfer in reinforcement learning is based on the idea that it is possible to use what is learned in one task to improve the learning process in another task. For transfer between tasks which share transition dynamics but differ in reward function, successor features have been shown to be a useful representation which allows for efficient computation of action-value functions for previously-learned policies in new tasks. These functions induce policies in the new tasks, so an agent may not need to learn a new policy for each new task it encounters, especially if it is allowed some amount of suboptimality in those tasks. We present new bounds for the performance of optimal policies in a new task, as well as an approach to use these bounds to decide, when presented with a new task, whether to use cached policies or learn a new policy.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/nemecek21a.html
http://proceedings.mlr.press/v139/nemecek21a.htmlContinuous Coordination As a Realistic Scenario for Lifelong LearningCurrent deep reinforcement learning (RL) algorithms are still highly task-specific and lack the ability to generalize to new environments. Lifelong learning (LLL), however, aims at solving multiple tasks sequentially by efficiently transferring and using knowledge between tasks. Despite a surge of interest in lifelong RL in recent years, the lack of a realistic testbed makes robust evaluation of LLL algorithms difficult. Multi-agent RL (MARL), on the other hand, can be seen as a natural scenario for lifelong RL due to its inherent non-stationarity, since the agents’ policies change over time. In this work, we introduce a multi-agent lifelong learning testbed that supports both zero-shot and few-shot settings. Our setup is based on Hanabi {—} a partially-observable, fully cooperative multi-agent game that has been shown to be challenging for zero-shot coordination. Its large strategy space makes it a desirable environment for lifelong RL tasks. We evaluate several recent MARL methods, and benchmark state-of-the-art LLL algorithms in limited memory and computation regimes to shed light on their strengths and weaknesses. This continual learning paradigm also provides us with a pragmatic way of going beyond centralized training which is the most commonly used training protocol in MARL. We empirically show that the agents trained in our setup are able to coordinate well with unseen agents, without any additional assumptions made by previous works. The code and all pre-trained models are available at https://github.com/chandar-lab/Lifelong-Hanabi.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/nekoei21a.html
http://proceedings.mlr.press/v139/nekoei21a.htmlBayesian Algorithm Execution: Estimating Computable Properties of Black-box Functions Using Mutual InformationIn many real world problems, we want to infer some property of an expensive black-box function f, given a budget of T function evaluations. One example is budget constrained global optimization of f, for which Bayesian optimization is a popular method. Other properties of interest include local optima, level sets, integrals, or graph-structured information induced by f. Often, we can find an algorithm A to compute the desired property, but it may require far more than T queries to execute. Given such an A, and a prior distribution over f, we refer to the problem of inferring the output of A using T evaluations as Bayesian Algorithm Execution (BAX). To tackle this problem, we present a procedure, InfoBAX, that sequentially chooses queries that maximize mutual information with respect to the algorithm’s output. Applying this to Dijkstra’s algorithm, for instance, we infer shortest paths in synthetic and real-world graphs with black-box edge costs. Using evolution strategies, we yield variants of Bayesian optimization that target local, rather than global, optima. On these problems, InfoBAX uses up to 500 times fewer queries to f than required by the original algorithm. Our method is closely connected to other Bayesian optimal experimental design procedures such as entropy search methods and optimal sensor placement using Gaussian processes.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/neiswanger21a.html
http://proceedings.mlr.press/v139/neiswanger21a.htmlEmergent Social Learning via Multi-agent Reinforcement LearningSocial learning is a key component of human and animal intelligence. By taking cues from the behavior of experts in their environment, social learners can acquire sophisticated behavior and rapidly adapt to new circumstances. This paper investigates whether independent reinforcement learning (RL) agents in a multi-agent environment can learn to use social learning to improve their performance. We find that in most circumstances, vanilla model-free RL agents do not use social learning. We analyze the reasons for this deficiency, and show that by imposing constraints on the training environment and introducing a model-based auxiliary loss we are able to obtain generalized social learning policies which enable agents to: i) discover complex skills that are not learned from single-agent training, and ii) adapt online to novel environments by taking cues from experts present in the new environment. In contrast, agents trained with model-free RL or imitation learning generalize poorly and do not succeed in the transfer tasks. By mixing multi-agent and solo training, we can obtain agents that use social learning to gain skills that they can deploy when alone, even out-performing agents trained alone from the start.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/ndousse21a.html
http://proceedings.mlr.press/v139/ndousse21a.htmlHardCoRe-NAS: Hard Constrained diffeRentiable Neural Architecture SearchRealistic use of neural networks often requires adhering to multiple constraints on latency, energy and memory among others. A popular approach to find fitting networks is through constrained Neural Architecture Search (NAS), however, previous methods enforce the constraint only softly. Therefore, the resulting networks do not exactly adhere to the resource constraint and their accuracy is harmed. In this work we resolve this by introducing Hard Constrained diffeRentiable NAS (HardCoRe-NAS), that is based on an accurate formulation of the expected resource requirement and a scalable search method that satisfies the hard constraint throughout the search. Our experiments show that HardCoRe-NAS generates state-of-the-art architectures, surpassing other NAS methods, while strictly satisfying the hard resource constraints without any tuning required.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/nayman21a.html
http://proceedings.mlr.press/v139/nayman21a.htmlGeometric convergence of elliptical slice samplingFor Bayesian learning, given likelihood function and Gaussian prior, the elliptical slice sampler, introduced by Murray, Adams and MacKay 2010, provides a tool for the construction of a Markov chain for approximate sampling of the underlying posterior distribution. Besides of its wide applicability and simplicity its main feature is that no tuning is necessary. Under weak regularity assumptions on the posterior density we show that the corresponding Markov chain is geometrically ergodic and therefore yield qualitative convergence guarantees. We illustrate our result for Gaussian posteriors as they appear in Gaussian process regression in a fully Gaussian scenario, which for example is exhibited in Gaussian process regression, as well as in a setting of a multi-modal distribution. Remarkably, our numerical experiments indicate a dimension-independent performance of elliptical slice sampling even in situations where our ergodicity result does not apply.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/natarovskii21a.html
http://proceedings.mlr.press/v139/natarovskii21a.htmlGenerating images with sparse representationsThe high dimensionality of images presents architecture and sampling-efficiency challenges for likelihood-based generative models. Previous approaches such as VQ-VAE use deep autoencoders to obtain compact representations, which are more practical as inputs for likelihood-based models. We present an alternative approach, inspired by common image compression methods like JPEG, and convert images to quantized discrete cosine transform (DCT) blocks, which are represented sparsely as a sequence of DCT channel, spatial location, and DCT coefficient triples. We propose a Transformer-based autoregressive architecture, which is trained to sequentially predict the conditional distribution of the next element in such sequences, and which scales effectively to high resolution images. On a range of image datasets, we demonstrate that our approach can generate high quality, diverse images, with sample metric scores competitive with state of the art methods. We additionally show that simple modifications to our method yield effective image colorization and super-resolution models.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/nash21a.html
http://proceedings.mlr.press/v139/nash21a.htmlRandomized Dimensionality Reduction for Facility Location and Single-Linkage ClusteringRandom dimensionality reduction is a versatile tool for speeding up algorithms for high-dimensional problems. We study its application to two clustering problems: the facility location problem, and the single-linkage hierarchical clustering problem, which is equivalent to computing the minimum spanning tree. We show that if we project the input pointset $X$ onto a random $d = O(d_X)$-dimensional subspace (where $d_X$ is the doubling dimension of $X$), then the optimum facility location cost in the projected space approximates the original cost up to a constant factor. We show an analogous statement for minimum spanning tree, but with the dimension $d$ having an extra $\log \log n$ term and the approximation factor being arbitrarily close to $1$. Furthermore, we extend these results to approximating {\em solutions} instead of just their {\em costs}. Lastly, we provide experimental results to validate the quality of solutions and the speedup due to the dimensionality reduction. Unlike several previous papers studying this approach in the context of $k$-means and $k$-medians, our dimension bound does not depend on the number of clusters but only on the intrinsic dimensionality of $X$.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/narayanan21b.html
http://proceedings.mlr.press/v139/narayanan21b.htmlMemory-Efficient Pipeline-Parallel DNN TrainingMany state-of-the-art ML results have been obtained by scaling up the number of parameters in existing models. However, parameters and activations for such large models often do not fit in the memory of a single accelerator device; this means that it is necessary to distribute training of large models over multiple accelerators. In this work, we propose PipeDream-2BW, a system that supports memory-efficient pipeline parallelism. PipeDream-2BW uses a novel pipelining and weight gradient coalescing strategy, combined with the double buffering of weights, to ensure high throughput, low memory footprint, and weight update semantics similar to data parallelism. In addition, PipeDream-2BW automatically partitions the model over the available hardware resources, while respecting hardware constraints such as memory capacities of accelerators and interconnect topologies. PipeDream-2BW can accelerate the training of large GPT and BERT language models by up to 20x with similar final model accuracy.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/narayanan21a.html
http://proceedings.mlr.press/v139/narayanan21a.htmlGMAC: A Distributional Perspective on Actor-Critic FrameworkIn this paper, we devise a distributional framework on actor-critic as a solution to distributional instability, action type restriction, and conflation between samples and statistics. We propose a new method that minimizes the Cram{é}r distance with the multi-step Bellman target distribution generated from a novel Sample-Replacement algorithm denoted SR(\lambda), which learns the correct value distribution under multiple Bellman operations. Parameterizing a value distribution with Gaussian Mixture Model further improves the efficiency and the performance of the method, which we name GMAC. We empirically show that GMAC captures the correct representation of value distributions and improves the performance of a conventional actor-critic method with low computational cost, in both discrete and continuous action spaces using Arcade Learning Environment (ALE) and PyBullet environment.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/nam21a.html
http://proceedings.mlr.press/v139/nam21a.htmlQuantitative Understanding of VAE as a Non-linearly Scaled Isometric EmbeddingVariational autoencoder (VAE) estimates the posterior parameters (mean and variance) of latent variables corresponding to each input data. While it is used for many tasks, the transparency of the model is still an underlying issue. This paper provides a quantitative understanding of VAE property through the differential geometric and information-theoretic interpretations of VAE. According to the Rate-distortion theory, the optimal transform coding is achieved by using an orthonormal transform with PCA basis where the transform space is isometric to the input. Considering the analogy of transform coding to VAE, we clarify theoretically and experimentally that VAE can be mapped to an implicit isometric embedding with a scale factor derived from the posterior parameter. As a result, we can estimate the data probabilities in the input space from the prior, loss metrics, and corresponding posterior parameters, and further, the quantitative importance of each latent variable can be evaluated like the eigenvalue of PCA.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/nakagawa21a.html
http://proceedings.mlr.press/v139/nakagawa21a.htmlOnline Limited Memory Neural-Linear Bandits with Likelihood MatchingWe study neural-linear bandits for solving problems where {\em both} exploration and representation learning play an important role. Neural-linear bandits harnesses the representation power of Deep Neural Networks (DNNs) and combines it with efficient exploration mechanisms by leveraging uncertainty estimation of the model, designed for linear contextual bandits on top of the last hidden layer. In order to mitigate the problem of representation change during the process, new uncertainty estimations are computed using stored data from an unlimited buffer. Nevertheless, when the amount of stored data is limited, a phenomenon called catastrophic forgetting emerges. To alleviate this, we propose a likelihood matching algorithm that is resilient to catastrophic forgetting and is completely online. We applied our algorithm, Limited Memory Neural-Linear with Likelihood Matching (NeuralLinear-LiM2) on a variety of datasets and observed that our algorithm achieves comparable performance to the unlimited memory approach while exhibits resilience to catastrophic forgetting.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/nabati21a.html
http://proceedings.mlr.press/v139/nabati21a.htmlNo-regret Algorithms for Capturing Events in Poisson Point ProcessesInhomogeneous Poisson point processes are widely used models of event occurrences. We address \emph{adaptive sensing of Poisson Point processes}, namely, maximizing the number of captured events subject to sensing costs. We encode prior assumptions on the rate function by modeling it as a member of a known \emph{reproducing kernel Hilbert space} (RKHS). By partitioning the domain into separate small regions, and using heteroscedastic linear regression, we propose a tractable estimator of Poisson process rates for two feedback models: \emph{count-record}, where exact locations of events are observed, and \emph{histogram} feedback, where only counts of events are observed. We derive provably accurate anytime confidence estimates for our estimators for sequentially acquired Poisson count data. Using these, we formulate algorithms based on optimism that provably incur sublinear count-regret. We demonstrate the practicality of the method on problems from crime modeling, revenue maximization as well as environmental monitoring.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/mutny21a.html
http://proceedings.mlr.press/v139/mutny21a.htmlImplicit-PDF: Non-Parametric Representation of Probability Distributions on the Rotation ManifoldIn the deep learning era, the vast majority of methods to predict pose from a single image are trained to classify or regress to a single given ground truth pose per image. Such methods have two main shortcomings, i) they cannot represent uncertainty about the predictions, and ii) they cannot handle symmetric objects, where multiple (potentially infinite) poses may be correct. Only recently these shortcomings have been addressed, but current approaches as limited in that they cannot express the full rich space of distributions on the rotation manifold. To this end, we introduce a method to estimate arbitrary, non-parametric distributions on SO(3). Our key idea is to represent the distributions implicitly, with a neural network that estimates the probability density, given the input image and a candidate pose. At inference time, grid sampling or gradient ascent can be used to find the most likely pose, but it is also possible to evaluate the density at any pose, enabling reasoning about symmetries and uncertainty. This is the most general way of representing distributions on manifolds, and to demonstrate its expressive power we introduce a new dataset containing symmetric and nearly-symmetric objects. Our method also shows advantages on the popular object pose estimation benchmarks ModelNet10-SO(3) and T-LESS. Code, data, and visualizations may be found at implicit-pdf.github.io.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/murphy21a.html
http://proceedings.mlr.press/v139/murphy21a.htmlBias-Variance Reduced Local SGD for Less Heterogeneous Federated LearningRecently, local SGD has got much attention and been extensively studied in the distributed learning community to overcome the communication bottleneck problem. However, the superiority of local SGD to minibatch SGD only holds in quite limited situations. In this paper, we study a new local algorithm called Bias-Variance Reduced Local SGD (BVR-L-SGD) for nonconvex distributed optimization. Algorithmically, our proposed bias and variance reduced local gradient estimator fully utilizes small second-order heterogeneity of local objectives and suggests randomly picking up one of the local models instead of taking the average of them when workers are synchronized. Theoretically, under small heterogeneity of local objectives, we show that BVR-L-SGD achieves better communication complexity than both the previous non-local and local methods under mild conditions, and particularly BVR-L-SGD is the first method that breaks the barrier of communication complexity $\Theta(1/\varepsilon)$ for general nonconvex smooth objectives when the heterogeneity is small and the local computation budget is large. Numerical results are given to verify the theoretical findings and give empirical evidence of the superiority of our method.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/murata21a.html
http://proceedings.mlr.press/v139/murata21a.htmlOblivious Sketching for Logistic RegressionWhat guarantees are possible for solving logistic regression in one pass over a data stream? To answer this question, we present the first data oblivious sketch for logistic regression. Our sketch can be computed in input sparsity time over a turnstile data stream and reduces the size of a $d$-dimensional data set from $n$ to only $\operatorname{poly}(\mu d\log n)$ weighted points, where $\mu$ is a useful parameter which captures the complexity of compressing the data. Solving (weighted) logistic regression on the sketch gives an $O(\log n)$-approximation to the original problem on the full data set. We also show how to obtain an $O(1)$-approximation with slight modifications. Our sketches are fast, simple, easy to implement, and our experiments demonstrate their practicality.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/munteanu21a.html
http://proceedings.mlr.press/v139/munteanu21a.htmlOutlier-Robust Optimal TransportOptimal transport (OT) measures distances between distributions in a way that depends on the geometry of the sample space. In light of recent advances in computational OT, OT distances are widely used as loss functions in machine learning. Despite their prevalence and advantages, OT loss functions can be extremely sensitive to outliers. In fact, a single adversarially-picked outlier can increase the standard $W_2$-distance arbitrarily. To address this issue, we propose an outlier-robust formulation of OT. Our formulation is convex but challenging to scale at a first glance. Our main contribution is deriving an \emph{equivalent} formulation based on cost truncation that is easy to incorporate into modern algorithms for computational OT. We demonstrate the benefits of our formulation in mean estimation problems under the Huber contamination model in simulations and outlier detection tasks on real data.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/mukherjee21a.html
http://proceedings.mlr.press/v139/mukherjee21a.htmlConnecting Interpretability and Robustness in Decision Trees through SeparationRecent research has recognized interpretability and robustness as essential properties of trustworthy classification. Curiously, a connection between robustness and interpretability was empirically observed, but the theoretical reasoning behind it remained elusive. In this paper, we rigorously investigate this connection. Specifically, we focus on interpretation using decision trees and robustness to l_{\infty}-perturbation. Previous works defined the notion of r-separation as a sufficient condition for robustness. We prove upper and lower bounds on the tree size in case the data is r-separated. We then show that a tighter bound on the size is possible when the data is linearly separated. We provide the first algorithm with provable guarantees both on robustness, interpretability, and accuracy in the context of decision trees. Experiments confirm that our algorithm yields classifiers that are both interpretable and robust and have high accuracy.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/moshkovitz21a.html
http://proceedings.mlr.press/v139/moshkovitz21a.htmlNeural Rough Differential Equations for Long Time SeriesNeural controlled differential equations (CDEs) are the continuous-time analogue of recurrent neural networks, as Neural ODEs are to residual networks, and offer a memory-efficient continuous-time way to model functions of potentially irregular time series. Existing methods for computing the forward pass of a Neural CDE involve embedding the incoming time series into path space, often via interpolation, and using evaluations of this path to drive the hidden state. Here, we use rough path theory to extend this formulation. Instead of directly embedding into path space, we instead represent the input signal over small time intervals through its \textit{log-signature}, which are statistics describing how the signal drives a CDE. This is the approach for solving \textit{rough differential equations} (RDEs), and correspondingly we describe our main contribution as the introduction of Neural RDEs. This extension has a purpose: by generalising the Neural CDE approach to a broader class of driving signals, we demonstrate particular advantages for tackling long time series. In this regime, we demonstrate efficacy on problems of length up to 17k observations and observe significant training speed-ups, improvements in model performance, and reduced memory requirements compared to existing approaches.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/morrill21b.html
http://proceedings.mlr.press/v139/morrill21b.htmlEfficient Deviation Types and Learning for Hindsight Rationality in Extensive-Form GamesHindsight rationality is an approach to playing general-sum games that prescribes no-regret learning dynamics for individual agents with respect to a set of deviations, and further describes jointly rational behavior among multiple agents with mediated equilibria. To develop hindsight rational learning in sequential decision-making settings, we formalize behavioral deviations as a general class of deviations that respect the structure of extensive-form games. Integrating the idea of time selection into counterfactual regret minimization (CFR), we introduce the extensive-form regret minimization (EFR) algorithm that achieves hindsight rationality for any given set of behavioral deviations with computation that scales closely with the complexity of the set. We identify behavioral deviation subsets, the partial sequence deviation types, that subsume previously studied types and lead to efficient EFR instances in games with moderate lengths. In addition, we present a thorough empirical analysis of EFR instantiated with different deviation types in benchmark games, where we find that stronger types typically induce better performance.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/morrill21a.html
http://proceedings.mlr.press/v139/morrill21a.htmlPODS: Policy Optimization via Differentiable SimulationCurrent reinforcement learning (RL) methods use simulation models as simple black-box oracles. In this paper, with the goal of improving the performance exhibited by RL algorithms, we explore a systematic way of leveraging the additional information provided by an emerging class of differentiable simulators. Building on concepts established by Deterministic Policy Gradients (DPG) methods, the neural network policies learned with our approach represent deterministic actions. In a departure from standard methodologies, however, learning these policies does not hinge on approximations of the value function that must be learned concurrently in an actor-critic fashion. Instead, we exploit differentiable simulators to directly compute the analytic gradient of a policy’s value function with respect to the actions it outputs. This, in turn, allows us to efficiently perform locally optimal policy improvement iterations. Compared against other state-of-the-art RL methods, we show that with minimal hyper-parameter tuning our approach consistently leads to better asymptotic behavior across a set of payload manipulation tasks that demand a high degree of accuracy and precision.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/mora21a.html
http://proceedings.mlr.press/v139/mora21a.htmlThe Power of Log-Sum-Exp: Sequential Density Ratio Matrix Estimation for Speed-Accuracy OptimizationWe propose a model for multiclass classification of time series to make a prediction as early and as accurate as possible. The matrix sequential probability ratio test (MSPRT) is known to be asymptotically optimal for this setting, but contains a critical assumption that hinders broad real-world applications; the MSPRT requires the underlying probability density. To address this problem, we propose to solve density ratio matrix estimation (DRME), a novel type of density ratio estimation that consists of estimating matrices of multiple density ratios with constraints and thus is more challenging than the conventional density ratio estimation. We propose a log-sum-exp-type loss function (LSEL) for solving DRME and prove the following: (i) the LSEL provides the true density ratio matrix as the sample size of the training set increases (consistency); (ii) it assigns larger gradients to harder classes (hard class weighting effect); and (iii) it provides discriminative scores even on class-imbalanced datasets (guess-aversion). Our overall architecture for early classification, MSPRT-TANDEM, statistically significantly outperforms baseline models on four datasets including action recognition, especially in the early stage of sequential observations. Our code and datasets are publicly available.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/miyagawa21a.html
http://proceedings.mlr.press/v139/miyagawa21a.htmlOffline Meta-Reinforcement Learning with Advantage WeightingThis paper introduces the offline meta-reinforcement learning (offline meta-RL) problem setting and proposes an algorithm that performs well in this setting. Offline meta-RL is analogous to the widely successful supervised learning strategy of pre-training a model on a large batch of fixed, pre-collected data (possibly from various tasks) and fine-tuning the model to a new task with relatively little data. That is, in offline meta-RL, we meta-train on fixed, pre-collected data from several tasks and adapt to a new task with a very small amount (less than 5 trajectories) of data from the new task. By nature of being offline, algorithms for offline meta-RL can utilize the largest possible pool of training data available and eliminate potentially unsafe or costly data collection during meta-training. This setting inherits the challenges of offline RL, but it differs significantly because offline RL does not generally consider a) transfer to new tasks or b) limited data from the test task, both of which we face in offline meta-RL. Targeting the offline meta-RL setting, we propose Meta-Actor Critic with Advantage Weighting (MACAW). MACAW is an optimization-based meta-learning algorithm that uses simple, supervised regression objectives for both the inner and outer loop of meta-training. On offline variants of common meta-RL benchmarks, we empirically find that this approach enables fully offline meta-reinforcement learning and achieves notable gains over prior methods.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/mitchell21a.html
http://proceedings.mlr.press/v139/mitchell21a.htmlAn Identifiable Double VAE For Disentangled RepresentationsA large part of the literature on learning disentangled representations focuses on variational autoencoders (VAEs). Recent developments demonstrate that disentanglement cannot be obtained in a fully unsupervised setting without inductive biases on models and data. However, Khemakhem et al., AISTATS, 2020 suggest that employing a particular form of factorized prior, conditionally dependent on auxiliary variables complementing input observations, can be one such bias, resulting in an identifiable model with guarantees on disentanglement. Working along this line, we propose a novel VAE-based generative model with theoretical guarantees on identifiability. We obtain our conditional prior over the latents by learning an optimal representation, which imposes an additional strength on their regularization. We also extend our method to semi-supervised settings. Experimental results indicate superior performance with respect to state-of-the-art approaches, according to several established metrics proposed in the literature on disentanglement.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/mita21a.html
http://proceedings.mlr.press/v139/mita21a.htmlOn the Explicit Role of Initialization on the Convergence and Implicit Bias of Overparametrized Linear NetworksNeural networks trained via gradient descent with random initialization and without any regularization enjoy good generalization performance in practice despite being highly overparametrized. A promising direction to explain this phenomenon is to study how initialization and overparametrization affect convergence and implicit bias of training algorithms. In this paper, we present a novel analysis of single-hidden-layer linear networks trained under gradient flow, which connects initialization, optimization, and overparametrization. Firstly, we show that the squared loss converges exponentially to its optimum at a rate that depends on the level of imbalance of the initialization. Secondly, we show that proper initialization constrains the dynamics of the network parameters to lie within an invariant set. In turn, minimizing the loss over this set leads to the min-norm solution. Finally, we show that large hidden layer width, together with (properly scaled) random initialization, ensures proximity to such an invariant set during training, allowing us to derive a novel non-asymptotic upper-bound on the distance between the trained network and the min-norm solution.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/min21c.html
http://proceedings.mlr.press/v139/min21c.htmlMeta-StyleSpeech : Multi-Speaker Adaptive Text-to-Speech GenerationWith rapid progress in neural text-to-speech (TTS) models, personalized speech generation is now in high demand for many applications. For practical applicability, a TTS model should generate high-quality speech with only a few audio samples from the given speaker, that are also short in length. However, existing methods either require to fine-tune the model or achieve low adaptation quality without fine-tuning. In this work, we propose StyleSpeech, a new TTS model which not only synthesizes high-quality speech but also effectively adapts to new speakers. Specifically, we propose Style-Adaptive Layer Normalization (SALN) which aligns gain and bias of the text input according to the style extracted from a reference speech audio. With SALN, our model effectively synthesizes speech in the style of the target speaker even from a single speech audio. Furthermore, to enhance StyleSpeech’s adaptation to speech from new speakers, we extend it to Meta-StyleSpeech by introducing two discriminators trained with style prototypes, and performing episodic training. The experimental results show that our models generate high-quality speech which accurately follows the speaker’s voice with single short-duration (1-3 sec) speech audio, significantly outperforming baselines.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/min21b.html
http://proceedings.mlr.press/v139/min21b.htmlSignatured Deep Fictitious Play for Mean Field Games with Common NoiseExisting deep learning methods for solving mean-field games (MFGs) with common noise fix the sampling common noise paths and then solve the corresponding MFGs. This leads to a nested loop structure with millions of simulations of common noise paths in order to produce accurate solutions, which results in prohibitive computational cost and limits the applications to a large extent. In this paper, based on the rough path theory, we propose a novel single-loop algorithm, named signatured deep fictitious play (Sig-DFP), by which we can work with the unfixed common noise setup to avoid the nested loop structure and reduce the computational complexity significantly. The proposed algorithm can accurately capture the effect of common uncertainty changes on mean-field equilibria without further training of neural networks, as previously needed in the existing machine learning algorithms. The efficiency is supported by three applications, including linear-quadratic MFGs, mean-field portfolio game, and mean-field game of optimal consumption and investment. Overall, we provide a new point of view from the rough path theory to solve MFGs with common noise with significantly improved efficiency and an extensive range of applications. In addition, we report the first deep learning work to deal with extended MFGs (a mean-field interaction via both the states and controls) with common noise.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/min21a.html
http://proceedings.mlr.press/v139/min21a.htmlAccuracy on the Line: on the Strong Correlation Between Out-of-Distribution and In-Distribution GeneralizationFor machine learning systems to be reliable, we must understand their performance in unseen, out- of-distribution environments. In this paper, we empirically show that out-of-distribution performance is strongly correlated with in-distribution performance for a wide range of models and distribution shifts. Specifically, we demonstrate strong correlations between in-distribution and out-of- distribution performance on variants of CIFAR- 10 & ImageNet, a synthetic pose estimation task derived from YCB objects, FMoW-WILDS satellite imagery classification, and wildlife classification in iWildCam-WILDS. The correlation holds across model architectures, hyperparameters, training set size, and training duration, and is more precise than what is expected from existing domain adaptation theory. To complete the picture, we also investigate cases where the correlation is weaker, for instance some synthetic distribution shifts from CIFAR-10-C and the tissue classification dataset Camelyon17-WILDS. Finally, we provide a candidate theory based on a Gaussian data model that shows how changes in the data covariance arising from distribution shift can affect the observed correlations.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/miller21b.html
http://proceedings.mlr.press/v139/miller21b.htmlOutside the Echo Chamber: Optimizing the Performative RiskIn performative prediction, predictions guide decision-making and hence can influence the distribution of future data. To date, work on performative prediction has focused on finding performatively stable models, which are the fixed points of repeated retraining. However, stable solutions can be far from optimal when evaluated in terms of the performative risk, the loss experienced by the decision maker when deploying a model. In this paper, we shift attention beyond performative stability and focus on optimizing the performative risk directly. We identify a natural set of properties of the loss function and model-induced distribution shift under which the performative risk is convex, a property which does not follow from convexity of the loss alone. Furthermore, we develop algorithms that leverage our structural assumptions to optimize the performative risk with better sample efficiency than generic methods for derivative-free convex optimization.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/miller21a.html
http://proceedings.mlr.press/v139/miller21a.htmlEfficientTTS: An Efficient and High-Quality Text-to-Speech ArchitectureIn this work, we address the Text-to-Speech (TTS) task by proposing a non-autoregressive architecture called EfficientTTS. Unlike the dominant non-autoregressive TTS models, which are trained with the need of external aligners, EfficientTTS optimizes all its parameters with a stable, end-to-end training procedure, allowing for synthesizing high quality speech in a fast and efficient manner. EfficientTTS is motivated by a new monotonic alignment modeling approach, which specifies monotonic constraints to the sequence alignment with almost no increase of computation. By combining EfficientTTS with different feed-forward network structures, we develop a family of TTS models, including both text-to-melspectrogram and text-to-waveform networks. We experimentally show that the proposed models significantly outperform counterpart models such as Tacotron 2 and Glow-TTS in terms of speech quality, training efficiency and synthesis speed, while still producing the speeches of strong robustness and great diversity. In addition, we demonstrate that proposed approach can be easily extended to autoregressive models such as Tacotron 2.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/miao21a.html
http://proceedings.mlr.press/v139/miao21a.htmlLearning in Nonzero-Sum Stochastic Games with PotentialsMulti-agent reinforcement learning (MARL) has become effective in tackling discrete cooperative game scenarios. However, MARL has yet to penetrate settings beyond those modelled by team and zero-sum games, confining it to a small subset of multi-agent systems. In this paper, we introduce a new generation of MARL learners that can handle \textit{nonzero-sum} payoff structures and continuous settings. In particular, we study the MARL problem in a class of games known as stochastic potential games (SPGs) with continuous state-action spaces. Unlike cooperative games, in which all agents share a common reward, SPGs are capable of modelling real-world scenarios where agents seek to fulfil their individual goals. We prove theoretically our learning method, $\ourmethod$, enables independent agents to learn Nash equilibrium strategies in \textit{polynomial time}. We demonstrate our framework tackles previously unsolvable tasks such as \textit{Coordination Navigation} and \textit{large selfish routing games} and that it outperforms the state of the art MARL baselines such as MADDPG and COMIX in such scenarios.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/mguni21a.html
http://proceedings.mlr.press/v139/mguni21a.htmlMixed Nash Equilibria in the Adversarial Examples GameThis paper tackles the problem of adversarial examples from a game theoretic point of view. We study the open question of the existence of mixed Nash equilibria in the zero-sum game formed by the attacker and the classifier. While previous works usually allow only one player to use randomized strategies, we show the necessity of considering randomization for both the classifier and the attacker. We demonstrate that this game has no duality gap, meaning that it always admits approximate Nash equilibria. We also provide the first optimization algorithms to learn a mixture of classifiers that approximately realizes the value of this game, \emph{i.e.} procedures to build an optimally robust randomized classifier.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/meunier21a.html
http://proceedings.mlr.press/v139/meunier21a.htmlProvably Efficient Learning of Transferable RewardsThe reward function is widely accepted as a succinct, robust, and transferable representation of a task. Typical approaches, at the basis of Inverse Reinforcement Learning (IRL), leverage on expert demonstrations to recover a reward function. In this paper, we study the theoretical properties of the class of reward functions that are compatible with the expert’s behavior. We analyze how the limited knowledge of the expert’s policy and of the environment affects the reward reconstruction phase. Then, we examine how the error propagates to the learned policy’s performance when transferring the reward function to a different environment. We employ these findings to devise a provably efficient active sampling approach, aware of the need for transferring the reward function, that can be paired with a large variety of IRL algorithms. Finally, we provide numerical simulations on benchmark environments.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/metelli21a.html
http://proceedings.mlr.press/v139/metelli21a.htmlCounterfactual Credit Assignment in Model-Free Reinforcement LearningCredit assignment in reinforcement learning is the problem of measuring an action’s influence on future rewards. In particular, this requires separating skill from luck, i.e. disentangling the effect of an action on rewards from that of external factors and subsequent actions. To achieve this, we adapt the notion of counterfactuals from causality theory to a model-free RL setup. The key idea is to condition value functions on future events, by learning to extract relevant information from a trajectory. We formulate a family of policy gradient algorithms that use these future-conditional value functions as baselines or critics, and show that they are provably low variance. To avoid the potential bias from conditioning on future information, we constrain the hindsight information to not contain information about the agent’s actions. We demonstrate the efficacy and validity of our algorithm on a number of illustrative and challenging problems.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/mesnard21a.html
http://proceedings.mlr.press/v139/mesnard21a.htmlLearn2Hop: Learned Optimization on Rough LandscapesOptimization of non-convex loss surfaces containing many local minima remains a critical problem in a variety of domains, including operations research, informatics, and material design. Yet, current techniques either require extremely high iteration counts or a large number of random restarts for good performance. In this work, we propose adapting recent developments in meta-learning to these many-minima problems by learning the optimization algorithm for various loss landscapes. We focus on problems from atomic structural optimization—finding low energy configurations of many-atom systems—including widely studied models such as bimetallic clusters and disordered silicon. We find that our optimizer learns a hopping behavior which enables efficient exploration and improves the rate of low energy minima discovery. Finally, our learned optimizers show promising generalization with efficiency gains on never before seen tasks (e.g. new elements or compositions). Code is available at https://learn2hop.page.link/github.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/merchant21a.html
http://proceedings.mlr.press/v139/merchant21a.htmlA statistical perspective on distillationKnowledge distillation is a technique for improving a “student” model by replacing its one-hot training labels with a label distribution obtained from a “teacher” model. Despite its broad success, several basic questions — e.g., Why does distillation help? Why do more accurate teachers not necessarily distill better? — have received limited formal study. In this paper, we present a statistical perspective on distillation which provides an answer to these questions. Our core observation is that a “Bayes teacher” providing the true class-probabilities can lower the variance of the student objective, and thus improve performance. We then establish a bias-variance tradeoff that quantifies the value of teachers that approximate the Bayes class-probabilities. This provides a formal criterion as to what constitutes a “good” teacher, namely, the quality of its probability estimates. Finally, we illustrate how our statistical perspective facilitates novel applications of distillation to bipartite ranking and multiclass retrieval.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/menon21a.html
http://proceedings.mlr.press/v139/menon21a.htmlAn Integer Linear Programming Framework for Mining Constraints from DataStructured output prediction problems (e.g., sequential tagging, hierarchical multi-class classification) often involve constraints over the output space. These constraints interact with the learned models to filter infeasible solutions and facilitate in building an accountable system. However, despite constraints are useful, they are often based on hand-crafted rules. This raises a question – can we mine constraints and rules from data based on a learning algorithm? In this paper, we present a general framework for mining constraints from data. In particular, we consider the inference in structured output prediction as an integer linear programming (ILP) problem. Then, given the coefficients of the objective function and the corresponding solution, we mine the underlying constraints by estimating the outer and inner polytopes of the feasible set. We verify the proposed constraint mining algorithm in various synthetic and real-world applications and demonstrate that the proposed approach successfully identifies the feasible set at scale. In particular, we show that our approach can learn to solve 9x9 Sudoku puzzles and minimal spanning tree problems from examples without providing the underlying rules. Our algorithm can also integrate with a neural network model to learn the hierarchical label structure of a multi-label classification task. Besides, we provide theoretical analysis about the tightness of the polytopes and the reliability of the mined constraints.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/meng21a.html
http://proceedings.mlr.press/v139/meng21a.htmlUCB Momentum Q-learning: Correcting the bias without forgettingWe propose UCBMQ, Upper Confidence Bound Momentum Q-learning, a new algorithm for reinforcement learning in tabular and possibly stage-dependent, episodic Markov decision process. UCBMQ is based on Q-learning where we add a momentum term and rely on the principle of optimism in face of uncertainty to deal with exploration. Our new technical ingredient of UCBMQ is the use of momentum to correct the bias that Q-learning suffers while, \emph{at the same time}, limiting the impact it has on the second-order term of the regret. For UCBMQ, we are able to guarantee a regret of at most $\tilde{O}(\sqrt{H^3SAT}+ H^4 S A)$ where $H$ is the length of an episode, $S$ the number of states, $A$ the number of actions, $T$ the number of episodes and ignoring terms in poly$\log(SAHT)$. Notably, UCBMQ is the first algorithm that simultaneously matches the lower bound of $\Omega(\sqrt{H^3SAT})$ for large enough $T$ and has a second-order term (with respect to $T$) that scales \emph{only linearly} with the number of states $S$.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/menard21b.html
http://proceedings.mlr.press/v139/menard21b.htmlFast active learning for pure exploration in reinforcement learningRealistic environments often provide agents with very limited feedback. When the environment is initially unknown, the feedback, in the beginning, can be completely absent, and the agents may first choose to devote all their effort on \emph{exploring efficiently.} The exploration remains a challenge while it has been addressed with many hand-tuned heuristics with different levels of generality on one side, and a few theoretically-backed exploration strategies on the other. Many of them are incarnated by \emph{intrinsic motivation} and in particular \emph{explorations bonuses}. A common choice is to use $1/\sqrt{n}$ bonus, where $n$ is a number of times this particular state-action pair was visited. We show that, surprisingly, for a pure-exploration objective of \emph{reward-free exploration}, bonuses that scale with $1/n$ bring faster learning rates, improving the known upper bounds with respect to the dependence on the horizon $H$. Furthermore, we show that with an improved analysis of the stopping time, we can improve by a factor $H$ the sample complexity in the \emph{best-policy identification} setting, which is another pure-exploration objective, where the environment provides rewards but the agent is not penalized for its behavior during the exploration phase.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/menard21a.html
http://proceedings.mlr.press/v139/menard21a.htmlNeural Architecture Search without TrainingThe time and effort involved in hand-designing deep neural networks is immense. This has prompted the development of Neural Architecture Search (NAS) techniques to automate this design. However, NAS algorithms tend to be slow and expensive; they need to train vast numbers of candidate networks to inform the search process. This could be alleviated if we could partially predict a network’s trained accuracy from its initial state. In this work, we examine the overlap of activations between datapoints in untrained networks and motivate how this can give a measure which is usefully indicative of a network’s trained performance. We incorporate this measure into a simple algorithm that allows us to search for powerful networks without any training in a matter of seconds on a single GPU, and verify its effectiveness on NAS-Bench-101, NAS-Bench-201, NATS-Bench, and Network Design Spaces. Our approach can be readily combined with more expensive search methods; we examine a simple adaptation of regularised evolutionary search. Code for reproducing our experiments is available at https://github.com/BayesWatch/nas-without-training.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/mellor21a.html
http://proceedings.mlr.press/v139/mellor21a.htmlA theory of high dimensional regression with arbitrary correlations between input features and target functions: sample complexity, multiple descent curves and a hierarchy of phase transitionsThe performance of neural networks depends on precise relationships between four distinct ingredients: the architecture, the loss function, the statistical structure of inputs, and the ground truth target function. Much theoretical work has focused on understanding the role of the first two ingredients under highly simplified models of random uncorrelated data and target functions. In contrast, performance likely relies on a conspiracy between the statistical structure of the input distribution and the structure of the function to be learned. To understand this better we revisit ridge regression in high dimensions, which corresponds to an exceedingly simple architecture and loss function, but we analyze its performance under arbitrary correlations between input features and the target function. We find a rich mathematical structure that includes: (1) a dramatic reduction in sample complexity when the target function aligns with data anisotropy; (2) the existence of multiple descent curves; (3) a sequence of phase transitions in the performance, loss landscape, and optimal regularization as a function of the amount of data that explains the first two effects.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/mel21a.html
http://proceedings.mlr.press/v139/mel21a.htmlControlling Graph Dynamics with Reinforcement Learning and Graph Neural NetworksWe consider the problem of controlling a partially-observed dynamic process on a graph by a limited number of interventions. This problem naturally arises in contexts such as scheduling virus tests to curb an epidemic; targeted marketing in order to promote a product; and manually inspecting posts to detect fake news spreading on social networks. We formulate this setup as a sequential decision problem over a temporal graph process. In face of an exponential state space, combinatorial action space and partial observability, we design a novel tractable scheme to control dynamical processes on temporal graphs. We successfully apply our approach to two popular problems that fall into our framework: prioritizing which nodes should be tested in order to curb the spread of an epidemic, and influence maximization on a graph.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/meirom21a.html
http://proceedings.mlr.press/v139/meirom21a.htmlLeveraging Non-uniformity in First-order Non-convex OptimizationClassical global convergence results for first-order methods rely on uniform smoothness and the Ł{}ojasiewicz inequality. Motivated by properties of objective functions that arise in machine learning, we propose a non-uniform refinement of these notions, leading to \emph{Non-uniform Smoothness} (NS) and \emph{Non-uniform Ł{}ojasiewicz inequality} (NŁ{}). The new definitions inspire new geometry-aware first-order methods that are able to converge to global optimality faster than the classical $\Omega(1/t^2)$ lower bounds. To illustrate the power of these geometry-aware methods and their corresponding non-uniform analysis, we consider two important problems in machine learning: policy gradient optimization in reinforcement learning (PG), and generalized linear model training in supervised learning (GLM). For PG, we find that normalizing the gradient ascent method can accelerate convergence to $O(e^{- c \cdot t})$ (where $c > 0$) while incurring less overhead than existing algorithms. For GLM, we show that geometry-aware normalized gradient descent can also achieve a linear convergence rate, which significantly improves the best known results. We additionally show that the proposed geometry-aware gradient descent methods escape landscape plateaus faster than standard gradient descent. Experimental results are used to illustrate and complement the theoretical findings.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/mei21a.html
http://proceedings.mlr.press/v139/mei21a.htmlFundamental Tradeoffs in Distributionally Adversarial TrainingAdversarial training is among the most effective techniques to improve robustness of models against adversarial perturbations. However, the full effect of this approach on models is not well understood. For example, while adversarial training can reduce the adversarial risk (prediction error against an adversary), it sometimes increase standard risk (generalization error when there is no adversary). In this paper, we focus on \emph{distribution perturbing} adversary framework wherein the adversary can change the test distribution within a neighborhood of the training data distribution. The neighborhood is defined via Wasserstein distance between distributions and the radius of the neighborhood is a measure of adversary’s manipulative power. We study the tradeoff between standard risk and adversarial risk and derive the Pareto-optimal tradeoff, achievable over specific classes of models, in the infinite data limit with features dimension kept fixed. We consider three learning settings: 1) Regression with the class of linear models; 2) Binary classification under the Gaussian mixtures data model, with the class of linear classifiers; 3) Regression with the class of random features model (which can be equivalently represented as two-layer neural network with random first-layer weights). We show that a tradeoff between standard and adversarial risk is manifested in all three settings. We further characterize the Pareto-optimal tradeoff curves and discuss how a variety of factors, such as features correlation, adversary’s power or the width of two-layer neural network would affect this tradeoff.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/mehrabi21a.html
http://proceedings.mlr.press/v139/mehrabi21a.htmlAdversarial Multi Class Learning under Weak Supervision with Performance GuaranteesWe develop a rigorous approach for using a set of arbitrarily correlated weak supervision sources in order to solve a multiclass classification task when only a very small set of labeled data is available. Our learning algorithm provably converges to a model that has minimum empirical risk with respect to an adversarial choice over feasible labelings for a set of unlabeled data, where the feasibility of a labeling is computed through constraints defined by rigorously estimated statistics of the weak supervision sources. We show theoretical guarantees for this approach that depend on the information provided by the weak supervision sources. Notably, this method does not require the weak supervision sources to have the same labeling space as the multiclass classification task. We demonstrate the effectiveness of our approach with experiments on various image classification tasks.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/mazzetto21a.html
http://proceedings.mlr.press/v139/mazzetto21a.htmlRobust Unsupervised Learning via L-statistic MinimizationDesigning learning algorithms that are resistant to perturbations of the underlying data distribution is a problem of wide practical and theoretical importance. We present a general approach to this problem focusing on unsupervised learning. The key assumption is that the perturbing distribution is characterized by larger losses relative to a given class of admissible models. This is exploited by a general descent algorithm which minimizes an $L$-statistic criterion over the model class, weighting small losses more. Our analysis characterizes the robustness of the method in terms of bounds on the reconstruction error relative to the underlying unperturbed distribution. As a byproduct, we prove uniform convergence bounds with respect to the proposed criterion for several popular models in unsupervised learning, a result which may be of independent interest. Numerical experiments with \textsc{kmeans} clustering and principal subspace analysis demonstrate the effectiveness of our approach.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/maurer21a.html
http://proceedings.mlr.press/v139/maurer21a.htmlProximal Causal Learning with Kernels: Two-Stage Estimation and Moment RestrictionWe address the problem of causal effect estima-tion in the presence of unobserved confounding,but where proxies for the latent confounder(s) areobserved. We propose two kernel-based meth-ods for nonlinear causal effect estimation in thissetting: (a) a two-stage regression approach, and(b) a maximum moment restriction approach. Wefocus on the proximal causal learning setting, butour methods can be used to solve a wider classof inverse problems characterised by a Fredholmintegral equation. In particular, we provide a uni-fying view of two-stage and moment restrictionapproaches for solving this problem in a nonlin-ear setting. We provide consistency guaranteesfor each algorithm, and demonstrate that these ap-proaches achieve competitive results on syntheticdata and data simulating a real-world task. In par-ticular, our approach outperforms earlier methodsthat are not suited to leveraging proxy variables.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/mastouri21a.html
http://proceedings.mlr.press/v139/mastouri21a.htmlNecessary and sufficient conditions for causal feature selection in time series with latent common causesWe study the identification of direct and indirect causes on time series with latent variables, and provide a constrained-based causal feature selection method, which we prove that is both sound and complete under some graph constraints. Our theory and estimation algorithm require only two conditional independence tests for each observed candidate time series to determine whether or not it is a cause of an observed target time series. Furthermore, our selection of the conditioning set is such that it improves signal to noise ratio. We apply our method on real data, and on a wide range of simulated experiments, which yield very low false positive and relatively low false negative rates.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/mastakouri21a.html
http://proceedings.mlr.press/v139/mastakouri21a.htmlBlind Pareto Fairness and Subgroup RobustnessMuch of the work in the field of group fairness addresses disparities between predefined groups based on protected features such as gender, age, and race, which need to be available at train, and often also at test, time. These approaches are static and retrospective, since algorithms designed to protect groups identified a priori cannot anticipate and protect the needs of different at-risk groups in the future. In this work we analyze the space of solutions for worst-case fairness beyond demographics, and propose Blind Pareto Fairness (BPF), a method that leverages no-regret dynamics to recover a fair minimax classifier that reduces worst-case risk of any potential subgroup of sufficient size, and guarantees that the remaining population receives the best possible level of service. BPF addresses fairness beyond demographics, that is, it does not rely on predefined notions of at-risk groups, neither at train nor at test time. Our experimental results show that the proposed framework improves worst-case risk in multiple standard datasets, while simultaneously providing better levels of service for the remaining population. The code is available at github.com/natalialmg/BlindParetoFairnessThu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/martinez21a.html
http://proceedings.mlr.press/v139/martinez21a.htmlMulti-Agent Training beyond Zero-Sum with Correlated Equilibrium Meta-SolversTwo-player, constant-sum games are well studied in the literature, but there has been limited progress outside of this setting. We propose Joint Policy-Space Response Oracles (JPSRO), an algorithm for training agents in n-player, general-sum extensive form games, which provably converges to an equilibrium. We further suggest correlated equilibria (CE) as promising meta-solvers, and propose a novel solution concept Maximum Gini Correlated Equilibrium (MGCE), a principled and computationally efficient family of solutions for solving the correlated equilibrium selection problem. We conduct several experiments using CE meta-solvers for JPSRO and demonstrate convergence on n-player, general-sum games.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/marris21a.html
http://proceedings.mlr.press/v139/marris21a.htmlExplanations for Monotonic Classifiers.In many classification tasks there is a requirement of monotonicity. Concretely, if all else remains constant, increasing (resp. decreasing) the value of one or more features must not decrease (resp. increase) the value of the prediction. Despite comprehensive efforts on learning monotonic classifiers, dedicated approaches for explaining monotonic classifiers are scarce and classifier-specific. This paper describes novel algorithms for the computation of one formal explanation of a (black-box) monotonic classifier. These novel algorithms are polynomial (indeed linear) in the run time complexity of the classifier. Furthermore, the paper presents a practically efficient model-agnostic algorithm for enumerating formal explanations.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/marques-silva21a.html
http://proceedings.mlr.press/v139/marques-silva21a.htmlAdaptive Sampling for Best Policy Identification in Markov Decision ProcessesWe investigate the problem of best-policy identification in discounted Markov Decision Processes (MDPs) when the learner has access to a generative model. The objective is to devise a learning algorithm returning the best policy as early as possible. We first derive a problem-specific lower bound of the sample complexity satisfied by any learning algorithm. This lower bound corresponds to an optimal sample allocation that solves a non-convex program, and hence, is hard to exploit in the design of efficient algorithms. We then provide a simple and tight upper bound of the sample complexity lower bound, whose corresponding nearly-optimal sample allocation becomes explicit. The upper bound depends on specific functionals of the MDP such as the sub-optimality gaps and the variance of the next-state value function, and thus really captures the hardness of the MDP. Finally, we devise KLB-TS (KL Ball Track-and-Stop), an algorithm tracking this nearly-optimal allocation, and provide asymptotic guarantees for its sample complexity (both almost surely and in expectation). The advantages of KLB-TS against state-of-the-art algorithms are discussed and illustrated numerically.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/marjani21a.html
http://proceedings.mlr.press/v139/marjani21a.htmlNear-Optimal Model-Free Reinforcement Learning in Non-Stationary Episodic MDPsWe consider model-free reinforcement learning (RL) in non-stationary Markov decision processes. Both the reward functions and the state transition functions are allowed to vary arbitrarily over time as long as their cumulative variations do not exceed certain variation budgets. We propose Restarted Q-Learning with Upper Confidence Bounds (RestartQ-UCB), the first model-free algorithm for non-stationary RL, and show that it outperforms existing solutions in terms of dynamic regret. Specifically, RestartQ-UCB with Freedman-type bonus terms achieves a dynamic regret bound of $\widetilde{O}(S^{\frac{1}{3}} A^{\frac{1}{3}} \Delta^{\frac{1}{3}} H T^{\frac{2}{3}})$, where $S$ and $A$ are the numbers of states and actions, respectively, $\Delta>0$ is the variation budget, $H$ is the number of time steps per episode, and $T$ is the total number of time steps. We further show that our algorithm is \emph{nearly optimal} by establishing an information-theoretical lower bound of $\Omega(S^{\frac{1}{3}} A^{\frac{1}{3}} \Delta^{\frac{1}{3}} H^{\frac{2}{3}} T^{\frac{2}{3}})$, the first lower bound in non-stationary RL. Numerical experiments validate the advantages of RestartQ-UCB in terms of both cumulative rewards and computational efficiency. We further demonstrate the power of our results in the context of multi-agent RL, where non-stationarity is a key challenge.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/mao21b.html
http://proceedings.mlr.press/v139/mao21b.htmlConsistent Nonparametric Methods for Network Assisted Covariate EstimationNetworks with node covariates are commonplace: for example, people in a social network have interests, or product preferences, etc. If we know the covariates for some nodes, can we infer them for the remaining nodes? In this paper we propose a new similarity measure between two nodes based on the patterns of their 2-hop neighborhoods. We show that a simple algorithm (CN-VEC) like nearest neighbor regression with this metric is consistent for a wide range of models when the degree grows faster than $n^{1/3}$ up-to logarithmic factors, where $n$ is the number of nodes. For "low-rank" latent variable models, the natural contender will be to estimate the latent variables using SVD and use them for non-parametric regression. While we show consistency of this method under less stringent sparsity conditions, our experimental results suggest that the simple local CN-VEC method either outperforms the global SVD-RBF method, or has comparable performance for low rank models. We also present simulated and real data experiments to show the effectiveness of our algorithms compared to the state of the art.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/mao21a.html
http://proceedings.mlr.press/v139/mao21a.htmlBeyond the Pareto Efficient Frontier: Constraint Active Search for Multiobjective Experimental DesignMany problems in engineering design and simulation require balancing competing objectives under the presence of uncertainty. Sample-efficient multiobjective optimization methods focus on the objective function values in metric space and ignore the sampling behavior of the design configurations in parameter space. Consequently, they may provide little actionable insight on how to choose designs in the presence of metric uncertainty or limited precision when implementing a chosen design. We propose a new formulation that accounts for the importance of the parameter space and is thus more suitable for multiobjective design problems; instead of searching for the Pareto-efficient frontier, we solicit the desired minimum performance thresholds on all objectives to define regions of satisfaction. We introduce an active search algorithm called Expected Coverage Improvement (ECI) to efficiently discover the region of satisfaction and simultaneously sample diverse acceptable configurations. We demonstrate our algorithm on several design and simulation domains: mechanical design, additive manufacturing, medical monitoring, and plasma physics.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/malkomes21a.html
http://proceedings.mlr.press/v139/malkomes21a.htmlSample Efficient Reinforcement Learning In Continuous State Spaces: A Perspective Beyond LinearityReinforcement learning (RL) is empirically successful in complex nonlinear Markov decision processes (MDPs) with continuous state spaces. By contrast, the majority of theoretical RL literature requires the MDP to satisfy some form of linear structure, in order to guarantee sample efficient RL. Such efforts typically assume the transition dynamics or value function of the MDP are described by linear functions of the state features. To resolve this discrepancy between theory and practice, we introduce the Effective Planning Window (EPW) condition, a structural condition on MDPs that makes no linearity assumptions. We demonstrate that the EPW condition permits sample efficient RL, by providing an algorithm which provably solves MDPs satisfying this condition. Our algorithm requires minimal assumptions on the policy class, which can include multi-layer neural networks with nonlinear activation functions. Notably, the EPW condition is directly motivated by popular gaming benchmarks, and we show that many classic Atari games satisfy this condition. We additionally show the necessity of conditions like EPW, by demonstrating that simple MDPs with slight nonlinearities cannot be solved sample efficiently.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/malik21c.html
http://proceedings.mlr.press/v139/malik21c.htmlA Sampling-Based Method for Tensor Ring DecompositionWe propose a sampling-based method for computing the tensor ring (TR) decomposition of a data tensor. The method uses leverage score sampled alternating least squares to fit the TR cores in an iterative fashion. By taking advantage of the special structure of TR tensors, we can efficiently estimate the leverage scores and attain a method which has complexity sublinear in the number of input tensor entries. We provide high-probability relative-error guarantees for the sampled least squares problems. We compare our proposal to existing methods in experiments on both synthetic and real data. Our method achieves substantial speedup—sometimes two or three orders of magnitude—over competing methods, while maintaining good accuracy. We also provide an example of how our method can be used for rapid feature extraction.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/malik21b.html
http://proceedings.mlr.press/v139/malik21b.htmlInverse Constrained Reinforcement LearningIn real world settings, numerous constraints are present which are hard to specify mathematically. However, for the real world deployment of reinforcement learning (RL), it is critical that RL agents are aware of these constraints, so that they can act safely. In this work, we consider the problem of learning constraints from demonstrations of a constraint-abiding agent’s behavior. We experimentally validate our approach and show that our framework can successfully learn the most likely constraints that the agent respects. We further show that these learned constraints are \textit{transferable} to new agents that may have different morphologies and/or reward functions. Previous works in this regard have either mainly been restricted to tabular (discrete) settings, specific types of constraints or assume the environment’s transition dynamics. In contrast, our framework is able to learn arbitrary \textit{Markovian} constraints in high-dimensions in a completely model-free setting. The code is available at: \url{https://github.com/shehryar-malik/icrl}.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/malik21a.html
http://proceedings.mlr.press/v139/malik21a.htmlQuantifying the Benefit of Using Differentiable Learning over Tangent KernelsWe study the relative power of learning with gradient descent on differentiable models, such as neural networks, versus using the corresponding tangent kernels. We show that under certain conditions, gradient descent achieves small error only if a related tangent kernel method achieves a non-trivial advantage over random guessing (a.k.a. weak learning), though this advantage might be very small even when gradient descent can achieve arbitrarily high accuracy. Complementing this, we show that without these conditions, gradient descent can in fact learn with small error even when no kernel method, in particular using the tangent kernel, can achieve a non-trivial advantage over random guessing.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/malach21a.html
http://proceedings.mlr.press/v139/malach21a.htmlKO codes: inventing nonlinear encoding and decoding for reliable wireless communication via deep-learningLandmark codes underpin reliable physical layer communication, e.g., Reed-Muller, BCH, Convolution, Turbo, LDPC, and Polar codes: each is a linear code and represents a mathematical breakthrough. The impact on humanity is huge: each of these codes has been used in global wireless communication standards (satellite, WiFi, cellular). Reliability of communication over the classical additive white Gaussian noise (AWGN) channel enables benchmarking and ranking of the different codes. In this paper, we construct KO codes, a computationally efficient family of deep-learning driven (encoder, decoder) pairs that outperform the state-of-the-art reliability performance on the standardized AWGN channel. KO codes beat state-of-the-art Reed-Muller and Polar codes, under the low-complexity successive cancellation decoding, in the challenging short-to-medium block length regime on the AWGN channel. We show that the gains of KO codes are primarily due to the nonlinear mapping of information bits directly to transmit symbols (bypassing modulation) and yet possess an efficient, high-performance decoder. The key technical innovation that renders this possible is design of a novel family of neural architectures inspired by the computation tree of the {\bf K}ronecker {\bf O}peration (KO) central to Reed-Muller and Polar codes. These architectures pave way for the discovery of a much richer class of hitherto unexplored nonlinear algebraic structures.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/makkuva21a.html
http://proceedings.mlr.press/v139/makkuva21a.htmlNear-Optimal Algorithms for Explainable k-Medians and k-MeansWe consider the problem of explainable $k$-medians and $k$-means introduced by Dasgupta, Frost, Moshkovitz, and Rashtchian (ICML 2020). In this problem, our goal is to find a \emph{threshold decision tree} that partitions data into $k$ clusters and minimizes the $k$-medians or $k$-means objective. The obtained clustering is easy to interpret because every decision node of a threshold tree splits data based on a single feature into two groups. We propose a new algorithm for this problem which is $\tilde O(\log k)$ competitive with $k$-medians with $\ell_1$ norm and $\tilde O(k)$ competitive with $k$-means. This is an improvement over the previous guarantees of $O(k)$ and $O(k^2)$ by Dasgupta et al (2020). We also provide a new algorithm which is $O(\log^{\nicefrac{3}{2}} k)$ competitive for $k$-medians with $\ell_2$ norm. Our first algorithm is near-optimal: Dasgupta et al (2020) showed a lower bound of $\Omega(\log k)$ for $k$-medians; in this work, we prove a lower bound of $\tilde\Omega(k)$ for $k$-means. We also provide a lower bound of $\Omega(\log k)$ for $k$-medians with $\ell_2$ norm.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/makarychev21a.html
http://proceedings.mlr.press/v139/makarychev21a.htmlExploiting structured data for learning contagious diseases under incomplete testingOne of the ways that machine learning algorithms can help control the spread of an infectious disease is by building models that predict who is likely to become infected making them good candidates for preemptive interventions. In this work we ask: can we build reliable infection prediction models when the observed data is collected under limited, and biased testing that prioritizes testing symptomatic individuals? Our analysis suggests that when the infection is highly transmissible, incomplete testing might be sufficient to achieve good out-of-sample prediction error. Guided by this insight, we develop an algorithm that predicts infections, and show that it outperforms baselines on simulated data. We apply our model to data from a large hospital to predict Clostridioides difficile infections; a communicable disease that is characterized by both symptomatically infected and asymptomatic (i.e., untested) carriers. Using a proxy instead of the unobserved untested-infected state, we show that our model outperforms benchmarks in predicting infections.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/makar21a.html
http://proceedings.mlr.press/v139/makar21a.htmlNonparametric Hamiltonian Monte CarloProbabilistic programming uses programs to express generative models whose posterior probability is then computed by built-in inference engines. A challenging goal is to develop general purpose inference algorithms that work out-of-the-box for arbitrary programs in a universal probabilistic programming language (PPL). The densities defined by such programs, which may use stochastic branching and recursion, are (in general) nonparametric, in the sense that they correspond to models on an infinite-dimensional parameter space. However standard inference algorithms, such as the Hamiltonian Monte Carlo (HMC) algorithm, target distributions with a fixed number of parameters. This paper introduces the Nonparametric Hamiltonian Monte Carlo (NP-HMC) algorithm which generalises HMC to nonparametric models. Inputs to NP-HMC are a new class of measurable functions called “tree representable”, which serve as a language-independent representation of the density functions of probabilistic programs in a universal PPL. We provide a correctness proof of NP-HMC, and empirically demonstrate significant performance improvements over existing approaches on several nonparametric examples.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/mak21a.html
http://proceedings.mlr.press/v139/mak21a.htmlStability and Convergence of Stochastic Gradient Clipping: Beyond Lipschitz Continuity and SmoothnessStochastic gradient algorithms are often unstable when applied to functions that do not have Lipschitz-continuous and/or bounded gradients. Gradient clipping is a simple and effective technique to stabilize the training process for problems that are prone to the exploding gradient problem. Despite its widespread popularity, the convergence properties of the gradient clipping heuristic are poorly understood, especially for stochastic problems. This paper establishes both qualitative and quantitative convergence results of the clipped stochastic (sub)gradient method (SGD) for non-smooth convex functions with rapidly growing subgradients. Our analyses show that clipping enhances the stability of SGD and that the clipped SGD algorithm enjoys finite convergence rates in many cases. We also study the convergence of a clipped method with momentum, which includes clipped SGD as a special case, for weakly convex problems under standard assumptions. With a novel Lyapunov analysis, we show that the proposed method achieves the best-known rate for the considered class of problems, demonstrating the effectiveness of clipped methods also in this regime. Numerical results confirm our theoretical developments.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/mai21a.html
http://proceedings.mlr.press/v139/mai21a.htmlDomain Generalization using Causal MatchingIn the domain generalization literature, a common objective is to learn representations independent of the domain after conditioning on the class label. We show that this objective is not sufficient: there exist counter-examples where a model fails to generalize to unseen domains even after satisfying class-conditional domain invariance. We formalize this observation through a structural causal model and show the importance of modeling within-class variations for generalization. Specifically, classes contain objects that characterize specific causal features, and domains can be interpreted as interventions on these objects that change non-causal features. We highlight an alternative condition: inputs across domains should have the same representation if they are derived from the same object. Based on this objective, we propose matching-based algorithms when base objects are observed (e.g., through data augmentation) and approximate the objective when objects are not observed (MatchDG). Our simple matching-based algorithms are competitive to prior work on out-of-domain accuracy for rotated MNIST, Fashion-MNIST, PACS, and Chest-Xray datasets. Our method MatchDG also recovers ground-truth object matches: on MNIST and Fashion-MNIST, top-10 matches from MatchDG have over 50% overlap with ground-truth matches.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/mahajan21b.html
http://proceedings.mlr.press/v139/mahajan21b.htmlTesseract: Tensorised Actors for Multi-Agent Reinforcement LearningReinforcement Learning in large action spaces is a challenging problem. This is especially true for cooperative multi-agent reinforcement learning (MARL), which often requires tractable learning while respecting various constraints like communication budget and information about other agents. In this work, we focus on the fundamental hurdle affecting both value-based and policy-gradient approaches: an exponential blowup of the action space with the number of agents. For value-based methods, it poses challenges in accurately representing the optimal value function for value-based methods, thus inducing suboptimality. For policy gradient methods, it renders the critic ineffective and exacerbates the problem of the lagging critic. We show that from a learning theory perspective, both problems can be addressed by accurately representing the associated action-value function with a low-complexity hypothesis class. This requires accurately modelling the agent interactions in a sample efficient way. To this end, we propose a novel tensorised formulation of the Bellman equation. This gives rise to our method Tesseract, which utilises the view of Q-function seen as a tensor where the modes correspond to action spaces of different agents. Algorithms derived from Tesseract decompose the Q-tensor across the agents and utilise low-rank tensor approximations to model the agent interactions relevant to the task. We provide PAC analysis for Tesseract based algorithms and highlight their relevance to the class of rich observation MDPs. Empirical results in different domains confirm the gains in sample efficiency using Tesseract as supported by the theory.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/mahajan21a.html
http://proceedings.mlr.press/v139/mahajan21a.htmlLearning Interaction Kernels for Agent Systems on Riemannian ManifoldsInteracting agent and particle systems are extensively used to model complex phenomena in science and engineering. We consider the problem of learning interaction kernels in these dynamical systems constrained to evolve on Riemannian manifolds from given trajectory data. The models we consider are based on interaction kernels depending on pairwise Riemannian distances between agents, with agents interacting locally along the direction of the shortest geodesic connecting them. We show that our estimators converge at a rate that is independent of the dimension of the state space, and derive bounds on the trajectory estimation error, on the manifold, between the observed and estimated dynamics. We demonstrate the performance of our estimator on two classical first order interacting systems: Opinion Dynamics and a Predator-Swarm system, with each system constrained on two prototypical manifolds, the $2$-dimensional sphere and the Poincaré disk model of hyperbolic space.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/maggioni21a.html
http://proceedings.mlr.press/v139/maggioni21a.htmlLearning to Generate Noise for Multi-Attack RobustnessAdversarial learning has emerged as one of the successful techniques to circumvent the susceptibility of existing methods against adversarial perturbations. However, the majority of existing defense methods are tailored to defend against a single category of adversarial perturbation (e.g. $\ell_\infty$-attack). In safety-critical applications, this makes these methods extraneous as the attacker can adopt diverse adversaries to deceive the system. Moreover, training on multiple perturbations simultaneously significantly increases the computational overhead during training. To address these challenges, we propose a novel meta-learning framework that explicitly learns to generate noise to improve the model’s robustness against multiple types of attacks. Its key component is \emph{Meta Noise Generator (MNG)} that outputs optimal noise to stochastically perturb a given sample, such that it helps lower the error on diverse adversarial perturbations. By utilizing samples generated by MNG, we train a model by enforcing the label consistency across multiple perturbations. We validate the robustness of models trained by our scheme on various datasets and against a wide variety of perturbations, demonstrating that it significantly outperforms the baselines across multiple perturbations with a marginal computational cost.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/madaan21a.html
http://proceedings.mlr.press/v139/madaan21a.htmlLocal Algorithms for Finding Densely Connected ClustersLocal graph clustering is an important algorithmic technique for analysing massive graphs, and has been widely applied in many research fields of data science. While the objective of most (local) graph clustering algorithms is to find a vertex set of low conductance, there has been a sequence of recent studies that highlight the importance of the inter-connection between clusters when analysing real-world datasets. Following this line of research, in this work we study local algorithms for finding a pair of vertex sets defined with respect to their inter-connection and their relationship with the rest of the graph. The key to our analysis is a new reduction technique that relates the structure of multiple sets to a single vertex set in the reduced graph. Among many potential applications, we show that our algorithms successfully recover densely connected clusters in the Interstate Disputes Dataset and the US Migration Dataset.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/macgregor21a.html
http://proceedings.mlr.press/v139/macgregor21a.htmlLearning Stochastic Behaviour from Aggregate DataLearning nonlinear dynamics from aggregate data is a challenging problem because the full trajectory of each individual is not available, namely, the individual observed at one time may not be observed at the next time point, or the identity of individual is unavailable. This is in sharp contrast to learning dynamics with full trajectory data, on which the majority of existing methods are based. We propose a novel method using the weak form of Fokker Planck Equation (FPE) — a partial differential equation — to describe the density evolution of data in a sampled form, which is then combined with Wasserstein generative adversarial network (WGAN) in the training process. In such a sample-based framework we are able to learn the nonlinear dynamics from aggregate data without explicitly solving the partial differential equation (PDE) FPE. We demonstrate our approach in the context of a series of synthetic and real-world data sets.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/ma21c.html
http://proceedings.mlr.press/v139/ma21c.htmlNeural-Pull: Learning Signed Distance Function from Point clouds by Learning to Pull Space onto SurfaceReconstructing continuous surfaces from 3D point clouds is a fundamental operation in 3D geometry processing. Several recent state-of-the-art methods address this problem using neural networks to learn signed distance functions (SDFs). In this paper, we introduce Neural-Pull, a new approach that is simple and leads to high quality SDFs. Specifically, we train a neural network to pull query 3D locations to their closest points on the surface using the predicted signed distance values and the gradient at the query locations, both of which are computed by the network itself. The pulling operation moves each query location with a stride given by the distance predicted by the network. Based on the sign of the distance, this may move the query location along or against the direction of the gradient of the SDF. This is a differentiable operation that allows us to update the signed distance value and the gradient simultaneously during training. Our outperforming results under widely used benchmarks demonstrate that we can learn SDFs more accurately and flexibly for surface reconstruction and single image reconstruction than the state-of-the-art methods. Our code and data are available at https://github.com/mabaorui/NeuralPull.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/ma21b.html
http://proceedings.mlr.press/v139/ma21b.htmlMeta-Cal: Well-controlled Post-hoc Calibration by RankingIn many applications, it is desirable that a classifier not only makes accurate predictions, but also outputs calibrated posterior probabilities. However, many existing classifiers, especially deep neural network classifiers, tend to be uncalibrated. Post-hoc calibration is a technique to recalibrate a model by learning a calibration map. Existing approaches mostly focus on constructing calibration maps with low calibration errors, however, this quality is inadequate for a calibrator being useful. In this paper, we introduce two constraints that are worth consideration in designing a calibration map for post-hoc calibration. Then we present Meta-Cal, which is built from a base calibrator and a ranking model. Under some mild assumptions, two high-probability bounds are given with respect to these constraints. Empirical results on CIFAR-10, CIFAR-100 and ImageNet and a range of popular network architectures show our proposed method significantly outperforms the current state of the art for post-hoc multi-class classification calibration.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/ma21a.html
http://proceedings.mlr.press/v139/ma21a.htmlValue Iteration in Continuous Actions, States and TimeClassical value iteration approaches are not applicable to environments with continuous states and actions. For such environments the states and actions must be discretized, which leads to an exponential increase in computational complexity. In this paper, we propose continuous fitted value iteration (cFVI). This algorithm enables dynamic programming for continuous states and actions with a known dynamics model. Exploiting the continuous time formulation, the optimal policy can be derived for non-linear control-affine dynamics. This closed-form solution enables the efficient extension of value iteration to continuous environments. We show in non-linear control experiments that the dynamic programming solution obtains the same quantitative performance as deep reinforcement learning methods in simulation but excels when transferred to the physical system.The policy obtained by cFVI is more robust to changes in the dynamics despite using only a deterministic model and without explicitly incorporating robustness in the optimizationThu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/lutter21a.html
http://proceedings.mlr.press/v139/lutter21a.htmlHyperHyperNetwork for the Design of Antenna ArraysWe present deep learning methods for the design of arrays and single instances of small antennas. Each design instance is conditioned on a target radiation pattern and is required to conform to specific spatial dimensions and to include, as part of its metallic structure, a set of predetermined locations. The solution, in the case of a single antenna, is based on a composite neural network that combines a simulation network, a hypernetwork, and a refinement network. In the design of the antenna array, we add an additional design level and employ a hypernetwork within a hypernetwork. The learning objective is based on measuring the similarity of the obtained radiation pattern to the desired one. Our experiments demonstrate that our approach is able to design novel antennas and antenna arrays that are compliant with the design requirements, considerably better than the baseline methods. We compare the solutions obtained by our method to existing designs and demonstrate a high level of overlap. When designing the antenna array of a cellular phone, the obtained solution displays improved properties over the existing one.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/lutati21a.html
http://proceedings.mlr.press/v139/lutati21a.htmlTrajectory Diversity for Zero-Shot CoordinationWe study the problem of zero-shot coordination (ZSC), where agents must independently produce strategies for a collaborative game that are compatible with novel partners not seen during training. Our first contribution is to consider the need for diversity in generating such agents. Because self-play (SP) agents control their own trajectory distribution during training, each policy typically only performs well on this exact distribution. As a result, they achieve low scores in ZSC, since playing with another agent is likely to put them in situations they have not encountered during training. To address this issue, we train a common best response (BR) to a population of agents, which we regulate to be diverse. To this end, we introduce \textit{Trajectory Diversity} (TrajeDi) – a differentiable objective for generating diverse reinforcement learning policies. We derive TrajeDi as a generalization of the Jensen-Shannon divergence between policies and motivate it experimentally in two simple settings. We then focus on the collaborative card game Hanabi, demonstrating the scalability of our method and improving upon the cross-play scores of both independently trained SP agents and BRs to unregularized populations.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/lupu21a.html
http://proceedings.mlr.press/v139/lupu21a.htmlGraphDF: A Discrete Flow Model for Molecular Graph GenerationWe consider the problem of molecular graph generation using deep models. While graphs are discrete, most existing methods use continuous latent variables, resulting in inaccurate modeling of discrete graph structures. In this work, we propose GraphDF, a novel discrete latent variable model for molecular graph generation based on normalizing flow methods. GraphDF uses invertible modulo shift transforms to map discrete latent variables to graph nodes and edges. We show that the use of discrete latent variables reduces computational costs and eliminates the negative effect of dequantization. Comprehensive experimental results show that GraphDF outperforms prior methods on random generation, property optimization, and constrained optimization tasks.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/luo21a.html
http://proceedings.mlr.press/v139/luo21a.htmlImproving Breadth-Wise Backpropagation in Graph Neural Networks Helps Learning Long-Range Dependencies.In this work, we focus on the ability of graph neural networks (GNNs) to learn long-range patterns in graphs with edge features. Learning patterns that involve longer paths in the graph, requires using deeper GNNs. However, GNNs suffer from a drop in performance with increasing network depth. To improve the performance of deeper GNNs, previous works have investigated normalization techniques and various types of skip connections. While they are designed to improve depth-wise backpropagation between the representations of the same node in successive layers, they do not improve breadth-wise backpropagation between representations of neighbouring nodes. To analyse the consequences, we design synthetic datasets serving as a testbed for the ability of GNNs to learn long-range patterns. Our analysis shows that several commonly used GNN variants with only depth-wise skip connections indeed have problems learning long-range patterns. They are clearly outperformed by an attention-based GNN architecture that we propose for improving both depth- and breadth-wise backpropagation. We also verify that the presented architecture is competitive on real-world data.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/lukovnikov21a.html
http://proceedings.mlr.press/v139/lukovnikov21a.htmlOn Monotonic Linear Interpolation of Neural Network ParametersLinear interpolation between initial neural network parameters and converged parameters after training with stochastic gradient descent (SGD) typically leads to a monotonic decrease in the training objective. This Monotonic Linear Interpolation (MLI) property, first observed by Goodfellow et al. 2014, persists in spite of the non-convex objectives and highly non-linear training dynamics of neural networks. Extending this work, we evaluate several hypotheses for this property that, to our knowledge, have not yet been explored. Using tools from differential geometry, we draw connections between the interpolated paths in function space and the monotonicity of the network — providing sufficient conditions for the MLI property under mean squared error. While the MLI property holds under various settings (e.g., network architectures and learning problems), we show in practice that networks violating the MLI property can be produced systematically, by encouraging the weights to move far from initialization. The MLI property raises important questions about the loss landscape geometry of neural networks and highlights the need to further study their global properties.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/lucas21a.html
http://proceedings.mlr.press/v139/lucas21a.htmlACE: Explaining cluster from an adversarial perspectiveA common workflow in single-cell RNA-seq analysis is to project the data to a latent space, cluster the cells in that space, and identify sets of marker genes that explain the differences among the discovered clusters. A primary drawback to this three-step procedure is that each step is carried out independently, thereby neglecting the effects of the nonlinear embedding and inter-gene dependencies on the selection of marker genes. Here we propose an integrated deep learning framework, Adversarial Clustering Explanation (ACE), that bundles all three steps into a single workflow. The method thus moves away from the notion of "marker genes" to instead identify a panel of explanatory genes. This panel may include genes that are not only enriched but also depleted relative to other cell types, as well as genes that exhibit differences between closely related cell types. Empirically, we demonstrate that ACE is able to identify gene panels that are both highly discriminative and nonredundant, and we demonstrate the applicability of ACE to an image recognition task.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/lu21e.html
http://proceedings.mlr.press/v139/lu21e.htmlVariance Reduced Training with Stratified Sampling for Forecasting ModelsIn large-scale time series forecasting, one often encounters the situation where the temporal patterns of time series, while drifting over time, differ from one another in the same dataset. In this paper, we provably show under such heterogeneity, training a forecasting model with commonly used stochastic optimizers (e.g. SGD) potentially suffers large variance on gradient estimation, and thus incurs long-time training. We show that this issue can be efficiently alleviated via stratification, which allows the optimizer to sample from pre-grouped time series strata. For better trading-off gradient variance and computation complexity, we further propose SCott (Stochastic Stratified Control Variate Gradient Descent), a variance reduced SGD-style optimizer that utilizes stratified sampling via control variate. In theory, we provide the convergence guarantee of SCott on smooth non-convex objectives. Empirically, we evaluate SCott and other baseline optimizers on both synthetic and real-world time series forecasting problems, and demonstrate SCott converges faster with respect to both iterations and wall clock time.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/lu21d.html
http://proceedings.mlr.press/v139/lu21d.htmlBinary Classification from Multiple Unlabeled Datasets via Surrogate Set ClassificationTo cope with high annotation costs, training a classifier only from weakly supervised data has attracted a great deal of attention these days. Among various approaches, strengthening supervision from completely unsupervised classification is a promising direction, which typically employs class priors as the only supervision and trains a binary classifier from unlabeled (U) datasets. While existing risk-consistent methods are theoretically grounded with high flexibility, they can learn only from two U sets. In this paper, we propose a new approach for binary classification from $m$ U-sets for $m\ge2$. Our key idea is to consider an auxiliary classification task called surrogate set classification (SSC), which is aimed at predicting from which U set each observed sample is drawn. SSC can be solved by a standard (multi-class) classification method, and we use the SSC solution to obtain the final binary classifier through a certain linear-fractional transformation. We built our method in a flexible and efficient end-to-end deep learning framework and prove it to be classifier-consistent. Through experiments, we demonstrate the superiority of our proposed method over state-of-the-art methods.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/lu21c.html
http://proceedings.mlr.press/v139/lu21c.htmlDANCE: Enhancing saliency maps using decoysSaliency methods can make deep neural network predictions more interpretable by identifying a set of critical features in an input sample, such as pixels that contribute most strongly to a prediction made by an image classifier. Unfortunately, recent evidence suggests that many saliency methods poorly perform, especially in situations where gradients are saturated, inputs contain adversarial perturbations, or predictions rely upon inter-feature dependence. To address these issues, we propose a framework, DANCE, which improves the robustness of saliency methods by following a two-step procedure. First, we introduce a perturbation mechanism that subtly varies the input sample without changing its intermediate representations. Using this approach, we can gather a corpus of perturbed ("decoy") data samples while ensuring that the perturbed and original input samples follow similar distributions. Second, we compute saliency maps for the decoy samples and propose a new method to aggregate saliency maps. With this design, we offset influence of gradient saturation. From a theoretical perspective, we show that the aggregated saliency map not only captures inter-feature dependence but, more importantly, is robust against previously described adversarial perturbation methods. Our empirical results suggest that, both qualitatively and quantitatively, DANCE outperforms existing methods in a variety of application domains.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/lu21b.html
http://proceedings.mlr.press/v139/lu21b.htmlOptimal Complexity in Decentralized TrainingDecentralization is a promising method of scaling up parallel machine learning systems. In this paper, we provide a tight lower bound on the iteration complexity for such methods in a stochastic non-convex setting. Our lower bound reveals a theoretical gap in known convergence rates of many existing decentralized training algorithms, such as D-PSGD. We prove by construction this lower bound is tight and achievable. Motivated by our insights, we further propose DeTAG, a practical gossip-style decentralized algorithm that achieves the lower bound with only a logarithm gap. Empirically, we compare DeTAG with other decentralized algorithms on image classification tasks, and we show DeTAG enjoys faster convergence compared to baselines, especially on unshuffled data and in sparse networks.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/lu21a.html
http://proceedings.mlr.press/v139/lu21a.htmlHEMET: A Homomorphic-Encryption-Friendly Privacy-Preserving Mobile Neural Network ArchitectureRecently Homomorphic Encryption (HE) is used to implement Privacy-Preserving Neural Networks (PPNNs) that perform inferences directly on encrypted data without decryption. Prior PPNNs adopt mobile network architectures such as SqueezeNet for smaller computing overhead, but we find naïvely using mobile network architectures for a PPNN does not necessarily achieve shorter inference latency. Despite having less parameters, a mobile network architecture typically introduces more layers and increases the HE multiplicative depth of a PPNN, thereby prolonging its inference latency. In this paper, we propose a \textbf{HE}-friendly privacy-preserving \textbf{M}obile neural n\textbf{ET}work architecture, \textbf{HEMET}. Experimental results show that, compared to state-of-the-art (SOTA) PPNNs, HEMET reduces the inference latency by $59.3%\sim 61.2%$, and improves the inference accuracy by $0.4 % \sim 0.5%$.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/lou21a.html
http://proceedings.mlr.press/v139/lou21a.htmlSymmetric Spaces for Graph Embeddings: A Finsler-Riemannian ApproachLearning faithful graph representations as sets of vertex embeddings has become a fundamental intermediary step in a wide range of machine learning applications. We propose the systematic use of symmetric spaces in representation learning, a class encompassing many of the previously used embedding targets. This enables us to introduce a new method, the use of Finsler metrics integrated in a Riemannian optimization scheme, that better adapts to dissimilar structures in the graph. We develop a tool to analyze the embeddings and infer structural properties of the data sets. For implementation, we choose Siegel spaces, a versatile family of symmetric spaces. Our approach outperforms competitive baselines for graph reconstruction tasks on various synthetic and real-world datasets. We further demonstrate its applicability on two downstream tasks, recommender systems and node classification.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/lopez21a.html
http://proceedings.mlr.press/v139/lopez21a.htmlJoint Online Learning and Decision-making via Dual Mirror DescentWe consider an online revenue maximization problem over a finite time horizon subject to lower and upper bounds on cost. At each period, an agent receives a context vector sampled i.i.d. from an unknown distribution and needs to make a decision adaptively. The revenue and cost functions depend on the context vector as well as some fixed but possibly unknown parameter vector to be learned. We propose a novel offline benchmark and a new algorithm that mixes an online dual mirror descent scheme with a generic parameter learning process. When the parameter vector is known, we demonstrate an $O(\sqrt{T})$ regret result as well an $O(\sqrt{T})$ bound on the possible constraint violations. When the parameter is not known and must be learned, we demonstrate that the regret and constraint violations are the sums of the previous $O(\sqrt{T})$ terms plus terms that directly depend on the convergence of the learning process.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/lobos21a.html
http://proceedings.mlr.press/v139/lobos21a.htmlRelative Positional Encoding for Transformers with Linear ComplexityRecent advances in Transformer models allow for unprecedented sequence lengths, due to linear space and time complexity. In the meantime, relative positional encoding (RPE) was proposed as beneficial for classical Transformers and consists in exploiting lags instead of absolute positions for inference. Still, RPE is not available for the recent linear-variants of the Transformer, because it requires the explicit computation of the attention matrix, which is precisely what is avoided by such methods. In this paper, we bridge this gap and present Stochastic Positional Encoding as a way to generate PE that can be used as a replacement to the classical additive (sinusoidal) PE and provably behaves like RPE. The main theoretical contribution is to make a connection between positional encoding and cross-covariance structures of correlated Gaussian processes. We illustrate the performance of our approach on the Long-Range Arena benchmark and on music generation.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/liutkus21a.html
http://proceedings.mlr.press/v139/liutkus21a.htmlA Sharp Analysis of Model-based Reinforcement Learning with Self-PlayModel-based algorithms—algorithms that explore the environment through building and utilizing an estimated model—are widely used in reinforcement learning practice and theoretically shown to achieve optimal sample efficiency for single-agent reinforcement learning in Markov Decision Processes (MDPs). However, for multi-agent reinforcement learning in Markov games, the current best known sample complexity for model-based algorithms is rather suboptimal and compares unfavorably against recent model-free approaches. In this paper, we present a sharp analysis of model-based self-play algorithms for multi-agent Markov games. We design an algorithm \emph{Optimistic Nash Value Iteration} (Nash-VI) for two-player zero-sum Markov games that is able to output an $\epsilon$-approximate Nash policy in $\tilde{\mathcal{O}}(H^3SAB/\epsilon^2)$ episodes of game playing, where $S$ is the number of states, $A,B$ are the number of actions for the two players respectively, and $H$ is the horizon length. This significantly improves over the best known model-based guarantee of $\tilde{\mathcal{O}}(H^4S^2AB/\epsilon^2)$, and is the first that matches the information-theoretic lower bound $\Omega(H^3S(A+B)/\epsilon^2)$ except for a $\min\{A,B\}$ factor. In addition, our guarantee compares favorably against the best known model-free algorithm if $\min\{A,B\}=o(H^3)$, and outputs a single Markov policy while existing sample-efficient model-free algorithms output a nested mixture of Markov policies that is in general non-Markov and rather inconvenient to store and execute. We further adapt our analysis to designing a provably efficient task-agnostic algorithm for zero-sum Markov games, and designing the first line of provably sample-efficient algorithms for multi-player general-sum Markov games.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/liu21z.html
http://proceedings.mlr.press/v139/liu21z.htmlDo We Actually Need Dense Over-Parameterization? In-Time Over-Parameterization in Sparse TrainingIn this paper, we introduce a new perspective on training deep neural networks capable of state-of-the-art performance without the need for the expensive over-parameterization by proposing the concept of In-Time Over-Parameterization (ITOP) in sparse training. By starting from a random sparse network and continuously exploring sparse connectivities during training, we can perform an Over-Parameterization over the course of training, closing the gap in the expressibility between sparse training and dense training. We further use ITOP to understand the underlying mechanism of Dynamic Sparse Training (DST) and discover that the benefits of DST come from its ability to consider across time all possible parameters when searching for the optimal sparse connectivity. As long as sufficient parameters have been reliably explored, DST can outperform the dense neural network by a large margin. We present a series of experiments to support our conjecture and achieve the state-of-the-art sparse training performance with ResNet-50 on ImageNet. More impressively, ITOP achieves dominant performance over the overparameterization-based sparse methods at extreme sparsities. When trained with ResNet-34 on CIFAR-100, ITOP can match the performance of the dense model at an extreme sparsity 98%.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/liu21y.html
http://proceedings.mlr.press/v139/liu21y.htmlWatermarking Deep Neural Networks with Greedy ResidualsDeep neural networks (DNNs) are considered as intellectual property of their corresponding owners and thus are in urgent need of ownership protection, due to the massive amount of time and resources invested in designing, tuning and training them. In this paper, we propose a novel watermark-based ownership protection method by using the residuals of important parameters. Different from other watermark-based ownership protection methods that rely on some specific neural network architectures and during verification require external data source, namely ownership indicators, our method does not explicitly use ownership indicators for verification to defeat various attacks against DNN watermarks. Specifically, we greedily select a few and important model parameters for embedding so that the impairment caused by the changed parameters can be reduced and the robustness against different attacks can be improved as the selected parameters can well preserve the model information. Also, without the external data sources for verification, the adversary can hardly cast doubts on ownership verification by forging counterfeit watermarks. The extensive experiments show that our method outperforms previous state-of-the-art methods in five tasks.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/liu21x.html
http://proceedings.mlr.press/v139/liu21x.htmlLeveraging Public Data for Practical Private Query ReleaseIn many statistical problems, incorporating priors can significantly improve performance. However, the use of prior knowledge in differentially private query release has remained underexplored, despite such priors commonly being available in the form of public datasets, such as previous US Census releases. With the goal of releasing statistics about a private dataset, we present PMW^Pub, which—unlike existing baselines—leverages public data drawn from a related distribution as prior information. We provide a theoretical analysis and an empirical evaluation on the American Community Survey (ACS) and ADULT datasets, which shows that our method outperforms state-of-the-art methods. Furthermore, PMW^Pub scales well to high-dimensional data domains, where running many existing methods would be computationally infeasible.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/liu21w.html
http://proceedings.mlr.press/v139/liu21w.htmlLearning Deep Neural Networks under Agnostic Corrupted SupervisionTraining deep neural network models in the presence of corrupted supervision is challenging as the corrupted data points may significantly impact generalization performance. To alleviate this problem, we present an efficient robust algorithm that achieves strong guarantees without any assumption on the type of corruption and provides a unified framework for both classification and regression problems. Unlike many existing approaches that quantify the quality of the data points (e.g., based on their individual loss values), and filter them accordingly, the proposed algorithm focuses on controlling the collective impact of data points on the average gradient. Even when a corrupted data point failed to be excluded by our algorithm, the data point will have a very limited impact on the overall loss, as compared with state-of-the-art filtering methods based on loss values. Extensive experiments on multiple benchmark datasets have demonstrated the robustness of our algorithm under different types of corruption. Our code is available at \url{https://github.com/illidanlab/PRL}.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/liu21v.html
http://proceedings.mlr.press/v139/liu21v.htmlSagaNet: A Small Sample Gated Network for Pediatric Cancer DiagnosisThe scarcity of available samples and the high annotation cost of medical data cause a bottleneck in many digital diagnosis tasks based on deep learning. This problem is especially severe in pediatric tumor tasks, due to the small population base of children and high sample diversity caused by the high metastasis rate of related tumors. Targeted research on pediatric tumors is urgently needed but lacks sufficient attention. In this work, we propose a novel model to solve the diagnosis task of small round blue cell tumors (SRBCTs). To solve the problem of high noise and high diversity in the small sample scenario, the model is constrained to pay attention to the valid areas in the pathological image with a masking mechanism, and a length-aware loss is proposed to improve the tolerance to feature diversity. We evaluate this framework on a challenging small sample SRBCTs dataset, whose classification is difficult even for professional pathologists. The proposed model shows the best performance compared with state-of-the-art deep models and generalization on another pathological dataset, which illustrates the potentiality of deep learning applications in difficult small sample medical tasks.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/liu21u.html
http://proceedings.mlr.press/v139/liu21u.htmlHow Do Adam and Training Strategies Help BNNs OptimizationThe best performing Binary Neural Networks (BNNs) are usually attained using Adam optimization and its multi-step training variants. However, to the best of our knowledge, few studies explore the fundamental reasons why Adam is superior to other optimizers like SGD for BNN optimization or provide analytical explanations that support specific training strategies. To address this, in this paper we first investigate the trajectories of gradients and weights in BNNs during the training process. We show the regularization effect of second-order momentum in Adam is crucial to revitalize the weights that are dead due to the activation saturation in BNNs. We find that Adam, through its adaptive learning rate strategy, is better equipped to handle the rugged loss surface of BNNs and reaches a better optimum with higher generalization ability. Furthermore, we inspect the intriguing role of the real-valued weights in binary networks, and reveal the effect of weight decay on the stability and sluggishness of BNN optimization. Through extensive experiments and analysis, we derive a simple training scheme, building on existing Adam-based optimization, which achieves 70.5% top-1 accuracy on the ImageNet dataset using the same architecture as the state-of-the-art ReActNet while achieving 1.1% higher accuracy. Code and models are available at https://github.com/liuzechun/AdamBNN.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/liu21t.html
http://proceedings.mlr.press/v139/liu21t.htmlDecoupling Exploration and Exploitation for Meta-Reinforcement Learning without SacrificesThe goal of meta-reinforcement learning (meta-RL) is to build agents that can quickly learn new tasks by leveraging prior experience on related tasks. Learning a new task often requires both exploring to gather task-relevant information and exploiting this information to solve the task. In principle, optimal exploration and exploitation can be learned end-to-end by simply maximizing task performance. However, such meta-RL approaches struggle with local optima due to a chicken-and-egg problem: learning to explore requires good exploitation to gauge the exploration’s utility, but learning to exploit requires information gathered via exploration. Optimizing separate objectives for exploration and exploitation can avoid this problem, but prior meta-RL exploration objectives yield suboptimal policies that gather information irrelevant to the task. We alleviate both concerns by constructing an exploitation objective that automatically identifies task-relevant information and an exploration objective to recover only this information. This avoids local optima in end-to-end training, without sacrificing optimal exploration. Empirically, DREAM substantially outperforms existing approaches on complex meta-RL problems, such as sparse-reward 3D visual navigation. Videos of DREAM: https://ezliu.github.io/dream/Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/liu21s.html
http://proceedings.mlr.press/v139/liu21s.htmlOn Robust Mean Estimation under Coordinate-level CorruptionWe study the problem of robust mean estimation and introduce a novel Hamming distance-based measure of distribution shift for coordinate-level corruptions. We show that this measure yields adversary models that capture more realistic corruptions than those used in prior works, and present an information-theoretic analysis of robust mean estimation in these settings. We show that for structured distributions, methods that leverage the structure yield information theoretically more accurate mean estimation. We also focus on practical algorithms for robust mean estimation and study when data cleaning-inspired approaches that first fix corruptions in the input data and then perform robust mean estimation can match the information theoretic bounds of our analysis. We finally demonstrate experimentally that this two-step approach outperforms structure-agnostic robust estimation and provides accurate mean estimation even for high-magnitude corruption.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/liu21r.html
http://proceedings.mlr.press/v139/liu21r.htmlTemporal Difference Learning as Gradient SplittingTemporal difference learning with linear function approximation is a popular method to obtain a low-dimensional approximation of the value function of a policy in a Markov Decision Process. We provide an interpretation of this method in terms of a splitting of the gradient of an appropriately chosen function. As a consequence of this interpretation, convergence proofs for gradient descent can be applied almost verbatim to temporal difference learning. Beyond giving a fuller explanation of why temporal difference works, this interpretation also yields improved convergence times. We consider the setting with $1/\sqrt{T}$ step-size, where previous comparable finite-time convergence time bounds for temporal difference learning had the multiplicative factor $1/(1-\gamma)$ in front of the bound, with $\gamma$ being the discount factor. We show that a minor variation on TD learning which estimates the mean of the value function separately has a convergence time where $1/(1-\gamma)$ only multiplies an asymptotically negligible term.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/liu21q.html
http://proceedings.mlr.press/v139/liu21q.htmlSelfish Sparse RNN TrainingSparse neural networks have been widely applied to reduce the computational demands of training and deploying over-parameterized deep neural networks. For inference acceleration, methods that discover a sparse network from a pre-trained dense network (dense-to-sparse training) work effectively. Recently, dynamic sparse training (DST) has been proposed to train sparse neural networks without pre-training a dense model (sparse-to-sparse training), so that the training process can also be accelerated. However, previous sparse-to-sparse methods mainly focus on Multilayer Perceptron Networks (MLPs) and Convolutional Neural Networks (CNNs), failing to match the performance of dense-to-sparse methods in the Recurrent Neural Networks (RNNs) setting. In this paper, we propose an approach to train intrinsically sparse RNNs with a fixed parameter count in one single run, without compromising performance. During training, we allow RNN layers to have a non-uniform redistribution across cell gates for better regularization. Further, we propose SNT-ASGD, a novel variant of the averaged stochastic gradient optimizer, which significantly improves the performance of all sparse training methods for RNNs. Using these strategies, we achieve state-of-the-art sparse training results, better than the dense-to-sparse methods, with various types of RNNs on Penn TreeBank and Wikitext-2 datasets. Our codes are available at https://github.com/Shiweiliuiiiiiii/Selfish-RNN.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/liu21p.html
http://proceedings.mlr.press/v139/liu21p.htmlA Value-Function-based Interior-point Method for Non-convex Bi-level OptimizationBi-level optimization model is able to capture a wide range of complex learning tasks with practical interest. Due to the witnessed efficiency in solving bi-level programs, gradient-based methods have gained popularity in the machine learning community. In this work, we propose a new gradient-based solution scheme, namely, the Bi-level Value-Function-based Interior-point Method (BVFIM). Following the main idea of the log-barrier interior-point scheme, we penalize the regularized value function of the lower level problem into the upper level objective. By further solving a sequence of differentiable unconstrained approximation problems, we consequently derive a sequential programming scheme. The numerical advantage of our scheme relies on the fact that, when gradient methods are applied to solve the approximation problem, we successfully avoid computing any expensive Hessian-vector or Jacobian-vector product. We prove the convergence without requiring any convexity assumption on either the upper level or the lower level objective. Experiments demonstrate the efficiency of the proposed BVFIM on non-convex bi-level problems.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/liu21o.html
http://proceedings.mlr.press/v139/liu21o.htmlFrom Local to Global Norm Emergence: Dissolving Self-reinforcing Substructures with Incremental Social InstrumentsNorm emergence is a process where agents in a multi-agent system establish self-enforcing conformity through repeated interactions. When such interactions are confined to a social topology, several self-reinforcing substructures (SRS) may emerge within the population. This prevents a formation of a global norm. We propose incremental social instruments (ISI) to dissolve these SRSs by creating ties between agents. Establishing ties requires some effort and cost. Hence, it is worth to design methods that build a small number of ties yet dissolve the SRSs. By using the notion of information entropy, we propose an indicator called the BA-ratio that measures the current SRSs. We find that by building ties with minimal BA-ratio, our ISI is effective in facilitating the global norm emergence. We explain this through our experiments and theoretical results. Furthermore, we propose the small-degree principle in minimising the BA-ratio that helps us to design efficient ISI algorithms for finding the optimal ties. Experiments on both synthetic and real-world network topologies demonstrate that our adaptive ISI is efficient at dissolving SRS.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/liu21n.html
http://proceedings.mlr.press/v139/liu21n.htmlCoach-Player Multi-agent Reinforcement Learning for Dynamic Team CompositionIn real-world multi-agent systems, agents with different capabilities may join or leave without altering the team’s overarching goals. Coordinating teams with such dynamic composition is challenging: the optimal team strategy varies with the composition. We propose COPA, a coach-player framework to tackle this problem. We assume the coach has a global view of the environment and coordinates the players, who only have partial views, by distributing individual strategies. Specifically, we 1) adopt the attention mechanism for both the coach and the players; 2) propose a variational objective to regularize learning; and 3) design an adaptive communication method to let the coach decide when to communicate with the players. We validate our methods on a resource collection task, a rescue game, and the StarCraft micromanagement tasks. We demonstrate zero-shot generalization to new team compositions. Our method achieves comparable or better performance than the setting where all players have a full view of the environment. Moreover, we see that the performance remains high even when the coach communicates as little as 13% of the time using the adaptive communication strategy.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/liu21m.html
http://proceedings.mlr.press/v139/liu21m.htmlOne Pass Late Fusion Multi-view ClusteringExisting late fusion multi-view clustering (LFMVC) optimally integrates a group of pre-specified base partition matrices to learn a consensus one. It is then taken as the input of the widely used k-means to generate the cluster labels. As observed, the learning of the consensus partition matrix and the generation of cluster labels are separately done. These two procedures lack necessary negotiation and can not best serve for each other, which may adversely affect the clustering performance. To address this issue, we propose to unify the aforementioned two learning procedures into a single optimization, in which the consensus partition matrix can better serve for the generation of cluster labels, and the latter is able to guide the learning of the former. To optimize the resultant optimization problem, we develop a four-step alternate algorithm with proved convergence. We theoretically analyze the clustering generalization error of the proposed algorithm on unseen data. Comprehensive experiments on multiple benchmark datasets demonstrate the superiority of our algorithm in terms of both clustering accuracy and computational efficiency. It is expected that the simplicity and effectiveness of our algorithm will make it a good option to be considered for practical multi-view clustering applications.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/liu21l.html
http://proceedings.mlr.press/v139/liu21l.htmlElastic Graph Neural NetworksWhile many existing graph neural networks (GNNs) have been proven to perform $\ell_2$-based graph smoothing that enforces smoothness globally, in this work we aim to further enhance the local smoothness adaptivity of GNNs via $\ell_1$-based graph smoothing. As a result, we introduce a family of GNNs (Elastic GNNs) based on $\ell_1$ and $\ell_2$-based graph smoothing. In particular, we propose a novel and general message passing scheme into GNNs. This message passing algorithm is not only friendly to back-propagation training but also achieves the desired smoothing properties with a theoretical convergence guarantee. Experiments on semi-supervised learning tasks demonstrate that the proposed Elastic GNNs obtain better adaptivity on benchmark datasets and are significantly robust to graph adversarial attacks. The implementation of Elastic GNNs is available at \url{https://github.com/lxiaorui/ElasticGNN}.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/liu21k.html
http://proceedings.mlr.press/v139/liu21k.htmlCooperative Exploration for Multi-Agent Deep Reinforcement LearningExploration is critical for good results in deep reinforcement learning and has attracted much attention. However, existing multi-agent deep reinforcement learning algorithms still use mostly noise-based techniques. Very recently, exploration methods that consider cooperation among multiple agents have been developed. However, existing methods suffer from a common challenge: agents struggle to identify states that are worth exploring, and hardly coordinate exploration efforts toward those states. To address this shortcoming, in this paper, we propose cooperative multi-agent exploration (CMAE): agents share a common goal while exploring. The goal is selected from multiple projected state spaces by a normalized entropy-based technique. Then, agents are trained to reach the goal in a coordinated manner. We demonstrate that CMAE consistently outperforms baselines on various tasks, including a sparse-reward version of multiple-particle environment (MPE) and the Starcraft multi-agent challenge (SMAC).Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/liu21j.html
http://proceedings.mlr.press/v139/liu21j.htmlStochastic Iterative Graph MatchingRecent works apply Graph Neural Networks (GNNs) to graph matching tasks and show promising results. Considering that model outputs are complex matchings, we devise several techniques to improve the learning of GNNs and obtain a new model, Stochastic Iterative Graph MAtching (SIGMA). Our model predicts a distribution of matchings, instead of a single matching, for a graph pair so the model can explore several probable matchings. We further introduce a novel multi-step matching procedure, which learns how to refine a graph pair’s matching results incrementally. The model also includes dummy nodes so that the model does not have to find matchings for nodes without correspondence. We fit this model to data via scalable stochastic optimization. We conduct extensive experiments across synthetic graph datasets as well as biochemistry and computer vision applications. Across all tasks, our results show that SIGMA can produce significantly improved graph matching results compared to state-of-the-art models. Ablation studies verify that each of our components (stochastic training, iterative matching, and dummy nodes) offers noticeable improvement.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/liu21i.html
http://proceedings.mlr.press/v139/liu21i.htmlHeterogeneous Risk MinimizationMachine learning algorithms with empirical risk minimization usually suffer from poor generalization performance due to the greedy exploitation of correlations among the training data, which are not stable under distributional shifts. Recently, some invariant learning methods for out-of-distribution (OOD) generalization have been proposed by leveraging multiple training environments to find invariant relationships. However, modern datasets are frequently assembled by merging data from multiple sources without explicit source labels. The resultant unobserved heterogeneity renders many invariant learning methods inapplicable. In this paper, we propose Heterogeneous Risk Minimization (HRM) framework to achieve joint learning of latent heterogeneity among the data and invariant relationship, which leads to stable prediction despite distributional shifts. We theoretically characterize the roles of the environment labels in invariant learning and justify our newly proposed HRM framework. Extensive experimental results validate the effectiveness of our HRM framework.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/liu21h.html
http://proceedings.mlr.press/v139/liu21h.htmlEvent Outlier Detection in Continuous TimeContinuous-time event sequences represent discrete events occurring in continuous time. Such sequences arise frequently in real-life. Usually we expect the sequences to follow some regular pattern over time. However, sometimes these patterns may be interrupted by unexpected absence or occurrences of events. Identification of these unexpected cases can be very important as they may point to abnormal situations that need human attention. In this work, we study and develop methods for detecting outliers in continuous-time event sequences, including unexpected absence and unexpected occurrences of events. Since the patterns that event sequences tend to follow may change in different contexts, we develop outlier detection methods based on point processes that can take context information into account. Our methods are based on Bayesian decision theory and hypothesis testing with theoretical guarantees. To test the performance of the methods, we conduct experiments on both synthetic data and real-world clinical data and show the effectiveness of the proposed methods.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/liu21g.html
http://proceedings.mlr.press/v139/liu21g.htmlJust Train Twice: Improving Group Robustness without Training Group InformationStandard training via empirical risk minimization (ERM) can produce models that achieve low error on average but high error on minority groups, especially in the presence of spurious correlations between the input and label. Prior approaches to this problem, like group distributionally robust optimization (group DRO), generally require group annotations for every training point. On the other hand, approaches that do not use group annotations generally do not improve minority performance. For example, we find that joint DRO, which dynamically upweights examples with high training loss, tends to optimize for examples that are irrelevant to the specific groups we seek to do well on. In this paper, we propose a simple two-stage approach, JTT, that achieves comparable performance to group DRO while only requiring group annotations on a significantly smaller validation set. JTT first attempts to identify informative training examples, which are often minority examples, by training an initial ERM classifier and selecting the examples with high training loss. Then, it trains a final classifier by upsampling the selected examples. Crucially, unlike joint DRO, JTT does not iteratively upsample examples that have high loss under the final classifier. On four image classification and natural language processing tasks with spurious correlations, we show that JTT closes 85% of the gap in accuracy on the worst group between ERM and group DRO.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/liu21f.html
http://proceedings.mlr.press/v139/liu21f.htmlBesov Function Approximation and Binary Classification on Low-Dimensional Manifolds Using Convolutional Residual NetworksMost of existing statistical theories on deep neural networks have sample complexities cursed by the data dimension and therefore cannot well explain the empirical success of deep learning on high-dimensional data. To bridge this gap, we propose to exploit the low-dimensional structures of the real world datasets and establish theoretical guarantees of convolutional residual networks (ConvResNet) in terms of function approximation and statistical recovery for binary classification problem. Specifically, given the data lying on a $d$-dimensional manifold isometrically embedded in $\mathbb{R}^D$, we prove that if the network architecture is properly chosen, ConvResNets can (1) approximate {\it Besov functions} on manifolds with arbitrary accuracy, and (2) learn a classifier by minimizing the empirical logistic risk, which gives an {\it excess risk} in the order of $n^{-\frac{s}{2s+2(s\vee d)}}$, where $s$ is a smoothness parameter. This implies that the sample complexity depends on the intrinsic dimension $d$, instead of the data dimension $D$. Our results demonstrate that ConvResNets are adaptive to low-dimensional structures of data sets.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/liu21e.html
http://proceedings.mlr.press/v139/liu21e.htmlDynamic Game Theoretic Neural OptimizerThe connection between training deep neural networks (DNNs) and optimal control theory (OCT) has attracted considerable attention as a principled tool of algorithmic design. Despite few attempts being made, they have been limited to architectures where the layer propagation resembles a Markovian dynamical system. This casts doubts on their flexibility to modern networks that heavily rely on non-Markovian dependencies between layers (e.g. skip connections in residual networks). In this work, we propose a novel dynamic game perspective by viewing each layer as a player in a dynamic game characterized by the DNN itself. Through this lens, different classes of optimizers can be seen as matching different types of Nash equilibria, depending on the implicit information structure of each (p)layer. The resulting method, called Dynamic Game Theoretic Neural Optimizer (DGNOpt), not only generalizes OCT-inspired optimizers to richer network class; it also motivates a new training principle by solving a multi-player cooperative game. DGNOpt shows convergence improvements over existing methods on image classification datasets with residual and inception networks. Our work marries strengths from both OCT and game theory, paving ways to new algorithmic opportunities from robust optimal control and bandit-based optimization.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/liu21d.html
http://proceedings.mlr.press/v139/liu21d.htmlLearning by Turning: Neural Architecture Aware OptimisationDescent methods for deep networks are notoriously capricious: they require careful tuning of step size, momentum and weight decay, and which method will work best on a new benchmark is a priori unclear. To address this problem, this paper conducts a combined study of neural architecture and optimisation, leading to a new optimiser called Nero: the neuronal rotator. Nero trains reliably without momentum or weight decay, works in situations where Adam and SGD fail, and requires little to no learning rate tuning. Also, Nero’s memory footprint is square root that of Adam or LAMB. Nero combines two ideas: (1) projected gradient descent over the space of balanced networks; (2) neuron-specific updates, where the step size sets the angle through which each neuron’s hyperplane turns. The paper concludes by discussing how this geometric connection between architecture and optimisation may impact theories of generalisation in deep learning.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/liu21c.html
http://proceedings.mlr.press/v139/liu21c.htmlAPS: Active Pretraining with Successor FeaturesWe introduce a new unsupervised pretraining objective for reinforcement learning. During the unsupervised reward-free pretraining phase, the agent maximizes mutual information between tasks and states induced by the policy. Our key contribution is a novel lower bound of this intractable quantity. We show that by reinterpreting and combining variational successor features \citep{Hansen2020Fast} with nonparametric entropy maximization \citep{liu2021behavior}, the intractable mutual information can be efficiently optimized. The proposed method Active Pretraining with Successor Feature (APS) explores the environment via nonparametric entropy maximization, and the explored data can be efficiently leveraged to learn behavior by variational successor features. APS addresses the limitations of existing mutual information maximization based and entropy maximization based unsupervised RL, and combines the best of both worlds. When evaluated on the Atari 100k data-efficiency benchmark, our approach significantly outperforms previous methods combining unsupervised pretraining with task-specific finetuning.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/liu21b.html
http://proceedings.mlr.press/v139/liu21b.htmlMulti-layered Network Exploration via Random Walks: From Offline Optimization to Online LearningMulti-layered network exploration (MuLaNE) problem is an important problem abstracted from many applications. In MuLaNE, there are multiple network layers where each node has an importance weight and each layer is explored by a random walk. The MuLaNE task is to allocate total random walk budget $B$ into each network layer so that the total weights of the unique nodes visited by random walks are maximized. We systematically study this problem from offline optimization to online learning. For the offline optimization setting where the network structure and node weights are known, we provide greedy based constant-ratio approximation algorithms for overlapping networks, and greedy or dynamic-programming based optimal solutions for non-overlapping networks. For the online learning setting, neither the network structure nor the node weights are known initially. We adapt the combinatorial multi-armed bandit framework and design algorithms to learn random walk related parameters and node weights while optimizing the budget allocation in multiple rounds, and prove that they achieve logarithmic regret bounds. Finally, we conduct experiments on a real-world social network dataset to validate our theoretical results.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/liu21ae.html
http://proceedings.mlr.press/v139/liu21ae.htmlNoise and Fluctuation of Finite Learning Rate Stochastic Gradient DescentIn the vanishing learning rate regime, stochastic gradient descent (SGD) is now relatively well understood. In this work, we propose to study the basic properties of SGD and its variants in the non-vanishing learning rate regime. The focus is on deriving exactly solvable results and discussing their implications. The main contributions of this work are to derive the stationary distribution for discrete-time SGD in a quadratic loss function with and without momentum; in particular, one implication of our result is that the fluctuation caused by discrete-time dynamics takes a distorted shape and is dramatically larger than a continuous-time theory could predict. Examples of applications of the proposed theory considered in this work include the approximation error of variants of SGD, the effect of minibatch noise, the optimal Bayesian inference, the escape rate from a sharp minimum, and the stationary covariance of a few second-order methods including damped Newton’s method, natural gradient descent, and Adam.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/liu21ad.html
http://proceedings.mlr.press/v139/liu21ad.htmlInfinite-Dimensional Optimization for Zero-Sum Games via Variational TransportGame optimization has been extensively studied when decision variables lie in a finite-dimensional space, of which solutions correspond to pure strategies at the Nash equilibrium (NE), and the gradient descent-ascent (GDA) method works widely in practice. In this paper, we consider infinite-dimensional zero-sum games by a min-max distributional optimization problem over a space of probability measures defined on a continuous variable set, which is inspired by finding a mixed NE for finite-dimensional zero-sum games. We then aim to answer the following question: \textit{Will GDA-type algorithms still be provably efficient when extended to infinite-dimensional zero-sum games?} To answer this question, we propose a particle-based variational transport algorithm based on GDA in the functional spaces. Specifically, the algorithm performs multi-step functional gradient descent-ascent in the Wasserstein space via pushing two sets of particles in the variable space. By characterizing the gradient estimation error from variational form maximization and the convergence behavior of each player with different objective landscapes, we prove rigorously that the generalized GDA algorithm converges to the NE or the value of the game efficiently for a class of games under the Polyak-Ł{ojasiewicz} (PL) condition. To conclude, we provide complete statistical and convergence guarantees for solving an infinite-dimensional zero-sum game via a provably efficient particle-based method. Additionally, our work provides the first thorough statistical analysis for the particle-based algorithm to learn an objective functional with a variational form using universal approximators (\textit{i.e.}, neural networks (NNs)), which is of independent interest.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/liu21ac.html
http://proceedings.mlr.press/v139/liu21ac.htmlGroup Fisher Pruning for Practical Network CompressionNetwork compression has been widely studied since it is able to reduce the memory and computation cost during inference. However, previous methods seldom deal with complicated structures like residual connections, group/depth-wise convolution and feature pyramid network, where channels of multiple layers are coupled and need to be pruned simultaneously. In this paper, we present a general channel pruning approach that can be applied to various complicated structures. Particularly, we propose a layer grouping algorithm to find coupled channels automatically. Then we derive a unified metric based on Fisher information to evaluate the importance of a single channel and coupled channels. Moreover, we find that inference speedup on GPUs is more correlated with the reduction of memory rather than FLOPs, and thus we employ the memory reduction of each channel to normalize the importance. Our method can be used to prune any structures including those with coupled channels. We conduct extensive experiments on various backbones, including the classic ResNet and ResNeXt, mobile-friendly MobileNetV2, and the NAS-based RegNet, both on image classification and object detection which is under-explored. Experimental results validate that our method can effectively prune sophisticated networks, boosting inference speed without sacrificing accuracy.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/liu21ab.html
http://proceedings.mlr.press/v139/liu21ab.htmlLottery Ticket Preserves Weight Correlation: Is It Desirable or Not?In deep model compression, the recent finding "Lottery Ticket Hypothesis" (LTH) pointed out that there could exist a winning ticket (i.e., a properly pruned sub-network together with original weight initialization) that can achieve competitive performance than the original dense network. However, it is not easy to observe such winning property in many scenarios, where for example, a relatively large learning rate is used even if it benefits training the original dense model. In this work, we investigate the underlying condition and rationale behind the winning property, and find that the underlying reason is largely attributed to the correlation between initialized weights and final-trained weights when the learning rate is not sufficiently large. Thus, the existence of winning property is correlated with an insufficient DNN pretraining, and is unlikely to occur for a well-trained DNN. To overcome this limitation, we propose the "pruning & fine-tuning" method that consistently outperforms lottery ticket sparse training under the same pruning algorithm and the same total training epochs. Extensive experiments over multiple deep models (VGG, ResNet, MobileNet-v2) on different datasets have been conducted to justify our proposals.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/liu21aa.html
http://proceedings.mlr.press/v139/liu21aa.htmlUnderstanding Instance-Level Label Noise: Disparate Impacts and TreatmentsThis paper aims to provide understandings for the effect of an over-parameterized model, e.g. a deep neural network, memorizing instance-dependent noisy labels. We first quantify the harms caused by memorizing noisy instances, and show the disparate impacts of noisy labels for sample instances with different representation frequencies. We then analyze how several popular solutions for learning with noisy labels mitigate this harm at the instance level. Our analysis reveals that existing approaches lead to disparate treatments when handling noisy instances. While higher-frequency instances often enjoy a high probability of an improvement by applying these solutions, lower-frequency instances do not. Our analysis reveals new understandings for when these approaches work, and provides theoretical justifications for previously reported empirical observations. This observation requires us to rethink the distribution of label noise across instances and calls for different treatments for instances in different regimes.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/liu21a.html
http://proceedings.mlr.press/v139/liu21a.htmlThe Earth Mover’s Pinball Loss: Quantiles for Histogram-Valued RegressionAlthough ubiquitous in the sciences, histogram data have not received much attention by the Deep Learning community. Whilst regression and classification tasks for scalar and vector data are routinely solved by neural networks, a principled approach for estimating histogram labels as a function of an input vector or image is lacking in the literature. We present a dedicated method for Deep Learning-based histogram regression, which incorporates cross-bin information and yields distributions over possible histograms, expressed by $\tau$-quantiles of the cumulative histogram in each bin. The crux of our approach is a new loss function obtained by applying the pinball loss to the cumulative histogram, which for 1D histograms reduces to the Earth Mover’s distance (EMD) in the special case of the median ($\tau = 0.5$), and generalizes it to arbitrary quantiles. We validate our method with an illustrative toy example, a football-related task, and an astrophysical computer vision problem. We show that with our loss function, the accuracy of the predicted median histograms is very similar to the standard EMD case (and higher than for per-bin loss functions such as cross-entropy), while the predictions become much more informative at almost no additional computational cost.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/list21a.html
http://proceedings.mlr.press/v139/list21a.htmlPhase Transitions, Distance Functions, and Implicit Neural RepresentationsRepresenting surfaces as zero level sets of neural networks recently emerged as a powerful modeling paradigm, named Implicit Neural Representations (INRs), serving numerous downstream applications in geometric deep learning and 3D vision. Training INRs previously required choosing between occupancy and distance function representation and different losses with unknown limit behavior and/or bias. In this paper we draw inspiration from the theory of phase transitions of fluids and suggest a loss for training INRs that learns a density function that converges to a proper occupancy function, while its log transform converges to a distance function. Furthermore, we analyze the limit minimizer of this loss showing it satisfies the reconstruction constraints and has minimal surface perimeter, a desirable inductive bias for surface reconstruction. Training INRs with this new loss leads to state-of-the-art reconstructions on a standard benchmark.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/lipman21a.html
http://proceedings.mlr.press/v139/lipman21a.htmlActive Learning of Continuous-time Bayesian Networks through InterventionsWe consider the problem of learning structures and parameters of Continuous-time Bayesian Networks (CTBNs) from time-course data under minimal experimental resources. In practice, the cost of generating experimental data poses a bottleneck, especially in the natural and social sciences. A popular approach to overcome this is Bayesian optimal experimental design (BOED). However, BOED becomes infeasible in high-dimensional settings, as it involves integration over all possible experimental outcomes. We propose a novel criterion for experimental design based on a variational approximation of the expected information gain. We show that for CTBNs, a semi-analytical expression for this criterion can be calculated for structure and parameter learning. By doing so, we can replace sampling over experimental outcomes by solving the CTBNs master-equation, for which scalable approximations exist. This alleviates the computational burden of sampling possible experimental outcomes in high-dimensions. We employ this framework to recommend interventional sequences. In this context, we extend the CTBN model to conditional CTBNs to incorporate interventions. We demonstrate the performance of our criterion on synthetic and real-world data.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/linzner21a.html
http://proceedings.mlr.press/v139/linzner21a.htmlTractable structured natural-gradient descent using local parameterizationsNatural-gradient descent (NGD) on structured parameter spaces (e.g., low-rank covariances) is computationally challenging due to difficult Fisher-matrix computations. We address this issue by using \emph{local-parameter coordinates} to obtain a flexible and efficient NGD method that works well for a wide-variety of structured parameterizations. We show four applications where our method (1) generalizes the exponential natural evolutionary strategy, (2) recovers existing Newton-like algorithms, (3) yields new structured second-order algorithms, and (4) gives new algorithms to learn covariances of Gaussian and Wishart-based distributions. We show results on a range of problems from deep learning, variational inference, and evolution strategies. Our work opens a new direction for scalable structured geometric methods.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/lin21e.html
http://proceedings.mlr.press/v139/lin21e.htmlGenerative Causal Explanations for Graph Neural NetworksThis paper presents {\em Gem}, a model-agnostic approach for providing interpretable explanations for any GNNs on various graph learning tasks. Specifically, we formulate the problem of providing explanations for the decisions of GNNs as a causal learning task. Then we train a causal explanation model equipped with a loss function based on Granger causality. Different from existing explainers for GNNs, {\em Gem} explains GNNs on graph-structured data from a causal perspective. It has better generalization ability as it has no requirements on the internal structure of the GNNs or prior knowledge on the graph learning tasks. In addition, {\em Gem}, once trained, can be used to explain the target GNN very quickly. Our theoretical analysis shows that several recent explainers fall into a unified framework of {\em additive feature attribution methods}. Experimental results on synthetic and real-world datasets show that {\em Gem} achieves a relative increase of the explanation accuracy by up to $30%$ and speeds up the explanation process by up to $110\times$ as compared to its state-of-the-art alternatives.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/lin21d.html
http://proceedings.mlr.press/v139/lin21d.htmlQuasi-global Momentum: Accelerating Decentralized Deep Learning on Heterogeneous DataDecentralized training of deep learning models is a key element for enabling data privacy and on-device learning over networks. In realistic learning scenarios, the presence of heterogeneity across different clients’ local datasets poses an optimization challenge and may severely deteriorate the generalization performance. In this paper, we investigate and identify the limitation of several decentralized optimization algorithms for different degrees of data heterogeneity. We propose a novel momentum-based method to mitigate this decentralized training difficulty. We show in extensive empirical experiments on various CV/NLP datasets (CIFAR-10, ImageNet, and AG News) and several network topologies (Ring and Social Network) that our method is much more robust to the heterogeneity of clients’ data than other existing methods, by a significant improvement in test performance (1%-20%).Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/lin21c.html
http://proceedings.mlr.press/v139/lin21c.htmlStraight to the Gradient: Learning to Use Novel Tokens for Neural Text GenerationAdvanced large-scale neural language models have led to significant success in many language generation tasks. However, the most commonly used training objective, Maximum Likelihood Estimation (MLE), has been shown problematic, where the trained model prefers using dull and repetitive phrases. In this work, we introduce ScaleGrad, a modification straight to the gradient of the loss function, to remedy the degeneration issue of the standard MLE objective. By directly maneuvering the gradient information, ScaleGrad makes the model learn to use novel tokens. Empirical results show the effectiveness of our method not only in open-ended generation, but also in directed generation tasks. With the simplicity in architecture, our method can serve as a general training objective that is applicable to most of the neural text generation tasks.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/lin21b.html
http://proceedings.mlr.press/v139/lin21b.htmlMaking transport more robust and interpretable by moving data through a small number of anchor pointsOptimal transport (OT) is a widely used technique for distribution alignment, with applications throughout the machine learning, graphics, and vision communities. Without any additional structural assumptions on transport, however, OT can be fragile to outliers or noise, especially in high dimensions. Here, we introduce Latent Optimal Transport (LOT), a new approach for OT that simultaneously learns low-dimensional structure in data while leveraging this structure to solve the alignment task. The idea behind our approach is to learn two sets of “anchors” that constrain the flow of transport between a source and target distribution. In both theoretical and empirical studies, we show that LOT regularizes the rank of transport and makes it more robust to outliers and the sampling density. We show that by allowing the source and target to have different anchors, and using LOT to align the latent spaces between anchors, the resulting transport plan has better structural interpretability and highlights connections between both the individual data points and the local geometry of the datasets.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/lin21a.html
http://proceedings.mlr.press/v139/lin21a.htmlDebiasing a First-order Heuristic for Approximate Bi-level OptimizationApproximate bi-level optimization (ABLO) consists of (outer-level) optimization problems, involving numerical (inner-level) optimization loops. While ABLO has many applications across deep learning, it suffers from time and memory complexity proportional to the length $r$ of its inner optimization loop. To address this complexity, an earlier first-order method (FOM) was proposed as a heuristic which omits second derivative terms, yielding significant speed gains and requiring only constant memory. Despite FOM’s popularity, there is a lack of theoretical understanding of its convergence properties. We contribute by theoretically characterizing FOM’s gradient bias under mild assumptions. We further demonstrate a rich family of examples where FOM-based SGD does not converge to a stationary point of the ABLO objective. We address this concern by proposing an unbiased FOM (UFOM) enjoying constant memory complexity as a function of $r$. We characterize the introduced time-variance tradeoff, demonstrate convergence bounds, and find an optimal UFOM for a given ABLO problem. Finally, we propose an efficient adaptive UFOM scheme.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/likhosherstov21a.html
http://proceedings.mlr.press/v139/likhosherstov21a.htmlGuided Exploration with Proximal Policy Optimization using a Single DemonstrationSolving sparse reward tasks through exploration is one of the major challenges in deep reinforcement learning, especially in three-dimensional, partially-observable environments. Critically, the algorithm proposed in this article is capable of using a single human demonstration to solve hard-exploration problems. We train an agent on a combination of demonstrations and own experience to solve problems with variable initial conditions and we integrate it with proximal policy optimization (PPO). The agent is also able to increase its performance and to tackle harder problems by replaying its own past trajectories prioritizing them based on the obtained reward and the maximum value of the trajectory. We finally compare variations of this algorithm to different imitation learning algorithms on a set of hard-exploration tasks in the Animal-AI Olympics environment. To the best of our knowledge, learning a task in a three-dimensional environment with comparable difficulty has never been considered before using only one human demonstration.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/libardi21a.html
http://proceedings.mlr.press/v139/libardi21a.htmlInformation Obfuscation of Graph Neural NetworksWhile the advent of Graph Neural Networks (GNNs) has greatly improved node and graph representation learning in many applications, the neighborhood aggregation scheme exposes additional vulnerabilities to adversaries seeking to extract node-level information about sensitive attributes. In this paper, we study the problem of protecting sensitive attributes by information obfuscation when learning with graph structured data. We propose a framework to locally filter out pre-determined sensitive attributes via adversarial training with the total variation and the Wasserstein distance. Our method creates a strong defense against inference attacks, while only suffering small loss in task performance. Theoretically, we analyze the effectiveness of our framework against a worst-case adversary, and characterize an inherent trade-off between maximizing predictive accuracy and minimizing information leakage. Experiments across multiple datasets from recommender systems, knowledge graphs and quantum chemistry demonstrate that the proposed approach provides a robust defense across various graph structures and tasks, while producing competitive GNN encoders for downstream tasks.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/liao21a.html
http://proceedings.mlr.press/v139/liao21a.htmlParallel Droplet Control in MEDA Biochips using Multi-Agent Reinforcement LearningMicrofluidic biochips are being utilized for clinical diagnostics, including COVID-19 testing, because of they provide sample-to-result turnaround at low cost. Recently, microelectrode-dot-array (MEDA) biochips have been proposed to advance microfluidics technology. A MEDA biochip manipulates droplets of nano/picoliter volumes to automatically execute biochemical protocols. During bioassay execution, droplets are transported in parallel to achieve high-throughput outcomes. However, a major concern associated with the use of MEDA biochips is microelectrode degradation over time. Recent work has shown that formulating droplet transportation as a reinforcement-learning (RL) problem enables the training of policies to capture the underlying health conditions of microelectrodes and ensure reliable fluidic operations. However, the above RL-based approach suffers from two key limitations: 1) it cannot be used for concurrent transportation of multiple droplets; 2) it requires the availability of CCD cameras for monitoring droplet movement. To overcome these problems, we present a multi-agent reinforcement learning (MARL) droplet-routing solution that can be used for various sizes of MEDA biochips with integrated sensors, and we demonstrate the reliable execution of a serial-dilution bioassay with the MARL droplet router on a fabricated MEDA biochip. To facilitate further research, we also present a simulation environment based on the PettingZoo Gym Interface for MARL-guided droplet-routing problems on MEDA biochips.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/liang21c.html
http://proceedings.mlr.press/v139/liang21c.htmlUncovering the Connections Between Adversarial Transferability and Knowledge TransferabilityKnowledge transferability, or transfer learning, has been widely adopted to allow a pre-trained model in the source domain to be effectively adapted to downstream tasks in the target domain. It is thus important to explore and understand the factors affecting knowledge transferability. In this paper, as the first work, we analyze and demonstrate the connections between knowledge transferability and another important phenomenon–adversarial transferability, \emph{i.e.}, adversarial examples generated against one model can be transferred to attack other models. Our theoretical studies show that adversarial transferability indicates knowledge transferability, and vice versa. Moreover, based on the theoretical insights, we propose two practical adversarial transferability metrics to characterize this process, serving as bidirectional indicators between adversarial and knowledge transferability. We conduct extensive experiments for different scenarios on diverse datasets, showing a positive correlation between adversarial transferability and knowledge transferability. Our findings will shed light on future research about effective knowledge transfer learning and adversarial transferability analyses.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/liang21b.html
http://proceedings.mlr.press/v139/liang21b.htmlTowards Understanding and Mitigating Social Biases in Language ModelsAs machine learning methods are deployed in real-world settings such as healthcare, legal systems, and social science, it is crucial to recognize how they shape social biases and stereotypes in these sensitive decision-making processes. Among such real-world deployments are large-scale pretrained language models (LMs) that can be potentially dangerous in manifesting undesirable representational biases - harmful biases resulting from stereotyping that propagate negative generalizations involving gender, race, religion, and other social constructs. As a step towards improving the fairness of LMs, we carefully define several sources of representational biases before proposing new benchmarks and metrics to measure them. With these tools, we propose steps towards mitigating social biases during text generation. Our empirical results and human evaluation demonstrate effectiveness in mitigating bias while retaining crucial contextual information for high-fidelity text generation, thereby pushing forward the performance-fairness Pareto frontier.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/liang21a.html
http://proceedings.mlr.press/v139/liang21a.htmlA Second look at Exponential and Cosine Step Sizes: Simplicity, Adaptivity, and PerformanceStochastic Gradient Descent (SGD) is a popular tool in training large-scale machine learning models. Its performance, however, is highly variable, depending crucially on the choice of the step sizes. Accordingly, a variety of strategies for tuning the step sizes have been proposed, ranging from coordinate-wise approaches (a.k.a. “adaptive” step sizes) to sophisticated heuristics to change the step size in each iteration. In this paper, we study two step size schedules whose power has been repeatedly confirmed in practice: the exponential and the cosine step sizes. For the first time, we provide theoretical support for them proving convergence rates for smooth non-convex functions, with and without the Polyak-Ł{}ojasiewicz (PL) condition. Moreover, we show the surprising property that these two strategies are \emph{adaptive} to the noise level in the stochastic gradients of PL functions. That is, contrary to polynomial step sizes, they achieve almost optimal performance without needing to know the noise level nor tuning their hyperparameters based on it. Finally, we conduct a fair and comprehensive empirical evaluation of real-world datasets with deep learning architectures. Results show that, even if only requiring at most two hyperparameters to tune, these two strategies best or match the performance of various finely-tuned state-of-the-art strategies.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/li21z.html
http://proceedings.mlr.press/v139/li21z.htmlTeraPipe: Token-Level Pipeline Parallelism for Training Large-Scale Language ModelsModel parallelism has become a necessity for training modern large-scale deep language models. In this work, we identify a new and orthogonal dimension from existing model parallel approaches: it is possible to perform pipeline parallelism within a single training sequence for Transformer-based language models thanks to its autoregressive property. This enables a more fine-grained pipeline compared with previous work. With this key idea, we design TeraPipe, a high-performance token-level pipeline parallel algorithm for synchronous model-parallel training of Transformer-based language models. We develop a novel dynamic programming-based algorithm to calculate the optimal pipelining execution scheme given a specific model and cluster configuration. We show that TeraPipe can speed up the training by 5.0x for the largest GPT-3 model with 175 billion parameters on an AWS cluster with 48 p3.16xlarge instances compared with state-of-the-art model-parallel methods. The code for reproduction can be found at https://github.com/zhuohan123/terapipeThu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/li21y.html
http://proceedings.mlr.press/v139/li21y.htmlAsymptotic Normality and Confidence Intervals for Prediction Risk of the Min-Norm Least Squares EstimatorThis paper quantifies the uncertainty of prediction risk for the min-norm least squares estimator in high-dimensional linear regression models. We establish the asymptotic normality of prediction risk when both the sample size and the number of features tend to infinity. Based on the newly established central limit theorems(CLTs), we derive the confidence intervals of the prediction risk under various scenarios. Our results demonstrate the sample-wise non-monotonicity of the prediction risk and confirm “more data hurt" phenomenon. Furthermore, the width of confidence intervals indicates that over-parameterization would enlarge the randomness of prediction performance.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/li21x.html
http://proceedings.mlr.press/v139/li21x.htmlOnline Unrelated Machine Load Balancing with Predictions RevisitedWe study the online load balancing problem with machine learned predictions, and give results that improve upon and extend those in a recent paper by Lattanzi et al. (2020). First, we design deterministic and randomized online rounding algorithms for the problem in the unrelated machine setting, with $O(\frac{\log m}{\log \log m})$- and $O(\frac{\log \log m}{\log \log \log m})$-competitive ratios. They respectively improve upon the previous ratios of $O(\log m)$ and $O(\log^3\log m)$, and match the lower bounds given by Lattanzi et al. Second, we extend their prediction scheme from the identical machine restricted assignment setting to the unrelated machine setting. With the knowledge of two vectors over machines, a dual vector and a weight vector, we can construct a good fractional assignment online, that can be passed to an online rounding algorithm. Finally, we consider the learning model introduced by Lavastida et al. (2020), and show that under the model, the two vectors can be learned efficiently with a few samples of instances.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/li21w.html
http://proceedings.mlr.press/v139/li21w.htmlFILTRA: Rethinking Steerable CNN by Filter TransformSteerable CNN imposes the prior knowledge of transformation invariance or equivariance in the network architecture to enhance the the network robustness on geometry transformation of data and reduce overfitting. It has been an intuitive and widely used technique to construct a steerable filter by augmenting a filter with its transformed copies in the past decades, which is named as filter transform in this paper. Recently, the problem of steerable CNN has been studied from aspect of group representation theory, which reveals the function space structure of a steerable kernel function. However, it is not yet clear on how this theory is related to the filter transform technique. In this paper, we show that kernel constructed by filter transform can also be interpreted in the group representation theory. This interpretation help complete the puzzle of steerable CNN theory and provides a novel and simple approach to implement steerable convolution operators. Experiments are executed on multiple datasets to verify the feasibility of the proposed approach.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/li21v.html
http://proceedings.mlr.press/v139/li21v.htmlCommunication-Efficient Distributed SVD via Local Power IterationsWe study distributed computing of the truncated singular value decomposition (SVD). We develop an algorithm that we call \texttt{LocalPower} for improving communication efficiency. Specifically, we uniformly partition the dataset among $m$ nodes and alternate between multiple (precisely $p$) local power iterations and one global aggregation. In the aggregation, we propose to weight each local eigenvector matrix with orthogonal Procrustes transformation (OPT). As a practical surrogate of OPT, sign-fixing, which uses a diagonal matrix with $\pm 1$ entries as weights, has better computation complexity and stability in experiments. We theoretically show that under certain assumptions \texttt{LocalPower} lowers the required number of communications by a factor of $p$ to reach a constant accuracy. We also show that the strategy of periodically decaying $p$ helps obtain high-precision solutions. We conduct experiments to demonstrate the effectiveness of \texttt{LocalPower}.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/li21u.html
http://proceedings.mlr.press/v139/li21u.htmlDistributionally Robust Optimization with Markovian DataWe study a stochastic program where the probability distribution of the uncertain problem parameters is unknown and only indirectly observed via finitely many correlated samples generated by an unknown Markov chain with $d$ states. We propose a data-driven distributionally robust optimization model to estimate the problem’s objective function and optimal solution. By leveraging results from large deviations theory, we derive statistical guarantees on the quality of these estimators. The underlying worst-case expectation problem is nonconvex and involves $\mathcal O(d^2)$ decision variables. Thus, it cannot be solved efficiently for large $d$. By exploiting the structure of this problem, we devise a customized Frank-Wolfe algorithm with convex direction-finding subproblems of size $\mathcal O(d)$. We prove that this algorithm finds a stationary point efficiently under mild conditions. The efficiency of the method is predicated on a dimensionality reduction enabled by a dual reformulation. Numerical experiments indicate that our approach has better computational and statistical properties than the state-of-the-art methods.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/li21t.html
http://proceedings.mlr.press/v139/li21t.htmlThe Symmetry between Arms and Knapsacks: A Primal-Dual Approach for Bandits with KnapsacksIn this paper, we study the bandits with knapsacks (BwK) problem and develop a primal-dual based algorithm that achieves a problem-dependent logarithmic regret bound. The BwK problem extends the multi-arm bandit (MAB) problem to model the resource consumption, and the existing BwK literature has been mainly focused on deriving asymptotically optimal distribution-free regret bounds. We first study the primal and dual linear programs underlying the BwK problem. From this primal-dual perspective, we discover symmetry between arms and knapsacks, and then propose a new notion of suboptimality measure for the BwK problem. The suboptimality measure highlights the important role of knapsacks in determining algorithm regret and inspires the design of our two-phase algorithm. In the first phase, the algorithm identifies the optimal arms and the binding knapsacks, and in the second phase, it exhausts the binding knapsacks via playing the optimal arms through an adaptive procedure. Our regret upper bound involves the proposed suboptimality measure and it has a logarithmic dependence on length of horizon $T$ and a polynomial dependence on $m$ (the numbers of arms) and $d$ (the number of knapsacks). To the best of our knowledge, this is the first problem-dependent logarithmic regret bound for solving the general BwK problem.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/li21s.html
http://proceedings.mlr.press/v139/li21s.htmlTesting DNN-based Autonomous Driving Systems under Critical Environmental ConditionsDue to the increasing usage of Deep Neural Network (DNN) based autonomous driving systems (ADS) where erroneous or unexpected behaviours can lead to catastrophic accidents, testing such systems is of growing importance. Existing approaches often just focus on finding erroneous behaviours and have not thoroughly studied the impact of environmental conditions. In this paper, we propose to test DNN-based ADS under different environmental conditions to identify the critical ones, that is, the environmental conditions under which the ADS are more prone to errors. To tackle the problem of the space of environmental conditions being extremely large, we present a novel approach named TACTIC that employs the search-based method to identify critical environmental conditions generated by an image-to-image translation model. Large-scale experiments show that TACTIC can effectively identify critical environmental conditions and produce realistic testing images, and meanwhile, reveal more erroneous behaviours compared to existing approaches.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/li21r.html
http://proceedings.mlr.press/v139/li21r.htmlPartially Observed Exchangeable ModelingModeling dependencies among features is fundamental for many machine learning tasks. Although there are often multiple related instances that may be leveraged to inform conditional dependencies, typical approaches only model conditional dependencies over individual instances. In this work, we propose a novel framework, partially observed exchangeable modeling (POEx) that takes in a set of related partially observed instances and infers the conditional distribution for the unobserved dimensions over multiple elements. Our approach jointly models the intra-instance (among features in a point) and inter-instance (among multiple points in a set) dependencies in data. POEx is a general framework that encompasses many existing tasks such as point cloud expansion and few-shot generation, as well as new tasks like few-shot imputation. Despite its generality, extensive empirical evaluations show that our model achieves state-of-the-art performance across a range of applications.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/li21q.html
http://proceedings.mlr.press/v139/li21q.htmlActive Feature Acquisition with Generative Surrogate ModelsMany real-world situations allow for the acquisition of additional relevant information when making an assessment with limited or uncertain data. However, traditional ML approaches either require all features to be acquired beforehand or regard part of them as missing data that cannot be acquired. In this work, we consider models that perform active feature acquisition (AFA) and query the environment for unobserved features to improve the prediction assessments at evaluation time. Our work reformulates the Markov decision process (MDP) that underlies the AFA problem as a generative modeling task and optimizes a policy via a novel model-based approach. We propose learning a generative surrogate model (GSM) that captures the dependencies among input features to assess potential information gain from acquisitions. The GSM is leveraged to provide intermediate rewards and auxiliary information to aid the agent navigate a complicated high-dimensional action space and sparse rewards. Furthermore, we extend AFA in a task we coin active instance recognition (AIR) for the unsupervised case where the target variables are the unobserved features themselves and the goal is to collect information for a particular instance in a cost-efficient way. Empirical results demonstrate that our approach achieves considerably better performance than previous state of the art methods on both supervised and unsupervised tasks.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/li21p.html
http://proceedings.mlr.press/v139/li21p.htmlTraining Graph Neural Networks with 1000 LayersDeep graph neural networks (GNNs) have achieved excellent results on various tasks on increasingly large graph datasets with millions of nodes and edges. However, memory complexity has become a major obstacle when training deep GNNs for practical applications due to the immense number of nodes, edges, and intermediate activations. To improve the scalability of GNNs, prior works propose smart graph sampling or partitioning strategies to train GNNs with a smaller set of nodes or sub-graphs. In this work, we study reversible connections, group convolutions, weight tying, and equilibrium models to advance the memory and parameter efficiency of GNNs. We find that reversible connections in combination with deep network architectures enable the training of overparameterized GNNs that significantly outperform existing methods on multiple datasets. Our models RevGNN-Deep (1001 layers with 80 channels each) and RevGNN-Wide (448 layers with 224 channels each) were both trained on a single commodity GPU and achieve an ROC-AUC of 87.74 $\pm$ 0.13 and 88.14 $\pm$ 0.15 on the ogbn-proteins dataset. To the best of our knowledge, RevGNN-Deep is the deepest GNN in the literature by one order of magnitude.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/li21o.html
http://proceedings.mlr.press/v139/li21o.htmlMixed Cross Entropy Loss for Neural Machine TranslationIn neural machine translation, Cross Entropy loss (CE) is the standard loss function in two training methods of auto-regressive models, i.e., teacher forcing and scheduled sampling. In this paper, we propose mixed Cross Entropy loss (mixed CE) as a substitute for CE in both training approaches. In teacher forcing, the model trained with CE regards the translation problem as a one-to-one mapping process, while in mixed CE this process can be relaxed to one-to-many. In scheduled sampling, we show that mixed CE has the potential to encourage the training and testing behaviours to be similar to each other, more effectively mitigating the exposure bias problem. We demonstrate the superiority of mixed CE over CE on several machine translation datasets, WMT’16 Ro-En, WMT’16 Ru-En, and WMT’14 En-De in both teacher forcing and scheduled sampling setups. Furthermore, in WMT’14 En-De, we also find mixed CE consistently outperforms CE on a multi-reference set as well as a challenging paraphrased reference set. We also found the model trained with mixed CE is able to provide a better probability distribution defined over the translation output space. Our code is available at https://github.com/haorannlp/mix.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/li21n.html
http://proceedings.mlr.press/v139/li21n.htmlA Novel Method to Solve Neural Knapsack Problems0-1 knapsack is of fundamental importance across many fields. In this paper, we present a game-theoretic method to solve 0-1 knapsack problems (KPs) where the number of items (products) is large and the values of items are not predetermined but decided by an external value assignment function (e.g., a neural network in our case) during the optimization process. While existing papers are interested in predicting solutions with neural networks for classical KPs whose objective functions are mostly linear functions, we are interested in solving KPs whose objective functions are neural networks. In other words, we choose a subset of items that maximize the sum of the values predicted by neural networks. Its key challenge is how to optimize the neural network-based non-linear KP objective with a budget constraint. Our solution is inspired by game-theoretic approaches in deep learning, e.g., generative adversarial networks. After formally defining our two-player game, we develop an adaptive gradient ascent method to solve it. In our experiments, our method successfully solves two neural network-based non-linear KPs and conventional linear KPs with 1 million items.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/li21m.html
http://proceedings.mlr.press/v139/li21m.htmlProvably End-to-end Label-noise Learning without Anchor PointsIn label-noise learning, the transition matrix plays a key role in building statistically consistent classifiers. Existing consistent estimators for the transition matrix have been developed by exploiting anchor points. However, the anchor-point assumption is not always satisfied in real scenarios. In this paper, we propose an end-to-end framework for solving label-noise learning without anchor points, in which we simultaneously optimize two objectives: the cross entropy loss between the noisy label and the predicted probability by the neural network, and the volume of the simplex formed by the columns of the transition matrix. Our proposed framework can identify the transition matrix if the clean class-posterior probabilities are sufficiently scattered. This is by far the mildest assumption under which the transition matrix is provably identifiable and the learned classifier is statistically consistent. Experimental results on benchmark datasets demonstrate the effectiveness and robustness of the proposed method.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/li21l.html
http://proceedings.mlr.press/v139/li21l.htmlSharper Generalization Bounds for ClusteringExisting generalization analysis of clustering mainly focuses on specific instantiations, such as (kernel) $k$-means, and a unified framework for studying clustering performance is still lacking. Besides, the existing excess clustering risk bounds are mostly of order $\mathcal{O}(K/\sqrt{n})$ provided that the underlying distribution has bounded support, where $n$ is the sample size and $K$ is the cluster numbers, or of order $\mathcal{O}(K^2/n)$ under strong assumptions on the underlying distribution, where these assumptions are hard to be verified in general. In this paper, we propose a unified clustering learning framework and investigate its excess risk bounds, obtaining state-of-the-art upper bounds under mild assumptions. Specifically, we derive sharper bounds of order $\mathcal{O}(K^2/n)$ under mild assumptions on the covering number of the hypothesis spaces, where these assumptions are easy to be verified. Moreover, for the hard clustering scheme, such as (kernel) $k$-means, if just assume the hypothesis functions to be bounded, we improve the upper bounds from the order $\mathcal{O}(K/\sqrt{n})$ to $\mathcal{O}(\sqrt{K}/\sqrt{n})$. Furthermore, state-of-the-art bounds of faster order $\mathcal{O}(K/n)$ are obtained with the covering number assumptions.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/li21k.html
http://proceedings.mlr.press/v139/li21k.htmlApproximate Group Fairness for ClusteringWe incorporate group fairness into the algorithmic centroid clustering problem, where $k$ centers are to be located to serve $n$ agents distributed in a metric space. We refine the notion of proportional fairness proposed in [Chen et al., ICML 2019] as {\em core fairness}. A $k$-clustering is in the core if no coalition containing at least $n/k$ agents can strictly decrease their total distance by deviating to a new center together. Our solution concept is motivated by the situation where agents are able to coordinate and utilities are transferable. A string of existence, hardness and approximability results is provided. Particularly, we propose two dimensions to relax core requirements: one is on the degree of distance improvement, and the other is on the size of deviating coalition. For both relaxations and their combination, we study the extent to which relaxed core fairness can be satisfied in metric spaces including line, tree and general metric space, and design approximation algorithms accordingly. We also conduct experiments on synthetic and real-world data to examine the performance of our algorithms.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/li21j.html
http://proceedings.mlr.press/v139/li21j.htmlQuantization Algorithms for Random Fourier FeaturesThe method of random projection (RP) is the standard technique for dimensionality reduction, approximate near neighbor search, compressed sensing, etc., which provides a simple and effective scheme for approximating pairwise inner products and Euclidean distances in massive data. Closely related to RP, the method of random Fourier features (RFF) has also become popular for approximating the (nonlinear) Gaussian kernel. RFF applies a specific nonlinear transformation on the projected data from RP. In practice, using the Gaussian kernel often leads to better performance than the linear kernel (inner product). After random projections, quantization is an important step for efficient data storage, computation and transmission. Quantization for RP has been extensively studied in the literature. In this paper, we focus on developing quantization algorithms for RFF. The task is in a sense challenging due to the tuning parameter $\gamma$ in the Gaussian kernel. For example, the quantizer and the quantized data might be tied to each specific Gaussian kernel parameter $\gamma$. Our contribution begins with the analysis on the probability distributions of RFF, and an interesting discovery that the marginal distribution of RFF is free of the parameter $\gamma$. This significantly simplifies the design of the Lloyd-Max (LM) quantization scheme for RFF in that there would be only one LM quantizer (regardless of $\gamma$). Detailed theoretical analysis is provided on the kernel estimators and approximation error, and experiments confirm the effectiveness and efficiency of the proposed method.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/li21i.html
http://proceedings.mlr.press/v139/li21i.htmlDitto: Fair and Robust Federated Learning Through PersonalizationFairness and robustness are two important concerns for federated learning systems. In this work, we identify that robustness to data and model poisoning attacks and fairness, measured as the uniformity of performance across devices, are competing constraints in statistically heterogeneous networks. To address these constraints, we propose employing a simple, general framework for personalized federated learning, Ditto, that can inherently provide fairness and robustness benefits, and develop a scalable solver for it. Theoretically, we analyze the ability of Ditto to achieve fairness and robustness simultaneously on a class of linear problems. Empirically, across a suite of federated datasets, we show that Ditto not only achieves competitive performance relative to recent personalization methods, but also enables more accurate, robust, and fair models relative to state-of-the-art fair or robust baselines.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/li21h.html
http://proceedings.mlr.press/v139/li21h.htmlMURAL: Meta-Learning Uncertainty-Aware Rewards for Outcome-Driven Reinforcement LearningExploration in reinforcement learning is, in general, a challenging problem. A common technique to make learning easier is providing demonstrations from a human supervisor, but such demonstrations can be expensive and time-consuming to acquire. In this work, we study a more tractable class of reinforcement learning problems defined simply by examples of successful outcome states, which can be much easier to provide while still making the exploration problem more tractable. In this problem setting, the reward function can be obtained automatically by training a classifier to categorize states as successful or not. However, as we will show, this requires the classifier to make uncertainty-aware predictions that are very difficult using standard techniques for training deep networks. To address this, we propose a novel mechanism for obtaining calibrated uncertainty based on an amortized technique for computing the normalized maximum likelihood (NML) distribution, leveraging tools from meta-learning to make this distribution tractable. We show that the resulting algorithm has a number of intriguing connections to both count-based exploration methods and prior algorithms for learning reward functions, while also providing more effective guidance towards the goal. We demonstrate that our algorithm solves a number of challenging navigation and robotic manipulation tasks which prove difficult or impossible for prior methods.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/li21g.html
http://proceedings.mlr.press/v139/li21g.htmlTheory of Spectral Method for Union of Subspaces-Based Random Geometry GraphSpectral method is a commonly used scheme to cluster data points lying close to Union of Subspaces, a task known as Subspace Clustering. The typical usage is to construct a Random Geometry Graph first and then apply spectral method to the graph to obtain clustering result. The latter step has been coined the name Spectral Clustering. As far as we know, in spite of the significance of both steps in spectral-method-based Subspace Clustering, all existing theoretical results focus on the first step of constructing the graph, but ignore the final step to correct false connections through spectral clustering. This paper establishes a theory to show the power of this method for the first time, in which we demonstrate the mechanism of spectral clustering by analyzing a simplified algorithm under the widely used semi-random model. Based on this theory, we prove the efficiency of Subspace Clustering in fairly broad conditions. The insights and analysis techniques developed in this paper might also have implications for other random graph problems.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/li21f.html
http://proceedings.mlr.press/v139/li21f.htmlPrivacy-Preserving Feature Selection with Secure Multiparty ComputationExisting work on privacy-preserving machine learning with Secure Multiparty Computation (MPC) is almost exclusively focused on model training and on inference with trained models, thereby overlooking the important data pre-processing stage. In this work, we propose the first MPC based protocol for private feature selection based on the filter method, which is independent of model training, and can be used in combination with any MPC protocol to rank features. We propose an efficient feature scoring protocol based on Gini impurity to this end. To demonstrate the feasibility of our approach for practical data science, we perform experiments with the proposed MPC protocols for feature selection in a commonly used machine-learning-as-a-service configuration where computations are outsourced to multiple servers, with semi-honest and with malicious adversaries. Regarding effectiveness, we show that secure feature selection with the proposed protocols improves the accuracy of classifiers on a variety of real-world data sets, without leaking information about the feature values or even which features were selected. Regarding efficiency, we document runtimes ranging from several seconds to an hour for our protocols to finish, depending on the size of the data set and the security settings.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/li21e.html
http://proceedings.mlr.press/v139/li21e.htmlA Free Lunch From ANN: Towards Efficient, Accurate Spiking Neural Networks CalibrationSpiking Neural Network (SNN) has been recognized as one of the next generation of neural networks. Conventionally, SNN can be converted from a pre-trained ANN by only replacing the ReLU activation to spike activation while keeping the parameters intact. Perhaps surprisingly, in this work we show that a proper way to calibrate the parameters during the conversion of ANN to SNN can bring significant improvements. We introduce SNN Calibration, a cheap but extraordinarily effective method by leveraging the knowledge within a pre-trained Artificial Neural Network (ANN). Starting by analyzing the conversion error and its propagation through layers theoretically, we propose the calibration algorithm that can correct the error layer-by-layer. The calibration only takes a handful number of training data and several minutes to finish. Moreover, our calibration algorithm can produce SNN with state-of-the-art architecture on the large-scale ImageNet dataset, including MobileNet and RegNet. Extensive experiments demonstrate the effectiveness and efficiency of our algorithm. For example, our advanced pipeline can increase up to 69% top-1 accuracy when converting MobileNet on ImageNet compared to baselines. Codes are released at https://github.com/yhhhli/SNN_Calibration.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/li21d.html
http://proceedings.mlr.press/v139/li21d.htmlWinograd Algorithm for AdderNetAdder neural network (AdderNet) is a new kind of deep model that replaces the original massive multiplications in convolutions by additions while preserving the high performance. Since the hardware complexity of additions is much lower than that of multiplications, the overall energy consumption is thus reduced significantly. To further optimize the hardware overhead of using AdderNet, this paper studies the winograd algorithm, which is a widely used fast algorithm for accelerating convolution and saving the computational costs. Unfortunately, the conventional Winograd algorithm cannot be directly applied to AdderNets since the distributive law in multiplication is not valid for the l1-norm. Therefore, we replace the element-wise multiplication in the Winograd equation by additions and then develop a new set of transform matrixes that can enhance the representation ability of output features to maintain the performance. Moreover, we propose the l2-to-l1 training strategy to mitigate the negative impacts caused by formal inconsistency. Experimental results on both FPGA and benchmarks show that the new method can further reduce the energy consumption without affecting the accuracy of the original AdderNet.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/li21c.html
http://proceedings.mlr.press/v139/li21c.htmlTightening the Dependence on Horizon in the Sample Complexity of Q-LearningQ-learning, which seeks to learn the optimal Q-function of a Markov decision process (MDP) in a model-free fashion, lies at the heart of reinforcement learning. Focusing on the synchronous setting (such that independent samples for all state-action pairs are queried via a generative model in each iteration), substantial progress has been made recently towards understanding the sample efficiency of Q-learning. To yield an entrywise $\varepsilon$-accurate estimate of the optimal Q-function, state-of-the-art theory requires at least an order of $\frac{|S||A|}{(1-\gamma)^5\varepsilon^{2}}$ samples in the infinite-horizon $\gamma$-discounted setting. In this work, we sharpen the sample complexity of synchronous Q-learning to the order of $\frac{|S||A|}{(1-\gamma)^4\varepsilon^2}$ (up to some logarithmic factor) for any $0<\varepsilon <1$, leading to an order-wise improvement in $\frac{1}{1-\gamma}$. Analogous results are derived for finite-horizon MDPs as well. Notably, our sample complexity analysis unveils the effectiveness of vanilla Q-learning, which matches that of speedy Q-learning without requiring extra computation and storage. Our result is obtained by identifying novel error decompositions and recursion relations, which might shed light on how to study other variants of Q-learning.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/li21b.html
http://proceedings.mlr.press/v139/li21b.htmlPAGE: A Simple and Optimal Probabilistic Gradient Estimator for Nonconvex OptimizationIn this paper, we propose a novel stochastic gradient estimator—ProbAbilistic Gradient Estimator (PAGE)—for nonconvex optimization. PAGE is easy to implement as it is designed via a small adjustment to vanilla SGD: in each iteration, PAGE uses the vanilla minibatch SGD update with probability $p_t$ or reuses the previous gradient with a small adjustment, at a much lower computational cost, with probability $1-p_t$. We give a simple formula for the optimal choice of $p_t$. Moreover, we prove the first tight lower bound $\Omega(n+\frac{\sqrt{n}}{\epsilon^2})$ for nonconvex finite-sum problems, which also leads to a tight lower bound $\Omega(b+\frac{\sqrt{b}}{\epsilon^2})$ for nonconvex online problems, where $b:= \min\{\frac{\sigma^2}{\epsilon^2}, n\}$. Then, we show that PAGE obtains the optimal convergence results $O(n+\frac{\sqrt{n}}{\epsilon^2})$ (finite-sum) and $O(b+\frac{\sqrt{b}}{\epsilon^2})$ (online) matching our lower bounds for both nonconvex finite-sum and online problems. Besides, we also show that for nonconvex functions satisfying the Polyak-Ł{ojasiewicz} (PL) condition, PAGE can automatically switch to a faster linear convergence rate $O(\cdot\log \frac{1}{\epsilon})$. Finally, we conduct several deep learning experiments (e.g., LeNet, VGG, ResNet) on real datasets in PyTorch showing that PAGE not only converges much faster than SGD in training but also achieves the higher test accuracy, validating the optimal theoretical results and confirming the practical superiority of PAGE.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/li21a.html
http://proceedings.mlr.press/v139/li21a.htmlRun-Sort-ReRun: Escaping Batch Size Limitations in Sliced Wasserstein Generative ModelsWhen training an implicit generative model, ideally one would like the generator to reproduce all the different modes and subtleties of the target distribution. Naturally, when comparing two empirical distributions, the larger the sample population, the more these statistical nuances can be captured. However, existing objective functions are computationally constrained in the amount of samples they can consider by the memory required to process a batch of samples. In this paper, we build upon recent progress in sliced Wasserstein distances, a family of differentiable metrics for distribution discrepancy based on the Optimal Transport paradigm. We introduce a procedure to train these distances with virtually any batch size, allowing the discrepancy measure to capture richer statistics and better approximating the distance between the underlying continuous distributions. As an example, we demonstrate the matching of the distribution of Inception features with batches of tens of thousands of samples, achieving FID scores that outperform state-of-the-art implicit generative models.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/lezama21a.html
http://proceedings.mlr.press/v139/lezama21a.htmlBASE Layers: Simplifying Training of Large, Sparse ModelsWe introduce a new balanced assignment of experts (BASE) layer for large language models that greatly simplifies existing high capacity sparse layers. Sparse layers can dramatically improve the efficiency of training and inference by routing each token to specialized expert modules that contain only a small fraction of the model parameters. However, it can be difficult to learn balanced routing functions that make full use of the available experts; existing approaches typically use routing heuristics or auxiliary expert-balancing loss functions. In contrast, we formulate token-to-expert allocation as a linear assignment problem, allowing an optimal assignment in which each expert receives an equal number of tokens. This optimal assignment scheme improves efficiency by guaranteeing balanced compute loads, and also simplifies training by not requiring any new hyperparameters or auxiliary losses. Code is publicly released.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/lewis21a.html
http://proceedings.mlr.press/v139/lewis21a.htmlImproved, Deterministic Smoothing for L_1 Certified RobustnessRandomized smoothing is a general technique for computing sample-dependent robustness guarantees against adversarial attacks for deep classifiers. Prior works on randomized smoothing against L_1 adversarial attacks use additive smoothing noise and provide probabilistic robustness guarantees. In this work, we propose a non-additive and deterministic smoothing method, Deterministic Smoothing with Splitting Noise (DSSN). To develop DSSN, we first develop SSN, a randomized method which involves generating each noisy smoothing sample by first randomly splitting the input space and then returning a representation of the center of the subdivision occupied by the input sample. In contrast to uniform additive smoothing, the SSN certification does not require the random noise components used to be independent. Thus, smoothing can be done effectively in just one dimension and can therefore be efficiently derandomized for quantized data (e.g., images). To the best of our knowledge, this is the first work to provide deterministic "randomized smoothing" for a norm-based adversarial threat model while allowing for an arbitrary classifier (i.e., a deep model) to be used as a base classifier and without requiring an exponential number of smoothing samples. On CIFAR-10 and ImageNet datasets, we provide substantially larger L_1 robustness certificates compared to prior works, establishing a new state-of-the-art. The determinism of our method also leads to significantly faster certificate computation. Code is available at: https://github.com/alevine0/smoothingSplittingNoise.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/levine21a.html
http://proceedings.mlr.press/v139/levine21a.htmlStrategic Classification Made PracticalStrategic classification regards the problem of learning in settings where users can strategically modify their features to improve outcomes. This setting applies broadly, and has received much recent attention. But despite its practical significance, work in this space has so far been predominantly theoretical. In this paper we present a learning framework for strategic classification that is practical. Our approach directly minimizes the “strategic” empirical risk, which we achieve by differentiating through the strategic response of users. This provides flexibility that allows us to extend beyond the original problem formulation and towards more realistic learning scenarios. A series of experiments demonstrates the effectiveness of our approach on various learning settings.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/levanon21a.html
http://proceedings.mlr.press/v139/levanon21a.htmlSigGPDE: Scaling Sparse Gaussian Processes on Sequential DataMaking predictions and quantifying their uncertainty when the input data is sequential is a fundamental learning challenge, recently attracting increasing attention. We develop SigGPDE, a new scalable sparse variational inference framework for Gaussian Processes (GPs) on sequential data. Our contribution is twofold. First, we construct inducing variables underpinning the sparse approximation so that the resulting evidence lower bound (ELBO) does not require any matrix inversion. Second, we show that the gradients of the GP signature kernel are solutions of a hyperbolic partial differential equation (PDE). This theoretical insight allows us to build an efficient back-propagation algorithm to optimize the ELBO. We showcase the significant computational gains of SigGPDE compared to existing methods, while achieving state-of-the-art performance for classification tasks on large datasets of up to 1 million multivariate time series.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/lemercier21a.html
http://proceedings.mlr.press/v139/lemercier21a.htmlLearning to Price Against a Moving TargetIn the Learning to Price setting, a seller posts prices over time with the goal of maximizing revenue while learning the buyer’s valuation. This problem is very well understood when values are stationary (fixed or iid). Here we study the problem where the buyer’s value is a moving target, i.e., they change over time either by a stochastic process or adversarially with bounded variation. In either case, we provide matching upper and lower bounds on the optimal revenue loss. Since the target is moving, any information learned soon becomes out-dated, which forces the algorithms to keep switching between exploring and exploiting phases.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/leme21a.html
http://proceedings.mlr.press/v139/leme21a.htmlGlobally-Robust Neural NetworksThe threat of adversarial examples has motivated work on training certifiably robust neural networks to facilitate efficient verification of local robustness at inference time. We formalize a notion of global robustness, which captures the operational properties of on-line local robustness certification while yielding a natural learning objective for robust training. We show that widely-used architectures can be easily adapted to this objective by incorporating efficient global Lipschitz bounds into the network, yielding certifiably-robust models by construction that achieve state-of-the-art verifiable accuracy. Notably, this approach requires significantly less time and memory than recent certifiable training methods, and leads to negligible costs when certifying points on-line; for example, our evaluation shows that it is possible to train a large robust Tiny-Imagenet model in a matter of hours. Our models effectively leverage inexpensive global Lipschitz bounds for real-time certification, despite prior suggestions that tighter local bounds are needed for good performance; we posit this is possible because our models are specifically trained to achieve tighter global bounds. Namely, we prove that the maximum achievable verifiable accuracy for a given dataset is not improved by using a local bound.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/leino21a.html
http://proceedings.mlr.press/v139/leino21a.htmlBetter Training using Weight-Constrained Stochastic DynamicsWe employ constraints to control the parameter space of deep neural networks throughout training. The use of customised, appropriately designed constraints can reduce the vanishing/exploding gradients problem, improve smoothness of classification boundaries, control weight magnitudes and stabilize deep neural networks, and thus enhance the robustness of training algorithms and the generalization capabilities of neural networks. We provide a general approach to efficiently incorporate constraints into a stochastic gradient Langevin framework, allowing enhanced exploration of the loss landscape. We also present specific examples of constrained training methods motivated by orthogonality preservation for weight matrices and explicit weight normalizations. Discretization schemes are provided both for the overdamped formulation of Langevin dynamics and the underdamped form, in which momenta further improve sampling efficiency. These optimisation schemes can be used directly, without needing to adapt neural network architecture design choices or to modify the objective with regularization terms, and see performance improvements in classification tasks.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/leimkuhler21a.html
http://proceedings.mlr.press/v139/leimkuhler21a.htmlScalable Evaluation of Multi-Agent Reinforcement Learning with Melting PotExisting evaluation suites for multi-agent reinforcement learning (MARL) do not assess generalization to novel situations as their primary objective (unlike supervised learning benchmarks). Our contribution, Melting Pot, is a MARL evaluation suite that fills this gap and uses reinforcement learning to reduce the human labor required to create novel test scenarios. This works because one agent’s behavior constitutes (part of) another agent’s environment. To demonstrate scalability, we have created over 80 unique test scenarios covering a broad range of research topics such as social dilemmas, reciprocity, resource sharing, and task partitioning. We apply these test scenarios to standard MARL training algorithms, and demonstrate how Melting Pot reveals weaknesses not apparent from training performance alone.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/leibo21a.html
http://proceedings.mlr.press/v139/leibo21a.htmlStability and Generalization of Stochastic Gradient Methods for Minimax ProblemsMany machine learning problems can be formulated as minimax problems such as Generative Adversarial Networks (GANs), AUC maximization and robust estimation, to mention but a few. A substantial amount of studies are devoted to studying the convergence behavior of their stochastic gradient-type algorithms. In contrast, there is relatively little work on understanding their generalization, i.e., how the learning models built from training examples would behave on test examples. In this paper, we provide a comprehensive generalization analysis of stochastic gradient methods for minimax problems under both convex-concave and nonconvex-nonconcave cases through the lens of algorithmic stability. We establish a quantitative connection between stability and several generalization measures both in expectation and with high probability. For the convex-concave setting, our stability analysis shows that stochastic gradient descent ascent attains optimal generalization bounds for both smooth and nonsmooth minimax problems. We also establish generalization bounds for both weakly-convex-weakly-concave and gradient-dominated problems. We report preliminary experimental results to verify our theory.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/lei21b.html
http://proceedings.mlr.press/v139/lei21b.htmlNear-Optimal Linear Regression under Distribution ShiftTransfer learning is essential when sufficient data comes from the source domain, with scarce labeled data from the target domain. We develop estimators that achieve minimax linear risk for linear regression problems under distribution shift. Our algorithms cover different transfer learning settings including covariate shift and model shift. We also consider when data are generated from either linear or general nonlinear models. We show that linear minimax estimators are within an absolute constant of the minimax risk even among nonlinear estimators for various source/target distributions.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/lei21a.html
http://proceedings.mlr.press/v139/lei21a.htmlPEBBLE: Feedback-Efficient Interactive Reinforcement Learning via Relabeling Experience and Unsupervised Pre-trainingConveying complex objectives to reinforcement learning (RL) agents can often be difficult, involving meticulous design of reward functions that are sufficiently informative yet easy enough to provide. Human-in-the-loop RL methods allow practitioners to instead interactively teach agents through tailored feedback; however, such approaches have been challenging to scale since human feedback is very expensive. In this work, we aim to make this process more sample- and feedback-efficient. We present an off-policy, interactive RL algorithm that capitalizes on the strengths of both feedback and off-policy learning. Specifically, we learn a reward model by actively querying a teacher’s preferences between two clips of behavior and use it to train an agent. To enable off-policy learning, we relabel all the agent’s past experience when its reward model changes. We additionally show that pre-training our agents with unsupervised exploration substantially increases the mileage of its queries. We demonstrate that our approach is capable of learning tasks of higher complexity than previously considered by human-in-the-loop methods, including a variety of locomotion and robotic manipulation skills. We also show that our method is able to utilize real-time human feedback to effectively prevent reward exploitation and learn new behaviors that are difficult to specify with standard reward functions.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/lee21i.html
http://proceedings.mlr.press/v139/lee21i.htmlAchieving Near Instance-Optimality and Minimax-Optimality in Stochastic and Adversarial Linear Bandits SimultaneouslyIn this work, we develop linear bandit algorithms that automatically adapt to different environments. By plugging a novel loss estimator into the optimization problem that characterizes the instance-optimal strategy, our first algorithm not only achieves nearly instance-optimal regret in stochastic environments, but also works in corrupted environments with additional regret being the amount of corruption, while the state-of-the-art (Li et al., 2019) achieves neither instance-optimality nor the optimal dependence on the corruption amount. Moreover, by equipping this algorithm with an adversarial component and carefully-designed testings, our second algorithm additionally enjoys minimax-optimal regret in completely adversarial environments, which is the first of this kind to our knowledge. Finally, all our guarantees hold with high probability, while existing instance-optimal guarantees only hold in expectation.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/lee21h.html
http://proceedings.mlr.press/v139/lee21h.htmlSUNRISE: A Simple Unified Framework for Ensemble Learning in Deep Reinforcement LearningOff-policy deep reinforcement learning (RL) has been successful in a range of challenging domains. However, standard off-policy RL algorithms can suffer from several issues, such as instability in Q-learning and balancing exploration and exploitation. To mitigate these issues, we present SUNRISE, a simple unified ensemble method, which is compatible with various off-policy RL algorithms. SUNRISE integrates two key ingredients: (a) ensemble-based weighted Bellman backups, which re-weight target Q-values based on uncertainty estimates from a Q-ensemble, and (b) an inference method that selects actions using the highest upper-confidence bounds for efficient exploration. By enforcing the diversity between agents using Bootstrap with random initialization, we show that these different ideas are largely orthogonal and can be fruitfully integrated, together further improving the performance of existing off-policy RL algorithms, such as Soft Actor-Critic and Rainbow DQN, for both continuous and discrete control tasks on both low-dimensional and high-dimensional environments.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/lee21g.html
http://proceedings.mlr.press/v139/lee21g.htmlOptiDICE: Offline Policy Optimization via Stationary Distribution Correction EstimationWe consider the offline reinforcement learning (RL) setting where the agent aims to optimize the policy solely from the data without further environment interactions. In offline RL, the distributional shift becomes the primary source of difficulty, which arises from the deviation of the target policy being optimized from the behavior policy used for data collection. This typically causes overestimation of action values, which poses severe problems for model-free algorithms that use bootstrapping. To mitigate the problem, prior offline RL algorithms often used sophisticated techniques that encourage underestimation of action values, which introduces an additional set of hyperparameters that need to be tuned properly. In this paper, we present an offline RL algorithm that prevents overestimation in a more principled way. Our algorithm, OptiDICE, directly estimates the stationary distribution corrections of the optimal policy and does not rely on policy-gradients, unlike previous offline RL algorithms. Using an extensive set of benchmark datasets for offline RL, we show that OptiDICE performs competitively with the state-of-the-art methods.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/lee21f.html
http://proceedings.mlr.press/v139/lee21f.htmlContinual Learning in the Teacher-Student Setup: Impact of Task SimilarityContinual learning{—}the ability to learn many tasks in sequence{—}is critical for artificial learning systems. Yet standard training methods for deep networks often suffer from catastrophic forgetting, where learning new tasks erases knowledge of the earlier tasks. While catastrophic forgetting labels the problem, the theoretical reasons for interference between tasks remain unclear. Here, we attempt to narrow this gap between theory and practice by studying continual learning in the teacher-student setup. We extend previous analytical work on two-layer networks in the teacher-student setup to multiple teachers. Using each teacher to represent a different task, we investigate how the relationship between teachers affects the amount of forgetting and transfer exhibited by the student when the task switches. In line with recent work, we find that when tasks depend on similar features, intermediate task similarity leads to greatest forgetting. However, feature similarity is only one way in which tasks may be related. The teacher-student approach allows us to disentangle task similarity at the level of \emph{readouts} (hidden-to-output weights) as well as \emph{features} (input-to-hidden weights). We find a complex interplay between both types of similarity, initial transfer/forgetting rates, maximum transfer/forgetting, and the long-time (post-switch) amount of transfer/forgetting. Together, these results help illuminate the diverse factors contributing to catastrophic forgetting.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/lee21e.html
http://proceedings.mlr.press/v139/lee21e.htmlUnsupervised Embedding Adaptation via Early-Stage Feature Reconstruction for Few-Shot ClassificationWe propose unsupervised embedding adaptation for the downstream few-shot classification task. Based on findings that deep neural networks learn to generalize before memorizing, we develop Early-Stage Feature Reconstruction (ESFR) — a novel adaptation scheme with feature reconstruction and dimensionality-driven early stopping that finds generalizable features. Incorporating ESFR consistently improves the performance of baseline methods on all standard settings, including the recently proposed transductive method. ESFR used in conjunction with the transductive method further achieves state-of-the-art performance on mini-ImageNet, tiered-ImageNet, and CUB; especially with 1.2% 2.0% improvements in accuracy over the previous best performing method on 1-shot setting.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/lee21d.html
http://proceedings.mlr.press/v139/lee21d.htmlOn-the-fly Rectification for Robust Large-Vocabulary Topic InferenceAcross many data domains, co-occurrence statistics about the joint appearance of objects are powerfully informative. By transforming unsupervised learning problems into decompositions of co-occurrence statistics, spectral algorithms provide transparent and efficient algorithms for posterior inference such as latent topic analysis and community detection. As object vocabularies grow, however, it becomes rapidly more expensive to store and run inference algorithms on co-occurrence statistics. Rectifying co-occurrence, the key process to uphold model assumptions, becomes increasingly more vital in the presence of rare terms, but current techniques cannot scale to large vocabularies. We propose novel methods that simultaneously compress and rectify co-occurrence statistics, scaling gracefully with the size of vocabulary and the dimension of latent space. We also present new algorithms learning latent variables from the compressed statistics, and verify that our methods perform comparably to previous approaches on both textual and non-textual data.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/lee21c.html
http://proceedings.mlr.press/v139/lee21c.htmlFair Selective Classification Via SufficiencySelective classification is a powerful tool for decision-making in scenarios where mistakes are costly but abstentions are allowed. In general, by allowing a classifier to abstain, one can improve the performance of a model at the cost of reducing coverage and classifying fewer samples. However, recent work has shown, in some cases, that selective classification can magnify disparities between groups, and has illustrated this phenomenon on multiple real-world datasets. We prove that the sufficiency criterion can be used to mitigate these disparities by ensuring that selective classification increases performance on all groups, and introduce a method for mitigating the disparity in precision across the entire coverage scale based on this criterion. We then provide an upper bound on the conditional mutual information between the class label and sensitive attribute, conditioned on the learned features, which can be used as a regularizer to achieve fairer selective classification. The effectiveness of the method is demonstrated on the Adult, CelebA, Civil Comments, and CheXpert datasets.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/lee21b.html
http://proceedings.mlr.press/v139/lee21b.htmlSharing Less is More: Lifelong Learning in Deep Networks with Selective Layer TransferEffective lifelong learning across diverse tasks requires the transfer of diverse knowledge, yet transferring irrelevant knowledge may lead to interference and catastrophic forgetting. In deep networks, transferring the appropriate granularity of knowledge is as important as the transfer mechanism, and must be driven by the relationships among tasks. We first show that the lifelong learning performance of several current deep learning architectures can be significantly improved by transfer at the appropriate layers. We then develop an expectation-maximization (EM) method to automatically select the appropriate transfer configuration and optimize the task network weights. This EM-based selective transfer is highly effective, balancing transfer performance on all tasks with avoiding catastrophic forgetting, as demonstrated on three algorithms in several lifelong object classification scenarios.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/lee21a.html
http://proceedings.mlr.press/v139/lee21a.htmlGaussian Process-Based Real-Time Learning for Safety Critical ApplicationsThe safe operation of physical systems typically relies on high-quality models. Since a continuous stream of data is generated during run-time, such models are often obtained through the application of Gaussian process regression because it provides guarantees on the prediction error. Due to its high computational complexity, Gaussian process regression must be used offline on batches of data, which prevents applications, where a fast adaptation through online learning is necessary to ensure safety. In order to overcome this issue, we propose the LoG-GP. It achieves a logarithmic update and prediction complexity in the number of training points through the aggregation of locally active Gaussian process models. Under weak assumptions on the aggregation scheme, it inherits safety guarantees from exact Gaussian process regression. These theoretical advantages are exemplarily exploited in the design of a safe and data-efficient, online-learning control policy. The efficiency and performance of the proposed real-time learning approach is demonstrated in a comparison to state-of-the-art methods.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/lederer21a.html
http://proceedings.mlr.press/v139/lederer21a.htmlLAMDA: Label Matching Deep Domain AdaptationDeep domain adaptation (DDA) approaches have recently been shown to perform better than their shallow rivals with better modeling capacity on complex domains (e.g., image, structural data, and sequential data). The underlying idea is to learn domain invariant representations on a latent space that can bridge the gap between source and target domains. Several theoretical studies have established insightful understanding and the benefit of learning domain invariant features; however, they are usually limited to the case where there is no label shift, hence hindering its applicability. In this paper, we propose and study a new challenging setting that allows us to use a Wasserstein distance (WS) to not only quantify the data shift but also to define the label shift directly. We further develop a theory to demonstrate that minimizing the WS of the data shift leads to closing the gap between the source and target data distributions on the latent space (e.g., an intermediate layer of a deep net), while still being able to quantify the label shift with respect to this latent space. Interestingly, our theory can consequently explain certain drawbacks of learning domain invariant features on the latent space. Finally, grounded on the results and guidance of our developed theory, we propose the Label Matching Deep Domain Adaptation (LAMDA) approach that outperforms baselines on real-world datasets for DA problems.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/le21a.html
http://proceedings.mlr.press/v139/le21a.htmlImproved Regret Bound and Experience Replay in Regularized Policy IterationIn this work, we study algorithms for learning in infinite-horizon undiscounted Markov decision processes (MDPs) with function approximation. We first show that the regret analysis of the Politex algorithm (a version of regularized policy iteration) can be sharpened from $O(T^{3/4})$ to $O(\sqrt{T})$ under nearly identical assumptions, and instantiate the bound with linear function approximation. Our result provides the first high-probability $O(\sqrt{T})$ regret bound for a computationally efficient algorithm in this setting. The exact implementation of Politex with neural network function approximation is inefficient in terms of memory and computation. Since our analysis suggests that we need to approximate the average of the action-value functions of past policies well, we propose a simple efficient implementation where we train a single Q-function on a replay buffer with past data. We show that this often leads to superior performance over other implementation choices, especially in terms of wall-clock time. Our work also provides a novel theoretical justification for using experience replay within policy iteration algorithms.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/lazic21a.html
http://proceedings.mlr.press/v139/lazic21a.htmlMorphVAE: Generating Neural Morphologies from 3D-Walks using a Variational Autoencoder with Spherical Latent SpaceFor the past century, the anatomy of a neuron has been considered one of its defining features: The shape of a neuron’s dendrites and axon fundamentally determines what other neurons it can connect to. These neurites have been described using mathematical tools e.g. in the context of cell type classification, but generative models of these structures have only rarely been proposed and are often computationally inefficient. Here we propose MorphVAE, a sequence-to-sequence variational autoencoder with spherical latent space as a generative model for neural morphologies. The model operates on walks within the tree structure of a neuron and can incorporate expert annotations on a subset of the data using semi-supervised learning. We develop our model on artificially generated toy data and evaluate its performance on dendrites of excitatory cells and axons of inhibitory cells of mouse motor cortex (M1) and dendrites of retinal ganglion cells. We show that the learned latent feature space allows for better cell type discrimination than other commonly used features. By sampling new walks from the latent space we can easily construct new morphologies with a specified degree of similarity to their reference neuron, providing an efficient generative model for neural morphologies.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/laturnus21a.html
http://proceedings.mlr.press/v139/laturnus21a.htmlCountSketches, Feature Hashing and the Median of ThreeIn this paper, we revisit the classic CountSketch method, which is a sparse, random projection that transforms a (high-dimensional) Euclidean vector $v$ to a vector of dimension $(2t-1) s$, where $t, s > 0$ are integer parameters. It is known that a CountSketch allows estimating coordinates of $v$ with variance bounded by $\|v\|_2^2/s$. For $t > 1$, the estimator takes the median of $2t-1$ independent estimates, and the probability that the estimate is off by more than $2 \|v\|_2/\sqrt{s}$ is exponentially small in $t$. This suggests choosing $t$ to be logarithmic in a desired inverse failure probability. However, implementations of CountSketch often use a small, constant $t$. Previous work only predicts a constant factor improvement in this setting. Our main contribution is a new analysis of CountSketch, showing an improvement in variance to $O(\min\{\|v\|_1^2/s^2,\|v\|_2^2/s\})$ when $t > 1$. That is, the variance decreases proportionally to $s^{-2}$, asymptotically for large enough $s$.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/larsen21a.html
http://proceedings.mlr.press/v139/larsen21a.htmlEfficient Message Passing for 0–1 ILPs with Binary Decision DiagramsWe present a message passing method for 0{–}1 integer linear programs. Our algorithm is based on a decomposition of the original problem into subproblems that are represented as binary deci- sion diagrams. The resulting Lagrangean dual is solved iteratively by a series of efficient block coordinate ascent steps. Our method has linear iteration complexity in the size of the decomposi- tion and can be effectively parallelized. The char- acteristics of our approach are desirable towards solving ever larger problems arising in structured prediction. We present experimental results on combinatorial problems from MAP inference for Markov Random Fields, quadratic assignment, discrete tomography and cell tracking for develop- mental biology and show promising performance.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/lange21a.html
http://proceedings.mlr.press/v139/lange21a.htmlGraph Cuts Always Find a Global Optimum for Potts Models (With a Catch)We prove that the alpha-expansion algorithm for MAP inference always returns a globally optimal assignment for Markov Random Fields with Potts pairwise potentials, with a catch: the returned assignment is only guaranteed to be optimal for an instance within a small perturbation of the original problem instance. In other words, all local minima with respect to expansion moves are global minima to slightly perturbed versions of the problem. On "real-world" instances, MAP assignments of small perturbations of the problem should be very similar to the MAP assignment(s) of the original problem instance. We design an algorithm that can certify whether this is the case in practice. On several MAP inference problem instances from computer vision, this algorithm certifies that MAP solutions to all of these perturbations are very close to solutions of the original instance. These results taken together give a cohesive explanation for the good performance of "graph cuts" algorithms in practice. Every local expansion minimum is a global minimum in a small perturbation of the problem, and all of these global minima are close to the original solution.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/lang21a.html
http://proceedings.mlr.press/v139/lang21a.htmlDiscovering symbolic policies with deep reinforcement learningDeep reinforcement learning (DRL) has proven successful for many difficult control problems by learning policies represented by neural networks. However, the complexity of neural network-based policies{—}involving thousands of composed non-linear operators{—}can render them problematic to understand, trust, and deploy. In contrast, simple policies comprising short symbolic expressions can facilitate human understanding, while also being transparent and exhibiting predictable behavior. To this end, we propose deep symbolic policy, a novel approach to directly search the space of symbolic policies. We use an autoregressive recurrent neural network to generate control policies represented by tractable mathematical expressions, employing a risk-seeking policy gradient to maximize performance of the generated policies. To scale to environments with multi-dimensional action spaces, we propose an "anchoring" algorithm that distills pre-trained neural network-based policies into fully symbolic policies, one action dimension at a time. We also introduce two novel methods to improve exploration in DRL-based combinatorial optimization, building on ideas of entropy regularization and distribution initialization. Despite their dramatically reduced complexity, we demonstrate that discovered symbolic policies outperform seven state-of-the-art DRL algorithms in terms of average rank and average normalized episodic reward across eight benchmark environments.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/landajuela21a.html
http://proceedings.mlr.press/v139/landajuela21a.htmlStochastic Multi-Armed Bandits with Unrestricted Delay DistributionsWe study the stochastic Multi-Armed Bandit (MAB) problem with random delays in the feedback received by the algorithm. We consider two settings: the {\it reward dependent} delay setting, where realized delays may depend on the stochastic rewards, and the {\it reward-independent} delay setting. Our main contribution is algorithms that achieve near-optimal regret in each of the settings, with an additional additive dependence on the quantiles of the delay distribution. Our results do not make any assumptions on the delay distributions: in particular, we do not assume they come from any parametric family of distributions and allow for unbounded support and expectation; we further allow for the case of infinite delays where the algorithm might occasionally not observe any feedback.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/lancewicki21a.html
http://proceedings.mlr.press/v139/lancewicki21a.htmlGradient Disaggregation: Breaking Privacy in Federated Learning by Reconstructing the User Participant MatrixWe show that aggregated model updates in federated learning may be insecure. An untrusted central server may disaggregate user updates from sums of updates across participants given repeated observations, enabling the server to recover privileged information about individual users’ private training data via traditional gradient inference attacks. Our method revolves around reconstructing participant information (e.g: which rounds of training users participated in) from aggregated model updates by leveraging summary information from device analytics commonly used to monitor, debug, and manage federated learning systems. Our attack is parallelizable and we successfully disaggregate user updates on settings with up to thousands of participants. We quantitatively and qualitatively demonstrate significant improvements in the capability of various inference attacks on the disaggregated updates. Our attack enables the attribution of learned properties to individual users, violating anonymity, and shows that a determined central server may undermine the secure aggregation protocol to break individual users’ data privacy in federated learning.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/lam21b.html
http://proceedings.mlr.press/v139/lam21b.htmlModel Fusion for Personalized LearningProduction systems operating on a growing domain of analytic services often require generating warm-start solution models for emerging tasks with limited data. One potential approach to address this warm-start challenge is to adopt meta learning to generate a base model that can be adapted to solve unseen tasks with minimal fine-tuning. This however requires the training processes of previous solution models of existing tasks to be synchronized. This is not possible if these models were pre-trained separately on private data owned by different entities and cannot be synchronously re-trained. To accommodate for such scenarios, we develop a new personalized learning framework that synthesizes customized models for unseen tasks via fusion of independently pre-trained models of related tasks. We establish performance guarantee for the proposed framework and demonstrate its effectiveness on both synthetic and real datasets.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/lam21a.html
http://proceedings.mlr.press/v139/lam21a.htmlGeneralization Bounds in the Presence of Outliers: a Median-of-Means StudyIn contrast to the empirical mean, the Median-of-Means (MoM) is an estimator of the mean $\theta$ of a square integrable r.v. Z, around which accurate nonasymptotic confidence bounds can be built, even when Z does not exhibit a sub-Gaussian tail behavior. Thanks to the high confidence it achieves on heavy-tailed data, MoM has found various applications in machine learning, where it is used to design training procedures that are not sensitive to atypical observations. More recently, a new line of work is now trying to characterize and leverage MoM’s ability to deal with corrupted data. In this context, the present work proposes a general study of MoM’s concentration properties under the contamination regime, that provides a clear understanding on the impact of the outlier proportion and the number of blocks chosen. The analysis is extended to (multisample) U-statistics, i.e. averages over tuples of observations, that raise additional challenges due to the dependence induced. Finally, we show that the latter bounds can be used in a straightforward fashion to derive generalization guarantees for pairwise learning in a contaminated setting, and propose an algorithm to compute provably reliable decision functions.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/laforgue21a.html
http://proceedings.mlr.press/v139/laforgue21a.htmlAdaptive Newton Sketch: Linear-time Optimization with Quadratic Convergence and Effective Hessian DimensionalityWe propose a randomized algorithm with quadratic convergence rate for convex optimization problems with a self-concordant, composite, strongly convex objective function. Our method is based on performing an approximate Newton step using a random projection of the Hessian. Our first contribution is to show that, at each iteration, the embedding dimension (or sketch size) can be as small as the effective dimension of the Hessian matrix. Leveraging this novel fundamental result, we design an algorithm with a sketch size proportional to the effective dimension and which exhibits a quadratic rate of convergence. This result dramatically improves on the classical linear-quadratic convergence rates of state-of-the-art sub-sampled Newton methods. However, in most practical cases, the effective dimension is not known beforehand, and this raises the question of how to pick a sketch size as small as the effective dimension while preserving a quadratic convergence rate. Our second and main contribution is thus to propose an adaptive sketch size algorithm with quadratic convergence rate and which does not require prior knowledge or estimation of the effective dimension: at each iteration, it starts with a small sketch size, and increases it until quadratic progress is achieved. Importantly, we show that the embedding dimension remains proportional to the effective dimension throughout the entire path and that our method achieves state-of-the-art computational complexity for solving convex optimization programs with a strongly convex component. We discuss and illustrate applications to linear and quadratic programming, as well as logistic regression and other generalized linear models.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/lacotte21a.html
http://proceedings.mlr.press/v139/lacotte21a.htmlOn the price of explainability for some clustering problemsThe price of explainability for a clustering task can be defined as the unavoidable loss, in terms of the objective function, if we force the final partition to be explainable. Here, we study this price for the following clustering problems: $k$-means, $k$-medians, $k$-centers and maximum-spacing. We provide upper and lower bounds for a natural model where explainability is achieved via decision trees. For the $k$-means and $k$-medians problems our upper bounds improve those obtained by [Dasgupta et. al, ICML 20] for low dimensions. Another contribution is a simple and efficient algorithm for building explainable clusterings for the $k$-means problem. We provide empirical evidence that its performance is better than the current state of the art for decision-tree based explainable clustering.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/laber21a.html
http://proceedings.mlr.press/v139/laber21a.htmlASAM: Adaptive Sharpness-Aware Minimization for Scale-Invariant Learning of Deep Neural NetworksRecently, learning algorithms motivated from sharpness of loss surface as an effective measure of generalization gap have shown state-of-the-art performances. Nevertheless, sharpness defined in a rigid region with a fixed radius, has a drawback in sensitivity to parameter re-scaling which leaves the loss unaffected, leading to weakening of the connection between sharpness and generalization gap. In this paper, we introduce the concept of adaptive sharpness which is scale-invariant and propose the corresponding generalization bound. We suggest a novel learning method, adaptive sharpness-aware minimization (ASAM), utilizing the proposed generalization bound. Experimental results in various benchmark datasets show that ASAM contributes to significant improvement of model generalization performance.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/kwon21b.html
http://proceedings.mlr.press/v139/kwon21b.htmlTargeted Data Acquisition for Evolving Negotiation AgentsSuccessful negotiators must learn how to balance optimizing for self-interest and cooperation. Yet current artificial negotiation agents often heavily depend on the quality of the static datasets they were trained on, limiting their capacity to fashion an adaptive response balancing self-interest and cooperation. For this reason, we find that these agents can achieve either high utility or cooperation, but not both. To address this, we introduce a targeted data acquisition framework where we guide the exploration of a reinforcement learning agent using annotations from an expert oracle. The guided exploration incentivizes the learning agent to go beyond its static dataset and develop new negotiation strategies. We show that this enables our agents to obtain higher-reward and more Pareto-optimal solutions when negotiating with both simulated and human partners compared to standard supervised learning and reinforcement learning methods. This trend additionally holds when comparing agents using our targeted data acquisition framework to variants of agents trained with a mix of supervised learning and reinforcement learning, or to agents using tailored reward functions that explicitly optimize for utility and Pareto-optimality.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/kwon21a.html
http://proceedings.mlr.press/v139/kwon21a.htmlMeta-Thompson SamplingEfficient exploration in bandits is a fundamental online learning problem. We propose a variant of Thompson sampling that learns to explore better as it interacts with bandit instances drawn from an unknown prior. The algorithm meta-learns the prior and thus we call it MetaTS. We propose several efficient implementations of MetaTS and analyze it in Gaussian bandits. Our analysis shows the benefit of meta-learning and is of a broader interest, because we derive a novel prior-dependent Bayes regret bound for Thompson sampling. Our theory is complemented by empirical evaluation, which shows that MetaTS quickly adapts to the unknown prior.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/kveton21a.html
http://proceedings.mlr.press/v139/kveton21a.htmlA Scalable Second Order Method for Ill-Conditioned Matrix Completion from Few SamplesWe propose an iterative algorithm for low-rank matrix completion with that can be interpreted as an iteratively reweighted least squares (IRLS) algorithm, a saddle-escaping smoothing Newton method or a variable metric proximal gradient method applied to a non-convex rank surrogate. It combines the favorable data-efficiency of previous IRLS approaches with an improved scalability by several orders of magnitude. We establish the first local convergence guarantee from a minimal number of samples for that class of algorithms, showing that the method attains a local quadratic convergence rate. Furthermore, we show that the linear systems to be solved are well-conditioned even for very ill-conditioned ground truth matrices. We provide extensive experiments, indicating that unlike many state-of-the-art approaches, our method is able to complete very ill-conditioned matrices with a condition number of up to $10^{10}$ from few samples, while being competitive in its scalability.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/kummerle21a.html
http://proceedings.mlr.press/v139/kummerle21a.htmlImplicit rate-constrained optimization of non-decomposable objectivesWe consider a popular family of constrained optimization problems arising in machine learning that involve optimizing a non-decomposable evaluation metric with a certain thresholded form, while constraining another metric of interest. Examples of such problems include optimizing false negative rate at a fixed false positive rate, optimizing precision at a fixed recall, optimizing the area under the precision-recall or ROC curves, etc. Our key idea is to formulate a rate-constrained optimization that expresses the threshold parameter as a function of the model parameters via the Implicit Function theorem. We show how the resulting optimization problem can be solved using standard gradient based methods. Experiments on benchmark datasets demonstrate the effectiveness of our proposed method over existing state-of-the-art approaches for these problems.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/kumar21b.html
http://proceedings.mlr.press/v139/kumar21b.htmlBayesian Structural Adaptation for Continual LearningContinual Learning is a learning paradigm where learning systems are trained on a sequence of tasks. The goal here is to perform well on the current task without suffering from a performance drop on the previous tasks. Two notable directions among the recent advances in continual learning with neural networks are (1) variational Bayes based regularization by learning priors from previous tasks, and, (2) learning the structure of deep networks to adapt to new tasks. So far, these two approaches have been largely orthogonal. We present a novel Bayesian framework based on continually learning the structure of deep neural networks, to unify these distinct yet complementary approaches. The proposed framework learns the deep structure for each task by learning which weights to be used, and supports inter-task transfer through the overlapping of different sparse subsets of weights learned by different tasks. An appealing aspect of our proposed continual learning framework is that it is applicable to both discriminative (supervised) and generative (unsupervised) settings. Experimental results on supervised and unsupervised benchmarks demonstrate that our approach performs comparably or better than recent advances in continual learning.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/kumar21a.html
http://proceedings.mlr.press/v139/kumar21a.htmlDifferentially Private Bayesian Inference for Generalized Linear ModelsGeneralized linear models (GLMs) such as logistic regression are among the most widely used arms in data analyst’s repertoire and often used on sensitive datasets. A large body of prior works that investigate GLMs under differential privacy (DP) constraints provide only private point estimates of the regression coefficients, and are not able to quantify parameter uncertainty. In this work, with logistic and Poisson regression as running examples, we introduce a generic noise-aware DP Bayesian inference method for a GLM at hand, given a noisy sum of summary statistics. Quantifying uncertainty allows us to determine which of the regression coefficients are statistically significantly different from zero. We provide a previously unknown tight privacy analysis and experimentally demonstrate that the posteriors obtained from our model, while adhering to strong privacy guarantees, are close to the non-private posteriors.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/kulkarni21a.html
http://proceedings.mlr.press/v139/kulkarni21a.htmlNear-Optimal Confidence Sequences for Bounded Random VariablesMany inference problems, such as sequential decision problems like A/B testing, adaptive sampling schemes like bandit selection, are often online in nature. The fundamental problem for online inference is to provide a sequence of confidence intervals that are valid uniformly over the growing-into-infinity sample sizes. To address this question, we provide a near-optimal confidence sequence for bounded random variables by utilizing Bentkus’ concentration results. We show that it improves on the existing approaches that use the Cram{é}r-Chernoff technique such as the Hoeffding, Bernstein, and Bennett inequalities. The resulting confidence sequence is confirmed to be favorable in synthetic coverage problems, adaptive stopping algorithms, and multi-armed bandit problems.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/kuchibhotla21a.html
http://proceedings.mlr.press/v139/kuchibhotla21a.htmlOut-of-Distribution Generalization via Risk Extrapolation (REx)Distributional shift is one of the major obstacles when transferring machine learning prediction systems from the lab to the real world. To tackle this problem, we assume that variation across training domains is representative of the variation we might encounter at test time, but also that shifts at test time may be more extreme in magnitude. In particular, we show that reducing differences in risk across training domains can reduce a model’s sensitivity to a wide range of extreme distributional shifts, including the challenging setting where the input contains both causal and anti-causal elements. We motivate this approach, Risk Extrapolation (REx), as a form of robust optimization over a perturbation set of extrapolated domains (MM-REx), and propose a penalty on the variance of training risks (V-REx) as a simpler variant. We prove that variants of REx can recover the causal mechanisms of the targets, while also providing robustness to changes in the input distribution (“covariate shift”). By appropriately trading-off robustness to causally induced distributional shifts and covariate shift, REx is able to outperform alternative methods such as Invariant Risk Minimization in situations where these types of shift co-occur.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/krueger21a.html
http://proceedings.mlr.press/v139/krueger21a.htmlAdapting to misspecification in contextual bandits with offline regression oraclesComputationally efficient contextual bandits are often based on estimating a predictive model of rewards given contexts and arms using past data. However, when the reward model is not well-specified, the bandit algorithm may incur unexpected regret, so recent work has focused on algorithms that are robust to misspecification. We propose a simple family of contextual bandit algorithms that adapt to misspecification error by reverting to a good safe policy when there is evidence that misspecification is causing a regret increase. Our algorithm requires only an offline regression oracle to ensure regret guarantees that gracefully degrade in terms of a measure of the average misspecification level. Compared to prior work, we attain similar regret guarantees, but we do no rely on a master algorithm, and do not require more robust oracles like online or constrained regression oracles (e.g., Foster et al. (2020), Krishnamurthy et al. (2020)). This allows us to design algorithms for more general function approximation classes.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/krishnamurthy21a.html
http://proceedings.mlr.press/v139/krishnamurthy21a.htmlRevisiting Peng’s Q($λ$) for Modern Reinforcement LearningOff-policy multi-step reinforcement learning algorithms consist of conservative and non-conservative algorithms: the former actively cut traces, whereas the latter do not. Recently, Munos et al. (2016) proved the convergence of conservative algorithms to an optimal Q-function. In contrast, non-conservative algorithms are thought to be unsafe and have a limited or no theoretical guarantee. Nonetheless, recent studies have shown that non-conservative algorithms empirically outperform conservative ones. Motivated by the empirical results and the lack of theory, we carry out theoretical analyses of Peng’s Q($\lambda$), a representative example of non-conservative algorithms. We prove that \emph{it also converges to an optimal policy} provided that the behavior policy slowly tracks a greedy policy in a way similar to conservative policy iteration. Such a result has been conjectured to be true but has not been proven. We also experiment with Peng’s Q($\lambda$) in complex continuous control tasks, confirming that Peng’s Q($\lambda$) often outperforms conservative algorithms despite its simplicity. These results indicate that Peng’s Q($\lambda$), which was thought to be unsafe, is a theoretically-sound and practically effective algorithm.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/kozuno21a.html
http://proceedings.mlr.press/v139/kozuno21a.htmlADOM: Accelerated Decentralized Optimization Method for Time-Varying NetworksWe propose ADOM – an accelerated method for smooth and strongly convex decentralized optimization over time-varying networks. ADOM uses a dual oracle, i.e., we assume access to the gradient of the Fenchel conjugate of the individual loss functions. Up to a constant factor, which depends on the network structure only, its communication complexity is the same as that of accelerated Nesterov gradient method. To the best of our knowledge, only the algorithm of Rogozin et al. (2019) has a convergence rate with similar properties. However, their algorithm converges under the very restrictive assumption that the number of network changes can not be greater than a tiny percentage of the number of iterations. This assumption is hard to satisfy in practice, as the network topology changes usually can not be controlled. In contrast, ADOM merely requires the network to stay connected throughout time.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/kovalev21a.html
http://proceedings.mlr.press/v139/kovalev21a.htmlOffline Reinforcement Learning with Fisher Divergence Critic RegularizationMany modern approaches to offline Reinforcement Learning (RL) utilize behavior regularization, typically augmenting a model-free actor critic algorithm with a penalty measuring divergence of the policy from the offline data. In this work, we propose an alternative approach to encouraging the learned policy to stay close to the data, namely parameterizing the critic as the log-behavior-policy, which generated the offline data, plus a state-action value offset term, which can be learned using a neural network. Behavior regularization then corresponds to an appropriate regularizer on the offset term. We propose using a gradient penalty regularizer for the offset term and demonstrate its equivalence to Fisher divergence regularization, suggesting connections to the score matching and generative energy-based model literature. We thus term our resulting algorithm Fisher-BRC (Behavior Regularized Critic). On standard offline RL benchmarks, Fisher-BRC achieves both improved performance and faster convergence over existing state-of-the-art methods.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/kostrikov21a.html
http://proceedings.mlr.press/v139/kostrikov21a.htmlHigh Confidence Generalization for Reinforcement LearningWe present several classes of reinforcement learning algorithms that safely generalize to Markov decision processes (MDPs) not seen during training. Specifically, we study the setting in which some set of MDPs is accessible for training. The goal is to generalize safely to MDPs that are sampled from the same distribution, but which may not be in the set accessible for training. For various definitions of safety, our algorithms give probabilistic guarantees that agents can safely generalize to MDPs that are sampled from the same distribution but are not necessarily in the training set. These algorithms are a type of Seldonian algorithm (Thomas et al., 2019), which is a class of machine learning algorithms that return models with probabilistic safety guarantees for user-specified definitions of safety.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/kostas21a.html
http://proceedings.mlr.press/v139/kostas21a.htmlActive Testing: Sample-Efficient Model EvaluationWe introduce a new framework for sample-efficient model evaluation that we call active testing. While approaches like active learning reduce the number of labels needed for model training, existing literature largely ignores the cost of labeling test data, typically unrealistically assuming large test sets for model evaluation. This creates a disconnect to real applications, where test labels are important and just as expensive, e.g. for optimizing hyperparameters. Active testing addresses this by carefully selecting the test points to label, ensuring model evaluation is sample-efficient. To this end, we derive theoretically-grounded and intuitive acquisition strategies that are specifically tailored to the goals of active testing, noting these are distinct to those of active learning. As actively selecting labels introduces a bias; we further show how to remove this bias while reducing the variance of the estimator at the same time. Active testing is easy to implement and can be applied to any supervised machine learning method. We demonstrate its effectiveness on models including WideResNets and Gaussian processes on datasets including Fashion-MNIST and CIFAR-100.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/kossen21a.html
http://proceedings.mlr.press/v139/kossen21a.htmlNeRF-VAE: A Geometry Aware 3D Scene Generative ModelWe propose NeRF-VAE, a 3D scene generative model that incorporates geometric structure via Neural Radiance Fields (NeRF) and differentiable volume rendering. In contrast to NeRF, our model takes into account shared structure across scenes, and is able to infer the structure of a novel scene—without the need to re-train—using amortized inference. NeRF-VAE’s explicit 3D rendering process further contrasts previous generative models with convolution-based rendering which lacks geometric structure. Our model is a VAE that learns a distribution over radiance fields by conditioning them on a latent scene representation. We show that, once trained, NeRF-VAE is able to infer and render geometrically-consistent scenes from previously unseen 3D environments of synthetic scenes using very few input images. We further demonstrate that NeRF-VAE generalizes well to out-of-distribution cameras, while convolutional models do not. Finally, we introduce and study an attention-based conditioning mechanism of NeRF-VAE’s decoder, which improves model performance.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/kosiorek21a.html
http://proceedings.mlr.press/v139/kosiorek21a.htmlBoosting the Throughput and Accelerator Utilization of Specialized CNN Inference Beyond Increasing Batch SizeDatacenter vision systems widely use small, specialized convolutional neural networks (CNNs) trained on specific tasks for high-throughput inference. These settings employ accelerators with massive computational capacity, but which specialized CNNs underutilize due to having low arithmetic intensity. This results in suboptimal application-level throughput and poor returns on accelerator investment. Increasing batch size is the only known way to increase both application-level throughput and accelerator utilization for inference, but yields diminishing returns; specialized CNNs poorly utilize accelerators even with large batch size. We propose FoldedCNNs, a new approach to CNN design that increases inference throughput and utilization beyond large batch size. FoldedCNNs rethink the structure of inputs and layers of specialized CNNs to boost arithmetic intensity: in FoldedCNNs, f images with C channels each are concatenated into a single input with fC channels and jointly classified by a wider CNN. Increased arithmetic intensity in FoldedCNNs increases the throughput and GPU utilization of specialized CNN inference by up to 2.5x and 2.8x, with accuracy close to the original CNN in most cases.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/kosaian21a.html
http://proceedings.mlr.press/v139/kosaian21a.htmlKernel Stein Discrepancy DescentAmong dissimilarities between probability distributions, the Kernel Stein Discrepancy (KSD) has received much interest recently. We investigate the properties of its Wasserstein gradient flow to approximate a target probability distribution $\pi$ on $\mathbb{R}^d$, known up to a normalization constant. This leads to a straightforwardly implementable, deterministic score-based method to sample from $\pi$, named KSD Descent, which uses a set of particles to approximate $\pi$. Remarkably, owing to a tractable loss function, KSD Descent can leverage robust parameter-free optimization schemes such as L-BFGS; this contrasts with other popular particle-based schemes such as the Stein Variational Gradient Descent algorithm. We study the convergence properties of KSD Descent and demonstrate its practical relevance. However, we also highlight failure cases by showing that the algorithm can get stuck in spurious local minima.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/korba21a.html
http://proceedings.mlr.press/v139/korba21a.htmlEvaluating Robustness of Predictive Uncertainty Estimation: Are Dirichlet-based Models Reliable?Dirichlet-based uncertainty (DBU) models are a recent and promising class of uncertainty-aware models. DBU models predict the parameters of a Dirichlet distribution to provide fast, high-quality uncertainty estimates alongside with class predictions. In this work, we present the first large-scale, in-depth study of the robustness of DBU models under adversarial attacks. Our results suggest that uncertainty estimates of DBU models are not robust w.r.t. three important tasks: (1) indicating correctly and wrongly classified samples; (2) detecting adversarial examples; and (3) distinguishing between in-distribution (ID) and out-of-distribution (OOD) data. Additionally, we explore the first approaches to make DBU mod- els more robust. While adversarial training has a minor effect, our median smoothing based ap- proach significantly increases robustness of DBU models.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/kopetzki21a.html
http://proceedings.mlr.press/v139/kopetzki21a.htmlA Distribution-dependent Analysis of Meta LearningA key problem in the theory of meta-learning is to understand how the task distributions influence transfer risk, the expected error of a meta-learner on a new task drawn from the unknown task distribution. In this paper, focusing on fixed design linear regression with Gaussian noise and a Gaussian task (or parameter) distribution, we give distribution-dependent lower bounds on the transfer risk of any algorithm, while we also show that a novel, weighted version of the so-called biased regularized regression method is able to match these lower bounds up to a fixed constant factor. Notably, the weighting is derived from the covariance of the Gaussian task distribution. Altogether, our results provide a precise characterization of the difficulty of meta-learning in this Gaussian setting. While this problem setting may appear simple, we show that it is rich enough to unify the “parameter sharing” and “representation learning” streams of meta-learning; in particular, representation learning is obtained as the special case when the covariance matrix of the task distribution is unknown. For this case we propose to adopt the EM method, which is shown to enjoy efficient updates in our case. The paper is completed by an empirical study of EM. In particular, our experimental results show that the EM algorithm can attain the lower bound as the number of tasks grows, while the algorithm is also successful in competing with its alternatives when used in a representation learning context.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/konobeev21a.html
http://proceedings.mlr.press/v139/konobeev21a.htmlConsensus Control for Decentralized Deep LearningDecentralized training of deep learning models enables on-device learning over networks, as well as efficient scaling to large compute clusters. Experiments in earlier works reveal that, even in a data-center setup, decentralized training often suffers from the degradation in the quality of the model: the training and test performance of models trained in a decentralized fashion is in general worse than that of models trained in a centralized fashion, and this performance drop is impacted by parameters such as network size, communication topology and data partitioning. We identify the changing consensus distance between devices as a key parameter to explain the gap between centralized and decentralized training. We show in theory that when the training consensus distance is lower than a critical quantity, decentralized training converges as fast as the centralized counterpart. We empirically validate that the relation between generalization performance and consensus distance is consistent with this theoretical observation. Our empirical insights allow the principled design of better decentralized training schemes that mitigate the performance drop. To this end, we provide practical training guidelines and exemplify its effectiveness on the data-center setup as the important first step.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/kong21a.html
http://proceedings.mlr.press/v139/kong21a.htmlA Lower Bound for the Sample Complexity of Inverse Reinforcement LearningInverse reinforcement learning (IRL) is the task of finding a reward function that generates a desired optimal policy for a given Markov Decision Process (MDP). This paper develops an information-theoretic lower bound for the sample complexity of the finite state, finite action IRL problem. A geometric construction of $\beta$-strict separable IRL problems using spherical codes is considered. Properties of the ensemble size as well as the Kullback-Leibler divergence between the generated trajectories are derived. The resulting ensemble is then used along with Fano’s inequality to derive a sample complexity lower bound of $O(n \log n)$, where $n$ is the number of states in the MDP.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/komanduru21a.html
http://proceedings.mlr.press/v139/komanduru21a.htmlOne-sided Frank-Wolfe algorithms for saddle problemsWe study a class of convex-concave saddle-point problems of the form $\min_x\max_y ⟨Kx,y⟩+f_{\cal P}(x)-h^*(y)$ where $K$ is a linear operator, $f_{\cal P}$ is the sum of a convex function $f$ with a Lipschitz-continuous gradient and the indicator function of a bounded convex polytope ${\cal P}$, and $h^\ast$ is a convex (possibly nonsmooth) function. Such problem arises, for example, as a Lagrangian relaxation of various discrete optimization problems. Our main assumptions are the existence of an efficient {\em linear minimization oracle} ($lmo$) for $f_{\cal P}$ and an efficient {\em proximal map} ($prox$) for $h^*$ which motivate the solution via a blend of proximal primal-dual algorithms and Frank-Wolfe algorithms. In case $h^*$ is the indicator function of a linear constraint and function $f$ is quadratic, we show a $O(1/n^2)$ convergence rate on the dual objective, requiring $O(n \log n)$ calls of $lmo$. If the problem comes from the constrained optimization problem $\min_{x\in\mathbb R^d}\{f_{\cal P}(x)\:|\:Ax-b=0\}$ then we additionally get bound $O(1/n^2)$ both on the primal gap and on the infeasibility gap. In the most general case, we show a $O(1/n)$ convergence rate of the primal-dual gap again requiring $O(n\log n)$ calls of $lmo$. To the best of our knowledge, this improves on the known convergence rates for the considered class of saddle-point problems. We show applications to labeling problems frequently appearing in machine learning and computer vision.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/kolmogorov21a.html
http://proceedings.mlr.press/v139/kolmogorov21a.htmlWILDS: A Benchmark of in-the-Wild Distribution ShiftsDistribution shifts—where the training distribution differs from the test distribution—can substantially degrade the accuracy of machine learning (ML) systems deployed in the wild. Despite their ubiquity in the real-world deployments, these distribution shifts are under-represented in the datasets widely used in the ML community today. To address this gap, we present WILDS, a curated benchmark of 10 datasets reflecting a diverse range of distribution shifts that naturally arise in real-world applications, such as shifts across hospitals for tumor identification; across camera traps for wildlife monitoring; and across time and location in satellite imaging and poverty mapping. On each dataset, we show that standard training yields substantially lower out-of-distribution than in-distribution performance. This gap remains even with models trained by existing methods for tackling distribution shifts, underscoring the need for new methods for training models that are more robust to the types of distribution shifts that arise in practice. To facilitate method development, we provide an open-source package that automates dataset loading, contains default model architectures and hyperparameters, and standardizes evaluations. The full paper, code, and leaderboards are available at https://wilds.stanford.edu.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/koh21a.html
http://proceedings.mlr.press/v139/koh21a.htmlRepresentational aspects of depth and conditioning in normalizing flowsNormalizing flows are among the most popular paradigms in generative modeling, especially for images, primarily because we can efficiently evaluate the likelihood of a data point. This is desirable both for evaluating the fit of a model, and for ease of training, as maximizing the likelihood can be done by gradient descent. However, training normalizing flows comes with difficulties as well: models which produce good samples typically need to be extremely deep – which comes with accompanying vanishing/exploding gradient problems. A very related problem is that they are often poorly \emph{conditioned}: since they are parametrized as invertible maps from $\mathbb{R}^d \to \mathbb{R}^d$, and typical training data like images intuitively is lower-dimensional, the learned maps often have Jacobians that are close to being singular. In our paper, we tackle representational aspects around depth and conditioning of normalizing flows: both for general invertible architectures, and for a particular common architecture, affine couplings. We prove that $\Theta(1)$ affine coupling layers suffice to exactly represent a permutation or $1 \times 1$ convolution, as used in GLOW, showing that representationally the choice of partition is not a bottleneck for depth. We also show that shallow affine coupling networks are universal approximators in Wasserstein distance if ill-conditioning is allowed, and experimentally investigate related phenomena involving padding. Finally, we show a depth lower bound for general flow architectures with few neurons per layer and bounded Lipschitz constant.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/koehler21a.html
http://proceedings.mlr.press/v139/koehler21a.htmlScalable Optimal Transport in High Dimensions for Graph Distances, Embedding Alignment, and MoreThe current best practice for computing optimal transport (OT) is via entropy regularization and Sinkhorn iterations. This algorithm runs in quadratic time as it requires the full pairwise cost matrix, which is prohibitively expensive for large sets of objects. In this work we propose two effective log-linear time approximations of the cost matrix: First, a sparse approximation based on locality sensitive hashing (LSH) and, second, a Nystr{ö}m approximation with LSH-based sparse corrections, which we call locally corrected Nystr{ö}m (LCN). These approximations enable general log-linear time algorithms for entropy-regularized OT that perform well even for the complex, high-dimensional spaces common in deep learning. We analyse these approximations theoretically and evaluate them experimentally both directly and end-to-end as a component for real-world applications. Using our approximations for unsupervised word embedding alignment enables us to speed up a state-of-the-art method by a factor of 3 while also improving the accuracy by 3.1 percentage points without any additional model changes. For graph distance regression we propose the graph transport network (GTN), which combines graph neural networks (GNNs) with enhanced Sinkhorn. GTN outcompetes previous models by 48% and still scales log-linearly in the number of nodes.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/klicpera21a.html
http://proceedings.mlr.press/v139/klicpera21a.htmlCLOCS: Contrastive Learning of Cardiac Signals Across Space, Time, and PatientsThe healthcare industry generates troves of unlabelled physiological data. This data can be exploited via contrastive learning, a self-supervised pre-training method that encourages representations of instances to be similar to one another. We propose a family of contrastive learning methods, CLOCS, that encourages representations across space, time, \textit{and} patients to be similar to one another. We show that CLOCS consistently outperforms the state-of-the-art methods, BYOL and SimCLR, when performing a linear evaluation of, and fine-tuning on, downstream tasks. We also show that CLOCS achieves strong generalization performance with only 25% of labelled training data. Furthermore, our training procedure naturally generates patient-specific representations that can be used to quantify patient-similarity.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/kiyasseh21a.html
http://proceedings.mlr.press/v139/kiyasseh21a.htmlBias-Robust Bayesian Optimization via Dueling BanditsWe consider Bayesian optimization in settings where observations can be adversarially biased, for example by an uncontrolled hidden confounder. Our first contribution is a reduction of the confounded setting to the dueling bandit model. Then we propose a novel approach for dueling bandits based on information-directed sampling (IDS). Thereby, we obtain the first efficient kernelized algorithm for dueling bandits that comes with cumulative regret guarantees. Our analysis further generalizes a previously proposed semi-parametric linear bandit model to non-linear reward functions, and uncovers interesting links to doubly-robust estimation.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/kirschner21a.html
http://proceedings.mlr.press/v139/kirschner21a.htmlViLT: Vision-and-Language Transformer Without Convolution or Region SupervisionVision-and-Language Pre-training (VLP) has improved performance on various joint vision-and-language downstream tasks. Current approaches to VLP heavily rely on image feature extraction processes, most of which involve region supervision (e.g., object detection) and the convolutional architecture (e.g., ResNet). Although disregarded in the literature, we find it problematic in terms of both (1) efficiency/speed, that simply extracting input features requires much more computation than the multimodal interaction steps; and (2) expressive power, as it is upper bounded to the expressive power of the visual embedder and its predefined visual vocabulary. In this paper, we present a minimal VLP model, Vision-and-Language Transformer (ViLT), monolithic in the sense that the processing of visual inputs is drastically simplified to just the same convolution-free manner that we process textual inputs. We show that ViLT is up to tens of times faster than previous VLP models, yet with competitive or better downstream task performance. Our code and pre-trained weights are available at https://github.com/dandelin/vilt.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/kim21k.html
http://proceedings.mlr.press/v139/kim21k.htmlUnsupervised Skill Discovery with Bottleneck Option LearningHaving the ability to acquire inherent skills from environments without any external rewards or supervision like humans is an important problem. We propose a novel unsupervised skill discovery method named Information Bottleneck Option Learning (IBOL). On top of the linearization of environments that promotes more various and distant state transitions, IBOL enables the discovery of diverse skills. It provides the abstraction of the skills learned with the information bottleneck framework for the options with improved stability and encouraged disentanglement. We empirically demonstrate that IBOL outperforms multiple state-of-the-art unsupervised skill discovery methods on the information-theoretic evaluations and downstream tasks in MuJoCo environments, including Ant, HalfCheetah, Hopper and D’Kitty. Our code is available at https://vision.snu.ac.kr/projects/ibol.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/kim21j.html
http://proceedings.mlr.press/v139/kim21j.htmlThe Lipschitz Constant of Self-AttentionLipschitz constants of neural networks have been explored in various contexts in deep learning, such as provable adversarial robustness, estimating Wasserstein distance, stabilising training of GANs, and formulating invertible neural networks. Such works have focused on bounding the Lipschitz constant of fully connected or convolutional networks, composed of linear maps and pointwise non-linearities. In this paper, we investigate the Lipschitz constant of self-attention, a non-linear neural network module widely used in sequence modelling. We prove that the standard dot-product self-attention is not Lipschitz for unbounded input domain, and propose an alternative L2 self-attention that is Lipschitz. We derive an upper bound on the Lipschitz constant of L2 self-attention and provide empirical evidence for its asymptotic tightness. To demonstrate the practical relevance of our theoretical work, we formulate invertible self-attention and use it in a Transformer-based architecture for a character-level language modelling task.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/kim21i.html
http://proceedings.mlr.press/v139/kim21i.htmlInferring Latent Dynamics Underlying Neural Population Activity via Neural Differential EquationsAn important problem in systems neuroscience is to identify the latent dynamics underlying neural population activity. Here we address this problem by introducing a low-dimensional nonlinear model for latent neural population dynamics using neural ordinary differential equations (neural ODEs), with noisy sensory inputs and Poisson spike train outputs. We refer to this as the Poisson Latent Neural Differential Equations (PLNDE) model. We apply the PLNDE framework to a variety of synthetic datasets, and show that it accurately infers the phase portraits and fixed points of nonlinear systems augmented to produce spike train data, including the FitzHugh-Nagumo oscillator, a 3-dimensional nonlinear spiral, and a nonlinear sensory decision-making model with attractor dynamics. Our model significantly outperforms existing methods at inferring single-trial neural firing rates and the corresponding latent trajectories that generated them, especially in the regime where the spike counts and number of trials are low. We then apply our model to multi-region neural population recordings from medial frontal cortex of rats performing an auditory decision-making task. Our model provides a general, interpretable framework for investigating the neural mechanisms of decision-making and other cognitive computations through the lens of dynamical systems.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/kim21h.html
http://proceedings.mlr.press/v139/kim21h.htmlA Policy Gradient Algorithm for Learning to Learn in Multiagent Reinforcement LearningA fundamental challenge in multiagent reinforcement learning is to learn beneficial behaviors in a shared environment with other simultaneously learning agents. In particular, each agent perceives the environment as effectively non-stationary due to the changing policies of other agents. Moreover, each agent is itself constantly learning, leading to natural non-stationarity in the distribution of experiences encountered. In this paper, we propose a novel meta-multiagent policy gradient theorem that directly accounts for the non-stationary policy dynamics inherent to multiagent learning settings. This is achieved by modeling our gradient updates to consider both an agent’s own non-stationary policy dynamics and the non-stationary policy dynamics of other agents in the environment. We show that our theoretically grounded approach provides a general solution to the multiagent learning problem, which inherently comprises all key aspects of previous state of the art approaches on this topic. We test our method on a diverse suite of multiagent benchmarks and demonstrate a more efficient ability to adapt to new agents as they learn than baseline methods across the full spectrum of mixed incentive, competitive, and cooperative domains.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/kim21g.html
http://proceedings.mlr.press/v139/kim21g.htmlConditional Variational Autoencoder with Adversarial Learning for End-to-End Text-to-SpeechSeveral recent end-to-end text-to-speech (TTS) models enabling single-stage training and parallel sampling have been proposed, but their sample quality does not match that of two-stage TTS systems. In this work, we present a parallel end-to-end TTS method that generates more natural sounding audio than current two-stage models. Our method adopts variational inference augmented with normalizing flows and an adversarial training process, which improves the expressive power of generative modeling. We also propose a stochastic duration predictor to synthesize speech with diverse rhythms from input text. With the uncertainty modeling over latent variables and the stochastic duration predictor, our method expresses the natural one-to-many relationship in which a text input can be spoken in multiple ways with different pitches and rhythms. A subjective human evaluation (mean opinion score, or MOS) on the LJ Speech, a single speaker dataset, shows that our method outperforms the best publicly available TTS systems and achieves a MOS comparable to ground truth.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/kim21f.html
http://proceedings.mlr.press/v139/kim21f.htmlMessage Passing Adaptive Resonance Theory for Online Active Semi-supervised LearningActive learning is widely used to reduce labeling effort and training time by repeatedly querying only the most beneficial samples from unlabeled data. In real-world problems where data cannot be stored indefinitely due to limited storage or privacy issues, the query selection and the model update should be performed as soon as a new data sample is observed. Various online active learning methods have been studied to deal with these challenges; however, there are difficulties in selecting representative query samples and updating the model efficiently without forgetting. In this study, we propose Message Passing Adaptive Resonance Theory (MPART) that learns the distribution and topology of input data online. Through message passing on the topological graph, MPART actively queries informative and representative samples, and continuously improves the classification performance using both labeled and unlabeled data. We evaluate our model in stream-based selective sampling scenarios with comparable query selection strategies, showing that MPART significantly outperforms competitive models.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/kim21e.html
http://proceedings.mlr.press/v139/kim21e.htmlI-BERT: Integer-only BERT QuantizationTransformer based models, like BERT and RoBERTa, have achieved state-of-the-art results in many Natural Language Processing tasks. However, their memory footprint, inference latency, and power consumption are prohibitive efficient inference at the edge, and even at the data center. While quantization can be a viable solution for this, previous work on quantizing Transformer based models use floating-point arithmetic during inference, which cannot efficiently utilize integer-only logical units such as the recent Turing Tensor Cores, or traditional integer-only ARM processors. In this work, we propose I-BERT, a novel quantization scheme for Transformer based models that quantizes the entire inference with integer-only arithmetic. Based on lightweight integer-only approximation methods for nonlinear operations, e.g., GELU, Softmax, and Layer Normalization, I-BERT performs an end-to-end integer-only BERT inference without any floating point calculation. We evaluate our approach on GLUE downstream tasks using RoBERTa-Base/Large. We show that for both cases, I-BERT achieves similar (and slightly higher) accuracy as compared to the full-precision baseline. Furthermore, our preliminary implementation of I-BERT shows a speedup of 2.4- 4.0x for INT8 inference on a T4 GPU system as compared to FP32 inference. The framework has been developed in PyTorch and has been open-sourced.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/kim21d.html
http://proceedings.mlr.press/v139/kim21d.htmlReward Identification in Inverse Reinforcement LearningWe study the problem of reward identifiability in the context of Inverse Reinforcement Learning (IRL). The reward identifiability question is critical to answer when reasoning about the effectiveness of using Markov Decision Processes (MDPs) as computational models of real world decision makers in order to understand complex decision making behavior and perform counterfactual reasoning. While identifiability has been acknowledged as a fundamental theoretical question in IRL, little is known about the types of MDPs for which rewards are identifiable, or even if there exist such MDPs. In this work, we formalize the reward identification problem in IRL and study how identifiability relates to properties of the MDP model. For deterministic MDP models with the MaxEntRL objective, we prove necessary and sufficient conditions for identifiability. Building on these results, we present efficient algorithms for testing whether or not an MDP model is identifiable.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/kim21c.html
http://proceedings.mlr.press/v139/kim21c.htmlSelf-Improved Retrosynthetic PlanningRetrosynthetic planning is a fundamental problem in chemistry for finding a pathway of reactions to synthesize a target molecule. Recently, search algorithms have shown promising results for solving this problem by using deep neural networks (DNNs) to expand their candidate solutions, i.e., adding new reactions to reaction pathways. However, the existing works on this line are suboptimal; the retrosynthetic planning problem requires the reaction pathways to be (a) represented by real-world reactions and (b) executable using “building block” molecules, yet the DNNs expand reaction pathways without fully incorporating such requirements. Motivated by this, we propose an end-to-end framework for directly training the DNNs towards generating reaction pathways with the desirable properties. Our main idea is based on a self-improving procedure that trains the model to imitate successful trajectories found by itself. We also propose a novel reaction augmentation scheme based on a forward reaction model. Our experiments demonstrate that our scheme significantly improves the success rate of solving the retrosynthetic problem from 86.84% to 96.32% while maintaining the performance of DNN for predicting valid reactions.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/kim21b.html
http://proceedings.mlr.press/v139/kim21b.htmlImproving Predictors via Combination Across Diverse Task CategoriesPredictor combination is the problem of improving a task predictor using predictors of other tasks when the forms of individual predictors are unknown. Previous work approached this problem by nonparametrically assessing predictor relationships based on their joint evaluations on a shared sample. This limits their application to cases where all predictors are defined on the same task category, e.g. all predictors estimate attributes of shoes. We present a new predictor combination algorithm that overcomes this limitation. Our algorithm aligns the heterogeneous domains of different predictors in a shared latent space to facilitate comparisons of predictors independently of the domains on which they are originally defined. We facilitate this by a new data alignment scheme that matches data distributions across task categories. Based on visual attribute ranking experiments on datasets that span diverse task categories (e.g. shoes and animals), we demonstrate that our approach often significantly improves the performances of the initial predictors.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/kim21a.html
http://proceedings.mlr.press/v139/kim21a.htmlGRAD-MATCH: Gradient Matching based Data Subset Selection for Efficient Deep Model TrainingThe great success of modern machine learning models on large datasets is contingent on extensive computational resources with high financial and environmental costs. One way to address this is by extracting subsets that generalize on par with the full data. In this work, we propose a general framework, GRAD-MATCH, which finds subsets that closely match the gradient of the \emph{training or validation} set. We find such subsets effectively using an orthogonal matching pursuit algorithm. We show rigorous theoretical and convergence guarantees of the proposed algorithm and, through our extensive experiments on real-world datasets, show the effectiveness of our proposed framework. We show that GRAD-MATCH significantly and consistently outperforms several recent data-selection algorithms and achieves the best accuracy-efficiency trade-off. GRAD-MATCH is available as a part of the CORDS toolkit: \url{https://github.com/decile-team/cords}.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/killamsetty21a.html
http://proceedings.mlr.press/v139/killamsetty21a.htmlNeural SDEs as Infinite-Dimensional GANsStochastic differential equations (SDEs) are a staple of mathematical modelling of temporal dynamics. However, a fundamental limitation has been that such models have typically been relatively inflexible, which recent work introducing Neural SDEs has sought to solve. Here, we show that the current classical approach to fitting SDEs may be approached as a special case of (Wasserstein) GANs, and in doing so the neural and classical regimes may be brought together. The input noise is Brownian motion, the output samples are time-evolving paths produced by a numerical solver, and by parameterising a discriminator as a Neural Controlled Differential Equation (CDE), we obtain Neural SDEs as (in modern machine learning parlance) continuous-time generative time series models. Unlike previous work on this problem, this is a direct extension of the classical approach without reference to either prespecified statistics or density functions. Arbitrary drift and diffusions are admissible, so as the Wasserstein loss has a unique global minima, in the infinite data limit \textit{any} SDE may be learnt.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/kidger21b.html
http://proceedings.mlr.press/v139/kidger21b.html"Hey, that’s not an ODE": Faster ODE Adjoints via SeminormsNeural differential equations may be trained by backpropagating gradients via the adjoint method, which is another differential equation typically solved using an adaptive-step-size numerical differential equation solver. A proposed step is accepted if its error, \emph{relative to some norm}, is sufficiently small; else it is rejected, the step is shrunk, and the process is repeated. Here, we demonstrate that the particular structure of the adjoint equations makes the usual choices of norm (such as $L^2$) unnecessarily stringent. By replacing it with a more appropriate (semi)norm, fewer steps are unnecessarily rejected and the backpropagation is made faster. This requires only minor code modifications. Experiments on a wide range of tasks—including time series, generative modeling, and physical control—demonstrate a median improvement of 40% fewer function evaluations. On some problems we see as much as 62% fewer function evaluations, so that the overall training time is roughly halved.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/kidger21a.html
http://proceedings.mlr.press/v139/kidger21a.htmlFunctional Space Analysis of Local GAN ConvergenceRecent work demonstrated the benefits of studying continuous-time dynamics governing the GAN training. However, this dynamics is analyzed in the model parameter space, which results in finite-dimensional dynamical systems. We propose a novel perspective where we study the local dynamics of adversarial training in the general functional space and show how it can be represented as a system of partial differential equations. Thus, the convergence properties can be inferred from the eigenvalues of the resulting differential operator. We show that these eigenvalues can be efficiently estimated from the target dataset before training. Our perspective reveals several insights on the practical tricks commonly used to stabilize GANs, such as gradient penalty, data augmentation, and advanced integration schemes. As an immediate practical benefit, we demonstrate how one can a priori select an optimal data augmentation strategy for a particular generation task.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/khrulkov21a.html
http://proceedings.mlr.press/v139/khrulkov21a.htmlFinite-Sample Analysis of Off-Policy Natural Actor-Critic AlgorithmIn this paper, we provide finite-sample convergence guarantees for an off-policy variant of the natural actor-critic (NAC) algorithm based on Importance Sampling. In particular, we show that the algorithm converges to a global optimal policy with a sample complexity of $\mathcal{O}(\epsilon^{-3}\log^2(1/\epsilon))$ under an appropriate choice of stepsizes. In order to overcome the issue of large variance due to Importance Sampling, we propose the $Q$-trace algorithm for the critic, which is inspired by the V-trace algorithm (Espeholt et al., 2018). This enables us to explicitly control the bias and variance, and characterize the trade-off between them. As an advantage of off-policy sampling, a major feature of our result is that we do not need any additional assumptions, beyond the ergodicity of the Markov chain induced by the behavior policy.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/khodadadian21a.html
http://proceedings.mlr.press/v139/khodadadian21a.htmlMarkpainting: Adversarial Machine Learning meets InpaintingInpainting is a learned interpolation technique that is based on generative modeling and used to populate masked or missing pieces in an image; it has wide applications in picture editing and retouching. Recently, inpainting started being used for watermark removal, raising concerns. In this paper we study how to manipulate it using our markpainting technique. First, we show how an image owner with access to an inpainting model can augment their image in such a way that any attempt to edit it using that model will add arbitrary visible information. We find that we can target multiple different models simultaneously with our technique. This can be designed to reconstitute a watermark if the editor had been trying to remove it. Second, we show that our markpainting technique is transferable to models that have different architectures or were trained on different datasets, so watermarks created using it are difficult for adversaries to remove. Markpainting is novel and can be used as a manipulation alarm that becomes visible in the event of inpainting. Source code is available at: https://github.com/iliaishacked/markpainting.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/khachaturov21a.html
http://proceedings.mlr.press/v139/khachaturov21a.htmlAffine Invariant Analysis of Frank-Wolfe on Strongly Convex SetsIt is known that the Frank-Wolfe (FW) algorithm, which is affine covariant, enjoys faster convergence rates than $\mathcal{O}\left(1/K\right)$ when the constraint set is strongly convex. However, these results rely on norm-dependent assumptions, usually incurring non-affine invariant bounds, in contradiction with FW’s affine covariant property. In this work, we introduce new structural assumptions on the problem (such as the directional smoothness) and derive an affine invariant, norm-independent analysis of Frank-Wolfe. We show that our rates are better than any other known convergence rates of FW in this setting. Based on our analysis, we propose an affine invariant backtracking line-search. Interestingly, we show that typical backtracking line-searches using smoothness of the objective function present similar performances than its affine invariant counterpart, despite using affine dependent norms in the step size’s computation.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/kerdreux21a.html
http://proceedings.mlr.press/v139/kerdreux21a.htmlInterpretable Stability Bounds for Spectral Graph FiltersGraph-structured data arise in a variety of real-world context ranging from sensor and transportation to biological and social networks. As a ubiquitous tool to process graph-structured data, spectral graph filters have been used to solve common tasks such as denoising and anomaly detection, as well as design deep learning architectures such as graph neural networks. Despite being an important tool, there is a lack of theoretical understanding of the stability properties of spectral graph filters, which are important for designing robust machine learning models. In this paper, we study filter stability and provide a novel and interpretable upper bound on the change of filter output, where the bound is expressed in terms of the endpoint degrees of the deleted and newly added edges, as well as the spatial proximity of those edges. This upper bound allows us to reason, in terms of structural properties of the graph, when a spectral graph filter will be stable. We further perform extensive experiments to verify intuition that can be gained from the bound.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/kenlay21a.html
http://proceedings.mlr.press/v139/kenlay21a.htmlSelf Normalizing FlowsEfficient gradient computation of the Jacobian determinant term is a core problem in many machine learning settings, and especially so in the normalizing flow framework. Most proposed flow models therefore either restrict to a function class with easy evaluation of the Jacobian determinant, or an efficient estimator thereof. However, these restrictions limit the performance of such density models, frequently requiring significant depth to reach desired performance levels. In this work, we propose \emph{Self Normalizing Flows}, a flexible framework for training normalizing flows by replacing expensive terms in the gradient by learned approximate inverses at each layer. This reduces the computational complexity of each layer’s exact update from $\mathcal{O}(D^3)$ to $\mathcal{O}(D^2)$, allowing for the training of flow architectures which were otherwise computationally infeasible, while also providing efficient sampling. We show experimentally that such models are remarkably stable and optimize to similar data likelihood values as their exact gradient counterparts, while training more quickly and surpassing the performance of functionally constrained counterparts.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/keller21a.html
http://proceedings.mlr.press/v139/keller21a.htmlPrior Image-Constrained Reconstruction using Style-Based Generative ModelsObtaining a useful estimate of an object from highly incomplete imaging measurements remains a holy grail of imaging science. Deep learning methods have shown promise in learning object priors or constraints to improve the conditioning of an ill-posed imaging inverse problem. In this study, a framework for estimating an object of interest that is semantically related to a known prior image, is proposed. An optimization problem is formulated in the disentangled latent space of a style-based generative model, and semantically meaningful constraints are imposed using the disentangled latent representation of the prior image. Stable recovery from incomplete measurements with the help of a prior image is theoretically analyzed. Numerical experiments demonstrating the superior performance of our approach as compared to related methods are presented.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/kelkar21a.html
http://proceedings.mlr.press/v139/kelkar21a.htmlRegularized Submodular Maximization at ScaleIn this paper, we propose scalable methods for maximizing a regularized submodular function $f \triangleq g-\ell$ expressed as the difference between a monotone submodular function $g$ and a modular function $\ell$. Submodularity is inherently related to the notions of diversity, coverage, and representativeness. In particular, finding the mode (i.e., the most likely configuration) of many popular probabilistic models of diversity, such as determinantal point processes and strongly log-concave distributions, involves maximization of (regularized) submodular functions. Since a regularized function $f$ can potentially take on negative values, the classic theory of submodular maximization, which heavily relies on the non-negativity assumption of submodular functions, is not applicable. To circumvent this challenge, we develop the first one-pass streaming algorithm for maximizing a regularized submodular function subject to a $k$-cardinality constraint. Furthermore, we develop the first distributed algorithm that returns a solution $S$ in $O(1/ \epsilon)$ rounds of MapReduce computation. We highlight that our result, even for the unregularized case where the modular term $\ell$ is zero, improves the memory and communication complexity of the state-of-the-art by a factor of $O(1/ \epsilon)$ while arguably provides a simpler distributed algorithm and a unifying analysis. We empirically study the performance of our scalable methods on a set of real-life applications, including finding the mode of negatively correlated distributions, vertex cover of social networks, and several data summarization tasks.Thu, 01 Jul 2021 00:00:00 +0000
http://proceedings.mlr.press/v139/kazemi21a.html
http://proceedings.mlr.press/v139/kazemi21a.htmlWhen Does Data Augmentation Help With Membership Inference Attacks?Deep learning models often raise privacy concerns as they leak information about their training data. This leakage enables membership inference attacks (MIA) that can identify whether a data point was in a model’s training set. Research shows that some ’data augmentation’ mechanisms may redu