![[International Conference on Machine Learning Logo]](/v139/assets/images/logo-pmlr.svg){kind=logo}
[edit]
Volume 139: International Conference on Machine Learning, 18-24 July 2021, Virtual
[edit]
Editors: Marina Meila, Tong Zhang
A New Representation of Successor Features for Transfer across Dissimilar Environments
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:1-9
Massively Parallel and Asynchronous Tsetlin Machine Architecture Supporting Almost Constant-Time Scaling
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:10-20
[abs][Download PDF]
Debiasing Model Updates for Improving Personalized Federated Training
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:21-31
Memory Efficient Online Meta Learning
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:32-42
Robust Testing and Estimation under Manipulation Attacks
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:43-53
[abs][Download PDF]
GP-Tree: A Gaussian Process Classifier for Few-Shot Incremental Learning
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:54-65
f-Domain Adversarial Learning: Theory and Algorithms
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:66-75
Towards Rigorous Interpretations: a Formalisation of Feature Attribution
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:76-86
Acceleration via Fractal Learning Rate Schedules
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:87-99
A Regret Minimization Approach to Iterative Learning Control
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:100-109
Towards the Unification and Robustness of Perturbation and Gradient Based Explanations
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:110-119
[abs][Download PDF]
Label Inference Attacks from Log-loss Scores
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:120-129
Deep kernel processes
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:130-140
How Does Loss Function Affect Generalization Performance of Deep Learning? Application to Human Age Estimation
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:141-151
On Learnability via Gradient Method for Two-Layer ReLU Neural Networks in Teacher-Student Setting
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:152-162
Slot Machines: Discovering Winning Combinations of Random Weights in Neural Networks
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:163-174
A large-scale benchmark for few-shot program induction and synthesis
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:175-186
[abs][Download PDF]
Robust Pure Exploration in Linear Bandits with Limited Budget
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:187-195
Communication-Efficient Distributed Optimization with Quantized Preconditioners
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:196-206
Non-Exponentially Weighted Aggregation: Regret Bounds for Unbounded Loss Functions
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:207-218
Dataset Dynamics via Gradient Flows in Probability Space
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:219-230
Submodular Maximization subject to a Knapsack Constraint: Combinatorial Algorithms with Near-optimal Adaptive Complexity
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:231-242
Safe Reinforcement Learning with Linear Function Approximation
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:243-253
Automatic variational inference with cascading flows
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:254-263
Sparse Bayesian Learning via Stepwise Regression
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:264-274
Locally Persistent Exploration in Continuous Control Tasks with Sparse Rewards
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:275-285
Preferential Temporal Difference Learning
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:286-296
Unitary Branching Programs: Learnability and Lower Bounds
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:297-306
The Logical Options Framework
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:307-317
Annealed Flow Transport Monte Carlo
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:318-330
Permutation Weighting
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:331-341
Analyzing the tree-layer structure of Deep Forests
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:342-350
Dropout: Explicit Forms and Capacity Control
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:351-361
Tighter Bounds on the Log Marginal Likelihood of Gaussian Process Regression Using Conjugate Gradients
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:362-372
Deciding What to Learn: A Rate-Distortion Approach
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:373-382
Private Adaptive Gradient Methods for Convex Optimization
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:383-392
Private Stochastic Convex Optimization: Optimal Rates in L1 Geometry
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:393-403
Combinatorial Blocking Bandits with Stochastic Delays
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:404-413
Dichotomous Optimistic Search to Quantify Human Perception
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:414-424
Federated Learning under Arbitrary Communication Patterns
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:425-435
Asynchronous Distributed Learning : Adapting to Gradient Delays without Prior Knowledge
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:436-445
Decomposable Submodular Function Minimization via Maximum Flow
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:446-456
Differentially Private Query Release Through Adaptive Projection
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:457-467
On the Implicit Bias of Initialization Shape: Beyond Infinitesimal Mirror Descent
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:468-477
On-Off Center-Surround Receptive Fields for Accurate and Robust Image Classification
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:478-489
Uniform Convergence, Adversarial Spheres and a Simple Remedy
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:490-499
Faster Kernel Matrix Algebra via Density Estimation
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:500-510
Robust Reinforcement Learning using Least Squares Policy Iteration with Provable Performance Guarantees
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:511-520
Skill Discovery for Exploration and Planning using Deep Skill Graphs
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:521-531
Locally Adaptive Label Smoothing Improves Predictive Churn
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:532-542
How Important is the Train-Validation Split in Meta-Learning?
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:543-553
Stabilizing Equilibrium Models by Jacobian Regularization
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:554-565
Don’t Just Blame Over-parametrization for Over-confidence: Theoretical Analysis of Calibration in Binary Classification
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:566-576
Principled Exploration via Optimistic Bootstrapping and Backward Induction
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:577-587
GLSearch: Maximum Common Subgraph Detection via Learning to Search
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:588-598
Breaking the Limits of Message Passing Graph Neural Networks
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:599-608
Instance Specific Approximations for Submodular Maximization
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:609-618
[abs][Download PDF]
Augmented World Models Facilitate Zero-Shot Dynamics Generalization From a Single Offline Environment
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:619-629
Regularized Online Allocation Problems: Fairness and Beyond
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:630-639
Predict then Interpolate: A Simple Algorithm to Learn Stable Classifiers
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:640-650
Variational (Gradient) Estimate of the Score Function in Energy-based Latent Variable Models
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:651-661
Compositional Video Synthesis with Action Graphs
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:662-673
[abs][Download PDF]
Approximating a Distribution Using Weight Queries
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:674-683
Graph Convolution for Semi-Supervised Classification: Improved Linear Separability and Out-of-Distribution Generalization
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:684-693
Training Quantized Neural Networks to Global Optimality via Semidefinite Programming
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:694-704
Beyond $log^2(T)$ regret for decentralized bandits in matching markets
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:705-715
Optimal Thompson Sampling strategies for support-aware CVaR bandits
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:716-726
On Limited-Memory Subsampling Strategies for Bandits
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:727-737
Generalized Doubly Reparameterized Gradient Estimators
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:738-747
Directional Graph Networks
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:748-758
Policy Analysis using Synthetic Controls in Continuous-Time
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:759-768
Loss Surface Simplexes for Mode Connecting Volumes and Fast Ensembling
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:769-779
TFix: Learning to Fix Coding Errors with a Text-to-Text Transformer
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:780-791
Learning Queueing Policies for Organ Transplantation Allocation using Interpretable Counterfactual Survival Analysis
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:792-802
Learning from Biased Data: A Semi-Parametric Approach
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:803-812
Is Space-Time Attention All You Need for Video Understanding?
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:813-824
Confidence Scores Make Instance-dependent Label-noise Learning Possible
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:825-836
Size-Invariant Graph Representations for Graph Classification Extrapolations
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:837-851
Principal Bit Analysis: Autoencoding with Schur-Concave Loss
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:852-862
[abs][Download PDF]
Lower Bounds on Cross-Entropy Loss in the Presence of Test-time Adversaries
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:863-873
Additive Error Guarantees for Weighted Low Rank Approximation
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:874-883
Sample Complexity of Robust Linear Classification on Separated Data
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:884-893
Finding k in Latent $k-$ polytope
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:894-903
Non-Autoregressive Electron Redistribution Modeling for Reaction Prediction
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:904-913
TempoRL: Learning When to Act
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:914-924
Follow-the-Regularized-Leader Routes to Chaos in Routing Games
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:925-935
Neural Symbolic Regression that scales
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:936-945
Model Distillation for Revenue Optimization: Interpretable Personalized Pricing
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:946-956
[abs][Download PDF]
Scalable Normalizing Flows for Permutation Invariant Densities
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:957-967
[abs][Download PDF]
Online Learning for Load Balancing of Unknown Monotone Resource Allocation Games
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:968-979
Low-Precision Reinforcement Learning: Running Soft Actor-Critic in Half Precision
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:980-991
Multiplying Matrices Without Multiplying
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:992-1004
One for One, or All for All: Equilibria and Optimality of Collaboration in Federated Learning
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:1005-1014
Black-box density function estimation using recursive partitioning
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:1015-1025
Weisfeiler and Lehman Go Topological: Message Passing Simplicial Networks
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:1026-1037
The Hintons in your Neural Network: a Quantum Field Theory View of Deep Learning
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:1038-1048
Offline Contextual Bandits with Overparameterized Models
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:1049-1058
High-Performance Large-Scale Image Recognition Without Normalization
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:1059-1071
[abs][Download PDF]
Evaluating the Implicit Midpoint Integrator for Riemannian Hamiltonian Monte Carlo
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:1072-1081
Reinforcement Learning of Implicit and Explicit Control Flow Instructions
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:1082-1091
Machine Unlearning for Random Forests
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:1092-1104
Value Alignment Verification
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:1105-1115
Model-Free and Model-Based Policy Evaluation when Causality is Uncertain
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:1116-1126
Narrow Margins: Classification, Margins and Fat Tails
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:1127-1135
[abs][Download PDF]
Differentially Private Correlation Clustering
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:1136-1146
[abs][Download PDF]
Disambiguation of Weak Supervision leading to Exponential Convergence rates
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:1147-1157
Finite mixture models do not reliably learn the number of components
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:1158-1169
A Theory of Label Propagation for Subpopulation Shift
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:1170-1182
Lenient Regret and Good-Action Identification in Gaussian Process Bandits
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:1183-1192
A Zeroth-Order Block Coordinate Descent Algorithm for Huge-Scale Black-Box Optimization
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:1193-1203
GraphNorm: A Principled Approach to Accelerating Graph Neural Network Training
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:1204-1215
On Lower Bounds for Standard and Robust Gaussian Process Bandit Optimization
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:1216-1226
High-dimensional Experimental Design and Kernel Bandits
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:1227-1237
A Gradient Based Strategy for Hamiltonian Monte Carlo Hyperparameter Optimization
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:1238-1248
Asymmetric Heavy Tails and Implicit Bias in Gaussian Noise Injections
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:1249-1260
Fold2Seq: A Joint Sequence(1D)-Fold(3D) Embedding-based Generative Model for Protein Design
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:1261-1271
Learning from Similarity-Confidence Data
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:1272-1282
Parameter-free Locally Accelerated Conditional Gradients
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:1283-1293
Optimizing persistent homology based functions
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:1294-1303
Online Policy Gradient for Model Free Learning of Linear Quadratic Regulators with $\sqrt$T Regret
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:1304-1313
[abs][Download PDF]
Multi-Receiver Online Bayesian Persuasion
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:1314-1323
Marginal Contribution Feature Importance - an Axiomatic Approach for Explaining Data
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:1324-1335
Disentangling syntax and semantics in the brain with deep networks
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:1336-1348
Fair Classification with Noisy Protected Attributes: A Framework with Provable Guarantees
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:1349-1361
Best Model Identification: A Rested Bandit Formulation
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:1362-1372
Revisiting Rainbow: Promoting more insightful and inclusive deep reinforcement learning research
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:1373-1383
Learning Routines for Effective Off-Policy Reinforcement Learning
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:1384-1394
Learning Node Representations Using Stationary Flow Prediction on Large Payment and Cash Transaction Networks
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:1395-1406
GRAND: Graph Neural Diffusion
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:1407-1418
HoroPCA: Hyperbolic Dimensionality Reduction via Horospherical Projections
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:1419-1429
Goal-Conditioned Reinforcement Learning with Imagined Subgoals
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:1430-1440
Locally Private k-Means in One Round
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:1441-1451
Modularity in Reinforcement Learning via Algorithmic Independence in Credit Assignment
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:1452-1462
Image-Level or Object-Level? A Tale of Two Resampling Strategies for Long-Tailed Detection
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:1463-1472
[abs][Download PDF]
DeepWalking Backwards: From Embeddings Back to Graphs
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:1473-1483
Differentiable Spatial Planning using Transformers
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:1484-1495
Solving Challenging Dexterous Manipulation Tasks With Trajectory Optimisation and Reinforcement Learning
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:1496-1506
Classification with Rejection Based on Cost-sensitive Classification
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:1507-1517
Actionable Models: Unsupervised Offline Reinforcement Learning of Robotic Skills
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:1518-1528
Unified Robust Semi-Supervised Variational Autoencoder
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:1529-1538
[abs][Download PDF]
Unsupervised Learning of Visual 3D Keypoints for Control
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:1539-1549
Integer Programming for Causal Structure Learning in the Presence of Latent Variables
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:1550-1560
Improved Corruption Robust Algorithms for Episodic Reinforcement Learning
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:1561-1570
Scalable Computations of Wasserstein Barycenter via Input Convex Neural Networks
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:1571-1581
Neural Feature Matching in Implicit 3D Representations
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:1582-1593
Decentralized Riemannian Gradient Descent on the Stiefel Manifold
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:1594-1605
Learning Self-Modulating Attention in Continuous Time Space with Applications to Sequential Recommendation
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:1606-1616
[abs][Download PDF]
Mandoline: Model Evaluation under Distribution Shift
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:1617-1629
Order Matters: Probabilistic Modeling of Node Sequence for Graph Generation
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:1630-1639
CARTL: Cooperative Adversarially-Robust Transfer Learning
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:1640-1650
Finding the Stochastic Shortest Path with Low Regret: the Adversarial Cost and Unknown Transition Case
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:1651-1660
SpreadsheetCoder: Formula Prediction from Semi-structured Context
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:1661-1672
Large-Margin Contrastive Learning with Distance Polarization Regularizer
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:1673-1683
Z-GCNETs: Time Zigzags at Graph Convolutional Networks for Time Series Forecasting
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:1684-1694
A Unified Lottery Ticket Hypothesis for Graph Neural Networks
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:1695-1706
Network Inference and Influence Maximization from Samples
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:1707-1716
Data-driven Prediction of General Hamiltonian Dynamics via Learning Exactly-Symplectic Maps
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:1717-1727
Analysis of stochastic Lanczos quadrature for spectrum approximation
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:1728-1739
Large-Scale Multi-Agent Deep FBSDEs
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:1740-1748
Representation Subspace Distance for Domain Adaptation Regression
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:1749-1759
Overcoming Catastrophic Forgetting by Bayesian Generative Regularization
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:1760-1770
Cyclically Equivariant Neural Decoders for Cyclic Codes
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:1771-1780
A Receptor Skeleton for Capsule Neural Networks
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:1781-1790
Accelerating Gossip SGD with Periodic Global Averaging
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:1791-1802
ActNN: Reducing Training Memory Footprint via 2-Bit Activation Compressed Training
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:1803-1813
SPADE: A Spectral Method for Black-Box Adversarial Robustness Evaluation
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:1814-1824
Self-supervised and Supervised Joint Training for Resource-rich Machine Translation
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:1825-1835
Exact Optimization of Conformal Predictors via Incremental and Decremental Learning
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:1836-1845
Problem Dependent View on Structured Thresholding Bandit Problems
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:1846-1854
Online Optimization in Games via Control Theory: Connecting Regret, Passivity and Poincaré Recurrence
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:1855-1865
Understanding and Mitigating Accuracy Disparity in Regression
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:1866-1876
Private Alternating Least Squares: Practical Private Matrix Completion with Tighter Rates
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:1877-1887
Light RUMs
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:1888-1897
Parallelizing Legendre Memory Unit Training
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:1898-1907
Quantifying and Reducing Bias in Maximum Likelihood Estimation of Structured Anomalies
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:1908-1919
Robust Learning-Augmented Caching: An Experimental Study
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:1920-1930
Unifying Vision-and-Language Tasks via Text Generation
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:1931-1942
Learning from Nested Data with Ornstein Auto-Encoders
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:1943-1952
Variational Empowerment as Representation Learning for Goal-Conditioned Reinforcement Learning
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:1953-1963
Label-Only Membership Inference Attacks
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:1964-1974
Modeling Hierarchical Structures with Continuous Recursive Neural Networks
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:1975-1988
Scaling Multi-Agent Reinforcement Learning with Selective Parameter Sharing
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:1989-1998
[abs][Download PDF]
Beyond Variance Reduction: Understanding the True Impact of Baselines on Policy Optimization
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:1999-2009
First-Order Methods for Wasserstein Distributionally Robust MDP
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:2010-2019
Phasic Policy Gradient
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:2020-2027
Riemannian Convex Potential Maps
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:2028-2038
Scaling Properties of Deep Residual Networks
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:2039-2048
Differentially-Private Clustering of Easy Instances
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:2049-2059
Improving Ultrametrics Embeddings Through Coresets
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:2060-2068
[abs][Download PDF]
Correlation Clustering in Constant Many Parallel Rounds
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:2069-2078
Concentric mixtures of Mallows models for top-$k$ rankings: sampling and identifiability
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:2079-2088
Exploiting Shared Representations for Personalized Federated Learning
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:2089-2099
Differentiable Particle Filtering via Entropy-Regularized Optimal Transport
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:2100-2111
Fairness and Bias in Online Selection
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:2112-2121
[abs][Download PDF]
Relative Deviation Margin Bounds
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:2122-2131
A Discriminative Technique for Multiple-Source Adaptation
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:2132-2143
Characterizing Fairness Over the Set of Good Models Under Selective Labels
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:2144-2155
Two-way kernel matrix puncturing: towards resource-efficient PCA and spectral clustering
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:2156-2165
Explaining Time Series Predictions with Dynamic Masks
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:2166-2177
Generalised Lipschitz Regularisation Equals Distributional Robustness
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:2178-2188
Environment Inference for Invariant Learning
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:2189-2200
Mind the Box: $l_1$-APGD for Sparse Adversarial Attacks on Image Classifiers
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:2201-2211
Parameterless Transductive Feature Re-representation for Few-Shot Learning
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:2212-2221
[abs][Download PDF]
Randomized Algorithms for Submodular Function Maximization with a $k$-System Constraint
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:2222-2232
GBHT: Gradient Boosting Histogram Transform for Density Estimation
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:2233-2243
ProGraML: A Graph-based Program Representation for Data Flow Analysis and Compiler Optimizations
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:2244-2253
Combining Pessimism with Optimism for Robust and Efficient Model-Based Deep Reinforcement Learning
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:2254-2264
Quantifying Availability and Discovery in Recommender Systems via Stochastic Reachability
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:2265-2275
Dynamic Balancing for Model Selection in Bandits and RL
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:2276-2285
ConViT: Improving Vision Transformers with Soft Convolutional Inductive Biases
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:2286-2296
Consistent regression when oblivious outliers overwhelm
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:2297-2306
Offline Reinforcement Learning with Pseudometric Learning
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:2307-2318
A Tale of Two Efficient and Informative Negative Sampling Distributions
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:2319-2329
SiameseXML: Siamese Networks meet Extreme Classifiers with 100M Labels
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:2330-2340
[abs][Download PDF]
Fixed-Parameter and Approximation Algorithms for PCA with Outliers
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:2341-2351
Sliced Iterative Normalizing Flows
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:2352-2364
Convex Regularization in Monte-Carlo Tree Search
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:2365-2375
Demonstration-Conditioned Reinforcement Learning for Few-Shot Imitation
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:2376-2387
Re-understanding Finite-State Representations of Recurrent Policy Networks
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:2388-2397
Newton Method over Networks is Fast up to the Statistical Precision
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:2398-2409
BasisDeVAE: Interpretable Simultaneous Dimensionality Reduction and Feature-Level Clustering with Derivative-Based Variational Autoencoders
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:2410-2420
Intermediate Layer Optimization for Inverse Problems using Deep Generative Models
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:2421-2432
Measuring Robustness in Deep Learning Based Compressive Sensing
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:2433-2444
SAINT-ACC: Safety-Aware Intelligent Adaptive Cruise Control for Autonomous Vehicles Using Deep Reinforcement Learning
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:2445-2455
[abs][Download PDF]
Lipschitz normalization for self-attention layers with application to graph neural networks
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:2456-2466
[abs][Download PDF]
Householder Sketch for Accurate and Accelerated Least-Mean-Squares Solvers
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:2467-2477
Byzantine-Resilient High-Dimensional SGD with Local Iterations on Heterogeneous Data
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:2478-2488
Catformer: Designing Stable Transformers via Sensitivity Analysis
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:2489-2499
Diffusion Source Identification on Networks with Statistical Confidence
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:2500-2509
Bayesian Deep Learning via Subnetwork Inference
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:2510-2521
Adversarial Robustness Guarantees for Random Deep Neural Networks
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:2522-2534
High-Dimensional Gaussian Process Inference with Derivatives
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:2535-2545
Transfer-Based Semantic Anomaly Detection
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:2546-2558
Grid-Functioned Neural Networks
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:2559-2567
Multidimensional Scaling: Approximation and Complexity
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:2568-2578
What Does Rotation Prediction Tell Us about Classifier Accuracy under Varying Testing Environments?
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:2579-2589
[abs][Download PDF]
Toward Better Generalization Bounds with Locally Elastic Stability
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:2590-2600
Revenue-Incentive Tradeoffs in Dynamic Reserve Pricing
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:2601-2610
Heterogeneity for the Win: One-Shot Federated Clustering
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:2611-2620
Kernel Continual Learning
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:2621-2631
Bayesian Optimization over Hybrid Spaces
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:2632-2643
Navigation Turing Test (NTT): Learning to Evaluate Human-Like Navigation
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:2644-2653
Versatile Verification of Tree Ensembles
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:2654-2664
On the Inherent Regularization Effects of Noise Injection During Training
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:2665-2675
Hierarchical Agglomerative Graph Clustering in Nearly-Linear Time
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:2676-2686
Learning Online Algorithms with Distributional Advice
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:2687-2696
[abs][Download PDF]
A Wasserstein Minimax Framework for Mixed Linear Regression
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:2697-2706
Context-Aware Online Collective Inference for Templated Graphical Models
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:2707-2716
[abs][Download PDF]
ARMS: Antithetic-REINFORCE-Multi-Sample Gradient for Binary Variables
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:2717-2727
XOR-CD: Linearly Convergent Constrained Structure Generation
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:2728-2738
Dual Principal Component Pursuit for Robust Subspace Learning: Theory and Algorithms for a Holistic Approach
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:2739-2748
[abs][Download PDF]
Coded-InvNet for Resilient Prediction Serving Systems
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:2749-2759
Estimation and Quantization of Expected Persistence Diagrams
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:2760-2770
On Energy-Based Models with Overparametrized Shallow Neural Networks
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:2771-2782
Kernel-Based Reinforcement Learning: A Finite-Time Analysis
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:2783-2792
Attention is not all you need: pure attention loses rank doubly exponentially with depth
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:2793-2803
How rotational invariance of common kernels prevents generalization in high dimensions
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:2804-2814
Fast Stochastic Bregman Gradient Methods: Sharp Analysis and Variance Reduction
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:2815-2825
Bilinear Classes: A Structural Framework for Provable Generalization in RL
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:2826-2836
Improved Contrastive Divergence Training of Energy-Based Models
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:2837-2848
Order-Agnostic Cross Entropy for Non-Autoregressive Machine Translation
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:2849-2859
Putting the “Learning" into Learning-Augmented Algorithms for Frequency Estimation
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:2860-2869
Estimating $α$-Rank from A Few Entries with Low Rank Matrix Completion
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:2870-2879
Learning Diverse-Structured Networks for Adversarial Robustness
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:2880-2891
Risk Bounds and Rademacher Complexity in Batch Reinforcement Learning
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:2892-2902
Sawtooth Factorial Topic Embeddings Guided Gamma Belief Network
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:2903-2913
[abs][Download PDF]
Exponential Reduction in Sample Complexity with Learning of Ising Model Dynamics
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:2914-2925
Reinforcement Learning Under Moral Uncertainty
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:2926-2936
Confidence-Budget Matching for Sequential Budgeted Learning
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:2937-2947
Self-Paced Context Evaluation for Contextual Reinforcement Learning
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:2948-2958
Provably Strict Generalisation Benefit for Equivariant Models
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:2959-2969
Efficient Iterative Amortized Inference for Learning Symmetric and Disentangled Multi-Object Representations
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:2970-2981
Implicit Bias of Linear RNNs
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:2982-2992
Global Optimality Beyond Two Layers: Training Deep ReLU Networks via Convex Programs
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:2993-3003
Revealing the Structure of Deep Neural Networks via Convex Duality
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:3004-3014
Whitening for Self-Supervised Representation Learning
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:3015-3024
Graph Mixture Density Networks
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:3025-3035
[abs][Download PDF]
Cross-Gradient Aggregation for Decentralized Learning from Non-IID Data
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:3036-3046
Weight-covariance alignment for adversarially robust neural networks
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:3047-3056
Data augmentation for deep learning based accelerated MRI reconstruction with limited data
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:3057-3067
Poisson-Randomised DirBN: Large Mutation is Needed in Dirichlet Belief Networks
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:3068-3077
Model-based Reinforcement Learning for Continuous Control with Posterior Sampling
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:3078-3087
SECANT: Self-Expert Cloning for Zero-Shot Generalization of Visual Policies
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:3088-3099
On Estimation in Latent Variable Models
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:3100-3110
On Variational Inference in Biclustering Models
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:3111-3121
Learning Bounds for Open-Set Learning
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:3122-3132
Streaming Bayesian Deep Tensor Factorization
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:3133-3142
PID Accelerated Value Iteration Algorithm
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:3143-3153
Near-Optimal Entrywise Anomaly Detection for Low-Rank Matrices with Sub-Exponential Noise
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:3154-3163
Connecting Optimal Ex-Ante Collusion in Teams to Extensive-Form Correlation: Faster Algorithms and Positive Complexity Results
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:3164-3173
Train simultaneously, generalize better: Stability of gradient-based minimax learners
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:3174-3185
Unbalanced minibatch Optimal Transport; applications to Domain Adaptation
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:3186-3197
Risk-Sensitive Reinforcement Learning with Function Approximation: A Debiasing Approach
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:3198-3207
Lossless Compression of Efficient Private Local Randomizers
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:3208-3219
Dimensionality Reduction for the Sum-of-Distances Metric
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:3220-3229
Reserve Price Optimization for First Price Auctions in Display Advertising
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:3230-3239
[abs][Download PDF]
Uncertainty Principles of Encoding GANs
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:3240-3251
Pointwise Binary Classification with Pairwise Confidence Comparisons
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:3252-3262
Provably Correct Optimization and Exploration with Non-linear Policies
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:3263-3273
KD3A: Unsupervised Multi-Source Decentralized Domain Adaptation via Knowledge Distillation
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:3274-3283
Understanding Noise Injection in GANs
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:3284-3293
GNNAutoScale: Scalable and Expressive Graph Neural Networks via Historical Embeddings
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:3294-3304
PsiPhi-Learning: Reinforcement Learning with Demonstrations using Successor Features and Inverse Temporal Difference Learning
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:3305-3317
A Practical Method for Constructing Equivariant Multilayer Perceptrons for Arbitrary Matrix Groups
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:3318-3328
Few-Shot Conformal Prediction with Auxiliary Tasks
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:3329-3339
Scalable Certified Segmentation via Randomized Smoothing
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:3340-3351
What’s in the Box? Exploring the Inner Life of Neural Networks with Robust Rules
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:3352-3362
Online Learning with Optimism and Delay
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:3363-3373
Online A-Optimal Design and Active Linear Regression
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:3374-3383
Deep Adaptive Design: Amortizing Sequential Bayesian Experimental Design
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:3384-3395
Efficient Online Learning for Dynamic k-Clustering
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:3396-3406
Clustered Sampling: Low-Variance and Improved Representativity for Clients Selection in Federated Learning
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:3407-3416
Agnostic Learning of Halfspaces with Gradient Descent via Soft Margins
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:3417-3426
Provable Generalization of SGD-trained Neural Networks of Any Width in the Presence of Adversarial Label Noise
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:3427-3438
Post-selection inference with HSIC-Lasso
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:3439-3448
Variational Data Assimilation with a Learned Inverse Observation Operator
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:3449-3458
[abs][Download PDF]
Bayesian Quadrature on Riemannian Data Manifolds
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:3459-3468
Learn-to-Share: A Hardware-friendly Transfer Learning Framework Exploiting Computation and Parameter Sharing
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:3469-3479
Learning Task Informed Abstractions
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:3480-3491
Double-Win Quant: Aggressively Winning Robustness of Quantized Deep Neural Networks via Random Precision Training and Inference
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:3492-3504
Auto-NBA: Efficient and Effective Search Over the Joint Space of Networks, Bitwidths, and Accelerators
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:3505-3517
A Deep Reinforcement Learning Approach to Marginalized Importance Sampling with the Successor Representation
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:3518-3529
Learning disentangled representations via product manifold projection
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:3530-3540
Policy Information Capacity: Information-Theoretic Measure for Task Complexity in Deep Reinforcement Learning
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:3541-3552
An Information-Geometric Distance on the Space of Tasks
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:3553-3563
Maximum Mean Discrepancy Test is Aware of Adversarial Attacks
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:3564-3575
Unsupervised Co-part Segmentation through Assembly
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:3576-3586
Discriminative Complementary-Label Learning with Weighted Loss
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:3587-3597
RATT: Leveraging Unlabeled Data to Guarantee Generalization
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:3598-3609
On Proximal Policy Optimization’s Heavy-tailed Gradients
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:3610-3619
What does LIME really see in images?
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:3620-3629
Parametric Graph for Unimodal Ranking Bandit
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:3630-3639
Let’s Agree to Degree: Comparing Graph Convolutional Networks in the Message-Passing Framework
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:3640-3649
On the difficulty of unbiased alpha divergence minimization
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:3650-3659
How and Why to Use Experimental Data to Evaluate Methods for Observational Causal Inference
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:3660-3671
Strategic Classification in the Dark
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:3672-3681
EMaQ: Expected-Max Q-Learning Operator for Simple Yet Effective Offline and Online RL
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:3682-3691
Differentially Private Aggregation in the Shuffle Model: Almost Central Accuracy in Almost a Single Message
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:3692-3701
The Power of Adaptivity for Stochastic Submodular Cover
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:3702-3712
[abs][Download PDF]
Differentially Private Quantiles
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:3713-3722
Query Complexity of Adversarial Attacks
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:3723-3733
Spectral Normalisation for Deep Reinforcement Learning: An Optimisation Perspective
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:3734-3744
12-Lead ECG Reconstruction via Koopman Operators
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:3745-3754
[abs][Download PDF]
Function Contrastive Learning of Transferable Meta-Representations
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:3755-3765
Active Slices for Sliced Stein Discrepancy
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:3766-3776
On the Problem of Underranking in Group-Fair Ranking
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:3777-3787
MARINA: Faster Non-Convex Distributed Learning with Compression
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:3788-3798
Systematic Analysis of Cluster Similarity Indices: How to Validate Validation Measures
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:3799-3808
Revisiting Point Cloud Shape Classification with a Simple and Effective Baseline
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:3809-3820
Dissecting Supervised Contrastive Learning
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:3821-3830
Oops I Took A Gradient: Scalable Sampling for Discrete Distributions
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:3831-3841
Detecting Rewards Deterioration in Episodic Reinforcement Learning
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:3842-3853
Crystallization Learning with the Delaunay Triangulation
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:3854-3863
AutoAttend: Automated Attention Representation Search
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:3864-3874
Operationalizing Complex Causes: A Pragmatic View of Mediation
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:3875-3885
On a Combination of Alternating Minimization and Nesterov’s Momentum
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:3886-3898
Decentralized Single-Timescale Actor-Critic on Zero-Sum Two-Player Stochastic Games
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:3899-3909
Adversarial Policy Learning in Two-player Competitive Games
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:3910-3919
Soft then Hard: Rethinking the Quantization in Neural Image Compression
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:3920-3929
UneVEn: Universal Value Exploration for Multi-Agent Reinforcement Learning
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:3930-3941
Distribution-Free Calibration Guarantees for Histogram Binning without Sample Splitting
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:3942-3952
Correcting Exposure Bias for Link Recommendation
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:3953-3963
The Heavy-Tail Phenomenon in SGD
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:3964-3975
Knowledge Enhanced Machine Learning Pipeline against Diverse Adversarial Attacks
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:3976-3987
Adapting to Delays and Data in Adversarial Multi-Armed Bandits
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:3988-3997
Rate-Distortion Analysis of Minimum Excess Risk in Bayesian Learning
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:3998-4007
Regret Minimization in Stochastic Non-Convex Learning via a Proximal-Gradient Approach
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:4008-4017
Diversity Actor-Critic: Sample-Aware Entropy Regularization for Sample-Efficient Exploration
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:4018-4029
Adversarial Combinatorial Bandits with General Non-linear Reward Functions
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:4030-4039
[abs][Download PDF]
A Collective Learning Framework to Boost GNN Expressiveness for Node Classification
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:4040-4050
Grounding Language to Entities and Dynamics for Generalization in Reinforcement Learning
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:4051-4062
Sparse Feature Selection Makes Batch Reinforcement Learning More Sample Efficient
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:4063-4073
Bootstrapping Fitted Q-Evaluation for Off-Policy Inference
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:4074-4084
Compressed Maximum Likelihood
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:4085-4095
Valid Causal Inference with (Some) Invalid Instruments
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:4096-4106
Model Performance Scaling with Multiple Data Sources
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:4107-4116
Hierarchical VAEs Know What They Don’t Know
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:4117-4128
SPECTRE: defending against backdoor attacks using robust statistics
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:4129-4139
Boosting for Online Convex Optimization
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:4140-4149
[abs][Download PDF]
PipeTransformer: Automated Elastic Pipelining for Distributed Training of Large-scale Models
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:4150-4159
SoundDet: Polyphonic Moving Sound Event Detection and Localization from Raw Waveform
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:4160-4170
[abs][Download PDF]
Logarithmic Regret for Reinforcement Learning with Linear Function Approximation
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:4171-4180
Finding Relevant Information via a Discrete Fourier Expansion
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:4181-4191
Zeroth-Order Non-Convex Learning via Hierarchical Dual Averaging
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:4192-4202
Improving Molecular Graph Neural Network Explainability with Orthonormalization and Induced Sparsity
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:4203-4213
Muesli: Combining Improvements in Policy Optimization
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:4214-4226
Learning Representations by Humans, for Humans
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:4227-4238
Optimizing Black-box Metrics with Iterative Example Weighting
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:4239-4249
Trees with Attention for Set Prediction Tasks
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:4250-4261
Multiplicative Noise and Heavy Tails in Stochastic Optimization
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:4262-4274
MC-LSTM: Mass-Conserving LSTM
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:4275-4286
Learning Curves for Analysis of Deep Networks
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:4287-4296
Equivariant Learning of Stochastic Fields: Gaussian Processes and Steerable Conditional Neural Processes
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:4297-4307
Latent Programmer: Discrete Latent Codes for Program Synthesis
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:4308-4318
Chebyshev Polynomial Codes: Task Entanglement-based Coding for Distributed Matrix Multiplication
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:4319-4327
Federated Learning of User Verification Models Without Sharing Embeddings
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:4328-4336
[abs][Download PDF]
The Limits of Min-Max Optimization Algorithms: Convergence to Spurious Non-Critical Sets
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:4337-4348
Near-Optimal Representation Learning for Linear Bandits and Linear RL
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:4349-4358
On the Random Conjugate Kernel and Neural Tangent Kernel
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:4359-4368
Off-Belief Learning
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:4369-4379
Generalizable Episodic Memory for Deep Reinforcement Learning
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:4380-4390
A Scalable Deterministic Global Optimization Algorithm for Clustering Problems
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:4391-4401
[abs][Download PDF]
On Recovering from Modeling Errors Using Testing Bayesian Networks
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:4402-4411
A Novel Sequential Coreset Method for Gradient Descent Algorithms
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:4412-4422
[abs][Download PDF]
FL-NTK: A Neural Tangent Kernel-based Framework for Federated Learning Analysis
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:4423-4434
STRODE: Stochastic Boundary Ordinary Differential Equation
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:4435-4445
A Riemannian Block Coordinate Descent Method for Computing the Projection Robust Wasserstein Distance
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:4446-4455
Projection Robust Wasserstein Barycenters
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:4456-4465
Accurate Post Training Quantization With Small Calibration Sets
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:4466-4475
Learning and Planning in Complex Action Spaces
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:4476-4486
Generative Adversarial Transformers
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:4487-4499
Neural Pharmacodynamic State Space Modeling
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:4500-4510
Hyperparameter Selection for Imitation Learning
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:4511-4522
Pareto GAN: Extending the Representational Power of GANs to Heavy-Tailed Distributions
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:4523-4532
LieTransformer: Equivariant Self-Attention for Lie Groups
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:4533-4543
Crowdsourcing via Annotator Co-occurrence Imputation and Provable Symmetric Nonnegative Matrix Factorization
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:4544-4554
Selecting Data Augmentation for Simulating Interventions
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:4555-4562
Scalable Marginal Likelihood Estimation for Model Selection in Deep Learning
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:4563-4573
Active Learning for Distributionally Robust Level-Set Estimation
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:4574-4584
Learning Randomly Perturbed Structured Predictors for Direct Loss Minimization
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:4585-4595
Randomized Entity-wise Factorization for Multi-Agent Reinforcement Learning
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:4596-4606
Randomized Exploration in Reinforcement Learning with General Value Function Approximation
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:4607-4616
Distributed Second Order Methods with Fast Rates and Compressed Communication
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:4617-4628
What Are Bayesian Neural Network Posteriors Really Like?
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:4629-4640
How to Learn when Data Reacts to Your Model: Performative Gradient Descent
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:4641-4650
Perceiver: General Perception with Iterative Attention
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:4651-4664
[abs][Download PDF]
Imitation by Predicting Observations
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:4665-4676
[abs][Download PDF]
Local Correlation Clustering with Asymmetric Classification Errors
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:4677-4686
Alternative Microfoundations for Strategic Classification
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:4687-4697
Robust Density Estimation from Batches: The Best Things in Life are (Nearly) Free
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:4698-4708
Instance-Optimal Compressed Sensing via Posterior Sampling
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:4709-4720
Fairness for Image Generation with Uncertain Sensitive Attributes
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:4721-4732
Feature Clustering for Support Identification in Extreme Regions
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:4733-4743
Improved Regret Bounds of Bilinear Bandits using Action Space Analysis
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:4744-4754
Inverse Decision Modeling: Learning Interpretable Representations of Behavior
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:4755-4771
Catastrophic Fisher Explosion: Early Phase Fisher Matrix Impacts Generalization
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:4772-4784
Policy Gradient Bayesian Robust Optimization for Imitation Learning
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:4785-4796
In-Database Regression in Input Sparsity Time
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:4797-4806
Parallel and Flexible Sampling from Autoregressive Models via Langevin Dynamics
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:4807-4818
Objective Bound Conditional Gaussian Process for Bayesian Optimization
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:4819-4828
Quantifying Ignorance in Individual-Level Causal-Effect Estimates under Hidden Confounding
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:4829-4838
DeepReDuce: ReLU Reduction for Fast Private Inference
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:4839-4849
Factor-analytic inverse regression for high-dimension, small-sample dimensionality reduction
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:4850-4859
Fast margin maximization via dual acceleration
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:4860-4869
Marginalized Stochastic Natural Gradients for Black-Box Variational Inference
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:4870-4881
Bilevel Optimization: Convergence Analysis and Enhanced Design
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:4882-4892
Efficient Statistical Tests: A Neural Tangent Kernel Approach
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:4893-4903
Scaling Up Visual and Vision-Language Representation Learning With Noisy Text Supervision
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:4904-4916
Multi-Dimensional Classification via Sparse Label Encoding
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:4917-4926
[abs][Download PDF]
Self-Damaging Contrastive Learning
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:4927-4939
[abs][Download PDF]
Prioritized Level Replay
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:4940-4950
Monotonic Robust Policy Optimization with Model Discrepancy
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:4951-4960
Approximation Theory of Convolutional Architectures for Time Series Modelling
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:4961-4970
Streaming and Distributed Algorithms for Robust Column Subset Selection
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:4971-4981
Single Pass Entrywise-Transformed Low Rank Approximation
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:4982-4991
The Emergence of Individuality
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:4992-5001
Online Selection Problems against Constrained Adversary
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:5002-5012
Active Covering
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:5013-5022
Emphatic Algorithms for Deep Reinforcement Learning
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:5023-5033
Characterizing Structural Regularities of Labeled Data in Overparameterized Models
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:5034-5044
Optimal Streaming Algorithms for Multi-Armed Bandits
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:5045-5054
Towards Tight Bounds on the Sample Complexity of Average-reward MDPs
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:5055-5064
Almost Optimal Anytime Algorithm for Batched Multi-Armed Bandits
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:5065-5073
MOTS: Minimax Optimal Thompson Sampling
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:5074-5083
Is Pessimism Provably Efficient for Offline RL?
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:5084-5096
Adversarial Option-Aware Hierarchical Imitation Learning
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:5097-5106
Discrete-Valued Latent Preference Matrix Estimation with Graph Side Information
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:5107-5117
Provable Lipschitz Certification for Generative Models
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:5118-5126
Isometric Gaussian Process Latent Variable Model for Dissimilarity Data
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:5127-5136
[abs][Download PDF]
On the Generalization Power of Overfitted Two-Layer Neural Tangent Kernel Models
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:5137-5147
Improved Confidence Bounds for the Linear Logistic Model and Applications to Bandits
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:5148-5157
Detection of Signal in the Spiked Rectangular Models
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:5158-5167
Estimating Identifiable Causal Effects on Markov Equivalence Class through Double Machine Learning
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:5168-5179
A Nullspace Property for Subspace-Preserving Recovery
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:5180-5188
Training Recurrent Neural Networks via Forward Propagation Through Time
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:5189-5200
The Distributed Discrete Gaussian Mechanism for Federated Learning with Secure Aggregation
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:5201-5212
Practical and Private (Deep) Learning Without Sampling or Shuffling
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:5213-5225
A Differentiable Point Process with Its Application to Spiking Neural Networks
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:5226-5235
Projection techniques to update the truncated SVD of evolving matrices with applications
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:5236-5246
Optimal Off-Policy Evaluation from Multiple Logging Policies
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:5247-5256
Efficient Performance Bounds for Primal-Dual Reinforcement Learning from Demonstrations
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:5257-5268
Statistical Estimation from Dependent Data
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:5269-5278
SKIing on Simplices: Kernel Interpolation on the Permutohedral Lattice for Scalable Gaussian Processes
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:5279-5289
Variational Auto-Regressive Gaussian Processes for Continual Learning
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:5290-5300
Off-Policy Confidence Sequences
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:5301-5310
Learning from History for Byzantine Robust Optimization
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:5311-5319
Non-Negative Bregman Divergence Minimization for Deep Direct Density Ratio Estimation
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:5320-5333
Improved Algorithms for Agnostic Pool-based Active Classification
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:5334-5344
When Does Data Augmentation Help With Membership Inference Attacks?
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:5345-5355
Regularized Submodular Maximization at Scale
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:5356-5366
Prior Image-Constrained Reconstruction using Style-Based Generative Models
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:5367-5377
Self Normalizing Flows
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:5378-5387
Interpretable Stability Bounds for Spectral Graph Filters
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:5388-5397
Affine Invariant Analysis of Frank-Wolfe on Strongly Convex Sets
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:5398-5408
Markpainting: Adversarial Machine Learning meets Inpainting
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:5409-5419
Finite-Sample Analysis of Off-Policy Natural Actor-Critic Algorithm
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:5420-5431
Functional Space Analysis of Local GAN Convergence
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:5432-5442
"Hey, that’s not an ODE": Faster ODE Adjoints via Seminorms
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:5443-5452
Neural SDEs as Infinite-Dimensional GANs
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:5453-5463
GRAD-MATCH: Gradient Matching based Data Subset Selection for Efficient Deep Model Training
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:5464-5474
Improving Predictors via Combination Across Diverse Task Categories
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:5475-5485
Self-Improved Retrosynthetic Planning
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:5486-5495
Reward Identification in Inverse Reinforcement Learning
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:5496-5505
I-BERT: Integer-only BERT Quantization
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:5506-5518
Message Passing Adaptive Resonance Theory for Online Active Semi-supervised Learning
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:5519-5529
Conditional Variational Autoencoder with Adversarial Learning for End-to-End Text-to-Speech
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:5530-5540
A Policy Gradient Algorithm for Learning to Learn in Multiagent Reinforcement Learning
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:5541-5550
Inferring Latent Dynamics Underlying Neural Population Activity via Neural Differential Equations
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:5551-5561
The Lipschitz Constant of Self-Attention
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:5562-5571
Unsupervised Skill Discovery with Bottleneck Option Learning
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:5572-5582
ViLT: Vision-and-Language Transformer Without Convolution or Region Supervision
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:5583-5594
[abs][Download PDF]
Bias-Robust Bayesian Optimization via Dueling Bandits
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:5595-5605
[abs][Download PDF]
CLOCS: Contrastive Learning of Cardiac Signals Across Space, Time, and Patients
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:5606-5615
Scalable Optimal Transport in High Dimensions for Graph Distances, Embedding Alignment, and More
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:5616-5627
Representational aspects of depth and conditioning in normalizing flows
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:5628-5636
WILDS: A Benchmark of in-the-Wild Distribution Shifts
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:5637-5664
One-sided Frank-Wolfe algorithms for saddle problems
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:5665-5675
A Lower Bound for the Sample Complexity of Inverse Reinforcement Learning
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:5676-5685
Consensus Control for Decentralized Deep Learning
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:5686-5696
A Distribution-dependent Analysis of Meta Learning
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:5697-5706
Evaluating Robustness of Predictive Uncertainty Estimation: Are Dirichlet-based Models Reliable?
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:5707-5718
Kernel Stein Discrepancy Descent
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:5719-5730
Boosting the Throughput and Accelerator Utilization of Specialized CNN Inference Beyond Increasing Batch Size
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:5731-5741
NeRF-VAE: A Geometry Aware 3D Scene Generative Model
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:5742-5752
[abs][Download PDF]
Active Testing: Sample-Efficient Model Evaluation
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:5753-5763
High Confidence Generalization for Reinforcement Learning
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:5764-5773
Offline Reinforcement Learning with Fisher Divergence Critic Regularization
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:5774-5783
ADOM: Accelerated Decentralized Optimization Method for Time-Varying Networks
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:5784-5793
Revisiting Peng’s Q($λ$) for Modern Reinforcement Learning
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:5794-5804
Adapting to misspecification in contextual bandits with offline regression oracles
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:5805-5814
Out-of-Distribution Generalization via Risk Extrapolation (REx)
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:5815-5826
Near-Optimal Confidence Sequences for Bounded Random Variables
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:5827-5837
Differentially Private Bayesian Inference for Generalized Linear Models
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:5838-5849
Bayesian Structural Adaptation for Continual Learning
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:5850-5860
Implicit rate-constrained optimization of non-decomposable objectives
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:5861-5871
A Scalable Second Order Method for Ill-Conditioned Matrix Completion from Few Samples
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:5872-5883
Meta-Thompson Sampling
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:5884-5893
Targeted Data Acquisition for Evolving Negotiation Agents
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:5894-5904
ASAM: Adaptive Sharpness-Aware Minimization for Scale-Invariant Learning of Deep Neural Networks
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:5905-5914
On the price of explainability for some clustering problems
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:5915-5925
Adaptive Newton Sketch: Linear-time Optimization with Quadratic Convergence and Effective Hessian Dimensionality
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:5926-5936
Generalization Bounds in the Presence of Outliers: a Median-of-Means Study
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:5937-5947
Model Fusion for Personalized Learning
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:5948-5958
Gradient Disaggregation: Breaking Privacy in Federated Learning by Reconstructing the User Participant Matrix
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:5959-5968
Stochastic Multi-Armed Bandits with Unrestricted Delay Distributions
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:5969-5978
[abs][Download PDF]
Discovering symbolic policies with deep reinforcement learning
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:5979-5989
Graph Cuts Always Find a Global Optimum for Potts Models (With a Catch)
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:5990-5999
Efficient Message Passing for 0–1 ILPs with Binary Decision Diagrams
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:6000-6010
CountSketches, Feature Hashing and the Median of Three
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:6011-6020
[abs][Download PDF]
MorphVAE: Generating Neural Morphologies from 3D-Walks using a Variational Autoencoder with Spherical Latent Space
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:6021-6031
Improved Regret Bound and Experience Replay in Regularized Policy Iteration
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:6032-6042
LAMDA: Label Matching Deep Domain Adaptation
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:6043-6054
Gaussian Process-Based Real-Time Learning for Safety Critical Applications
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:6055-6064
Sharing Less is More: Lifelong Learning in Deep Networks with Selective Layer Transfer
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:6065-6075
Fair Selective Classification Via Sufficiency
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:6076-6086
On-the-fly Rectification for Robust Large-Vocabulary Topic Inference
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:6087-6097
Unsupervised Embedding Adaptation via Early-Stage Feature Reconstruction for Few-Shot Classification
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:6098-6108
Continual Learning in the Teacher-Student Setup: Impact of Task Similarity
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:6109-6119
OptiDICE: Offline Policy Optimization via Stationary Distribution Correction Estimation
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:6120-6130
SUNRISE: A Simple Unified Framework for Ensemble Learning in Deep Reinforcement Learning
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:6131-6141
Achieving Near Instance-Optimality and Minimax-Optimality in Stochastic and Adversarial Linear Bandits Simultaneously
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:6142-6151
PEBBLE: Feedback-Efficient Interactive Reinforcement Learning via Relabeling Experience and Unsupervised Pre-training
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:6152-6163
Near-Optimal Linear Regression under Distribution Shift
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:6164-6174
Stability and Generalization of Stochastic Gradient Methods for Minimax Problems
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:6175-6186
Scalable Evaluation of Multi-Agent Reinforcement Learning with Melting Pot
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:6187-6199
Better Training using Weight-Constrained Stochastic Dynamics
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:6200-6211
Globally-Robust Neural Networks
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:6212-6222
Learning to Price Against a Moving Target
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:6223-6232
SigGPDE: Scaling Sparse Gaussian Processes on Sequential Data
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:6233-6242
Strategic Classification Made Practical
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:6243-6253
Improved, Deterministic Smoothing for L_1 Certified Robustness
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:6254-6264
BASE Layers: Simplifying Training of Large, Sparse Models
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:6265-6274
[abs][Download PDF]
Run-Sort-ReRun: Escaping Batch Size Limitations in Sliced Wasserstein Generative Models
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:6275-6285
[abs][Download PDF]
PAGE: A Simple and Optimal Probabilistic Gradient Estimator for Nonconvex Optimization
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:6286-6295
Tightening the Dependence on Horizon in the Sample Complexity of Q-Learning
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:6296-6306
Winograd Algorithm for AdderNet
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:6307-6315
[abs][Download PDF]
A Free Lunch From ANN: Towards Efficient, Accurate Spiking Neural Networks Calibration
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:6316-6325
Privacy-Preserving Feature Selection with Secure Multiparty Computation
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:6326-6336
Theory of Spectral Method for Union of Subspaces-Based Random Geometry Graph
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:6337-6345
[abs][Download PDF]
MURAL: Meta-Learning Uncertainty-Aware Rewards for Outcome-Driven Reinforcement Learning
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:6346-6356
Ditto: Fair and Robust Federated Learning Through Personalization
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:6357-6368
Quantization Algorithms for Random Fourier Features
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:6369-6380
Approximate Group Fairness for Clustering
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:6381-6391
[abs][Download PDF]
Sharper Generalization Bounds for Clustering
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:6392-6402
Provably End-to-end Label-noise Learning without Anchor Points
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:6403-6413
A Novel Method to Solve Neural Knapsack Problems
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:6414-6424
[abs][Download PDF]
Mixed Cross Entropy Loss for Neural Machine Translation
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:6425-6436
Training Graph Neural Networks with 1000 Layers
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:6437-6449
Active Feature Acquisition with Generative Surrogate Models
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:6450-6459
Partially Observed Exchangeable Modeling
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:6460-6470
Testing DNN-based Autonomous Driving Systems under Critical Environmental Conditions
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:6471-6482
The Symmetry between Arms and Knapsacks: A Primal-Dual Approach for Bandits with Knapsacks
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:6483-6492
Distributionally Robust Optimization with Markovian Data
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:6493-6503
Communication-Efficient Distributed SVD via Local Power Iterations
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:6504-6514
FILTRA: Rethinking Steerable CNN by Filter Transform
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:6515-6522
Online Unrelated Machine Load Balancing with Predictions Revisited
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:6523-6532
Asymptotic Normality and Confidence Intervals for Prediction Risk of the Min-Norm Least Squares Estimator
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:6533-6542
TeraPipe: Token-Level Pipeline Parallelism for Training Large-Scale Language Models
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:6543-6552
A Second look at Exponential and Cosine Step Sizes: Simplicity, Adaptivity, and Performance
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:6553-6564
Towards Understanding and Mitigating Social Biases in Language Models
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:6565-6576
Uncovering the Connections Between Adversarial Transferability and Knowledge Transferability
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:6577-6587
Parallel Droplet Control in MEDA Biochips using Multi-Agent Reinforcement Learning
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:6588-6599
Information Obfuscation of Graph Neural Networks
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:6600-6610
Guided Exploration with Proximal Policy Optimization using a Single Demonstration
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:6611-6620
Debiasing a First-order Heuristic for Approximate Bi-level Optimization
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:6621-6630
Making transport more robust and interpretable by moving data through a small number of anchor points
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:6631-6641
Straight to the Gradient: Learning to Use Novel Tokens for Neural Text Generation
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:6642-6653
Quasi-global Momentum: Accelerating Decentralized Deep Learning on Heterogeneous Data
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:6654-6665
Generative Causal Explanations for Graph Neural Networks
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:6666-6679
[abs][Download PDF]
Tractable structured natural-gradient descent using local parameterizations
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:6680-6691
Active Learning of Continuous-time Bayesian Networks through Interventions
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:6692-6701
Phase Transitions, Distance Functions, and Implicit Neural Representations
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:6702-6712
The Earth Mover’s Pinball Loss: Quantiles for Histogram-Valued Regression
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:6713-6724
Understanding Instance-Level Label Noise: Disparate Impacts and Treatments
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:6725-6735
APS: Active Pretraining with Successor Features
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:6736-6747
Learning by Turning: Neural Architecture Aware Optimisation
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:6748-6758
Dynamic Game Theoretic Neural Optimizer
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:6759-6769
Besov Function Approximation and Binary Classification on Low-Dimensional Manifolds Using Convolutional Residual Networks
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:6770-6780
Just Train Twice: Improving Group Robustness without Training Group Information
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:6781-6792
Event Outlier Detection in Continuous Time
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:6793-6803
Heterogeneous Risk Minimization
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:6804-6814
Stochastic Iterative Graph Matching
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:6815-6825
[abs][Download PDF]
Cooperative Exploration for Multi-Agent Deep Reinforcement Learning
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:6826-6836
Elastic Graph Neural Networks
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:6837-6849
[abs][Download PDF]
One Pass Late Fusion Multi-view Clustering
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:6850-6859
Coach-Player Multi-agent Reinforcement Learning for Dynamic Team Composition
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:6860-6870
From Local to Global Norm Emergence: Dissolving Self-reinforcing Substructures with Incremental Social Instruments
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:6871-6881
[abs][Download PDF]
A Value-Function-based Interior-point Method for Non-convex Bi-level Optimization
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:6882-6892
Selfish Sparse RNN Training
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:6893-6904
Temporal Difference Learning as Gradient Splitting
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:6905-6913
On Robust Mean Estimation under Coordinate-level Corruption
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:6914-6924
Decoupling Exploration and Exploitation for Meta-Reinforcement Learning without Sacrifices
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:6925-6935
How Do Adam and Training Strategies Help BNNs Optimization
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:6936-6946
[abs][Download PDF]
SagaNet: A Small Sample Gated Network for Pediatric Cancer Diagnosis
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:6947-6956
Learning Deep Neural Networks under Agnostic Corrupted Supervision
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:6957-6967
Leveraging Public Data for Practical Private Query Release
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:6968-6977
Watermarking Deep Neural Networks with Greedy Residuals
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:6978-6988
[abs][Download PDF]
Do We Actually Need Dense Over-Parameterization? In-Time Over-Parameterization in Sparse Training
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:6989-7000
A Sharp Analysis of Model-based Reinforcement Learning with Self-Play
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:7001-7010
Lottery Ticket Preserves Weight Correlation: Is It Desirable or Not?
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:7011-7020
Group Fisher Pruning for Practical Network Compression
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:7021-7032
Infinite-Dimensional Optimization for Zero-Sum Games via Variational Transport
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:7033-7044
Noise and Fluctuation of Finite Learning Rate Stochastic Gradient Descent
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:7045-7056
Multi-layered Network Exploration via Random Walks: From Offline Optimization to Online Learning
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:7057-7066
Relative Positional Encoding for Transformers with Linear Complexity
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:7067-7079
Joint Online Learning and Decision-making via Dual Mirror Descent
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:7080-7089
Symmetric Spaces for Graph Embeddings: A Finsler-Riemannian Approach
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:7090-7101
HEMET: A Homomorphic-Encryption-Friendly Privacy-Preserving Mobile Neural Network Architecture
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:7102-7110
Optimal Complexity in Decentralized Training
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:7111-7123
DANCE: Enhancing saliency maps using decoys
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:7124-7133
Binary Classification from Multiple Unlabeled Datasets via Surrogate Set Classification
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:7134-7144
Variance Reduced Training with Stratified Sampling for Forecasting Models
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:7145-7155
ACE: Explaining cluster from an adversarial perspective
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:7156-7167
[abs][Download PDF]
On Monotonic Linear Interpolation of Neural Network Parameters
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:7168-7179
Improving Breadth-Wise Backpropagation in Graph Neural Networks Helps Learning Long-Range Dependencies.
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:7180-7191
GraphDF: A Discrete Flow Model for Molecular Graph Generation
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:7192-7203
Trajectory Diversity for Zero-Shot Coordination
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:7204-7213
HyperHyperNetwork for the Design of Antenna Arrays
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:7214-7223
Value Iteration in Continuous Actions, States and Time
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:7224-7234
Meta-Cal: Well-controlled Post-hoc Calibration by Ranking
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:7235-7245
Neural-Pull: Learning Signed Distance Function from Point clouds by Learning to Pull Space onto Surface
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:7246-7257
Learning Stochastic Behaviour from Aggregate Data
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:7258-7267
Local Algorithms for Finding Densely Connected Clusters
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:7268-7278
[abs][Download PDF]
Learning to Generate Noise for Multi-Attack Robustness
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:7279-7289
Learning Interaction Kernels for Agent Systems on Riemannian Manifolds
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:7290-7300
Tesseract: Tensorised Actors for Multi-Agent Reinforcement Learning
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:7301-7312
Domain Generalization using Causal Matching
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:7313-7324
Stability and Convergence of Stochastic Gradient Clipping: Beyond Lipschitz Continuity and Smoothness
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:7325-7335
Nonparametric Hamiltonian Monte Carlo
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:7336-7347
Exploiting structured data for learning contagious diseases under incomplete testing
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:7348-7357
Near-Optimal Algorithms for Explainable k-Medians and k-Means
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:7358-7367
KO codes: inventing nonlinear encoding and decoding for reliable wireless communication via deep-learning
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:7368-7378
Quantifying the Benefit of Using Differentiable Learning over Tangent Kernels
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:7379-7389
Inverse Constrained Reinforcement Learning
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:7390-7399
A Sampling-Based Method for Tensor Ring Decomposition
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:7400-7411
Sample Efficient Reinforcement Learning In Continuous State Spaces: A Perspective Beyond Linearity
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:7412-7422
Beyond the Pareto Efficient Frontier: Constraint Active Search for Multiobjective Experimental Design
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:7423-7434
Consistent Nonparametric Methods for Network Assisted Covariate Estimation
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:7435-7446
[abs][Download PDF]
Near-Optimal Model-Free Reinforcement Learning in Non-Stationary Episodic MDPs
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:7447-7458
Adaptive Sampling for Best Policy Identification in Markov Decision Processes
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:7459-7468
Explanations for Monotonic Classifiers.
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:7469-7479
[abs][Download PDF]
Multi-Agent Training beyond Zero-Sum with Correlated Equilibrium Meta-Solvers
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:7480-7491
Blind Pareto Fairness and Subgroup Robustness
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:7492-7501
Necessary and sufficient conditions for causal feature selection in time series with latent common causes
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:7502-7511
Proximal Causal Learning with Kernels: Two-Stage Estimation and Moment Restriction
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:7512-7523
Robust Unsupervised Learning via L-statistic Minimization
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:7524-7533
Adversarial Multi Class Learning under Weak Supervision with Performance Guarantees
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:7534-7543
Fundamental Tradeoffs in Distributionally Adversarial Training
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:7544-7554
Leveraging Non-uniformity in First-order Non-convex Optimization
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:7555-7564
Controlling Graph Dynamics with Reinforcement Learning and Graph Neural Networks
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:7565-7577
A theory of high dimensional regression with arbitrary correlations between input features and target functions: sample complexity, multiple descent curves and a hierarchy of phase transitions
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:7578-7587
Neural Architecture Search without Training
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:7588-7598
Fast active learning for pure exploration in reinforcement learning
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:7599-7608
UCB Momentum Q-learning: Correcting the bias without forgetting
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:7609-7618
An Integer Linear Programming Framework for Mining Constraints from Data
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:7619-7631
[abs][Download PDF]
A statistical perspective on distillation
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:7632-7642
Learn2Hop: Learned Optimization on Rough Landscapes
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:7643-7653
Counterfactual Credit Assignment in Model-Free Reinforcement Learning
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:7654-7664
Provably Efficient Learning of Transferable Rewards
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:7665-7676
Mixed Nash Equilibria in the Adversarial Examples Game
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:7677-7687
Learning in Nonzero-Sum Stochastic Games with Potentials
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:7688-7699
EfficientTTS: An Efficient and High-Quality Text-to-Speech Architecture
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:7700-7709
Outside the Echo Chamber: Optimizing the Performative Risk
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:7710-7720
Accuracy on the Line: on the Strong Correlation Between Out-of-Distribution and In-Distribution Generalization
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:7721-7735
Signatured Deep Fictitious Play for Mean Field Games with Common Noise
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:7736-7747
Meta-StyleSpeech : Multi-Speaker Adaptive Text-to-Speech Generation
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:7748-7759
On the Explicit Role of Initialization on the Convergence and Implicit Bias of Overparametrized Linear Networks
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:7760-7768
An Identifiable Double VAE For Disentangled Representations
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:7769-7779
Offline Meta-Reinforcement Learning with Advantage Weighting
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:7780-7791
The Power of Log-Sum-Exp: Sequential Density Ratio Matrix Estimation for Speed-Accuracy Optimization
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:7792-7804
PODS: Policy Optimization via Differentiable Simulation
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:7805-7817
Efficient Deviation Types and Learning for Hindsight Rationality in Extensive-Form Games
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:7818-7828
Neural Rough Differential Equations for Long Time Series
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:7829-7838
Connecting Interpretability and Robustness in Decision Trees through Separation
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:7839-7849
Outlier-Robust Optimal Transport
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:7850-7860
Oblivious Sketching for Logistic Regression
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:7861-7871
Bias-Variance Reduced Local SGD for Less Heterogeneous Federated Learning
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:7872-7881
Implicit-PDF: Non-Parametric Representation of Probability Distributions on the Rotation Manifold
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:7882-7893
No-regret Algorithms for Capturing Events in Poisson Point Processes
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:7894-7904
Online Limited Memory Neural-Linear Bandits with Likelihood Matching
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:7905-7915
Quantitative Understanding of VAE as a Non-linearly Scaled Isometric Embedding
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:7916-7926
GMAC: A Distributional Perspective on Actor-Critic Framework
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:7927-7936
Memory-Efficient Pipeline-Parallel DNN Training
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:7937-7947
Randomized Dimensionality Reduction for Facility Location and Single-Linkage Clustering
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:7948-7957
Generating images with sparse representations
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:7958-7968
Geometric convergence of elliptical slice sampling
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:7969-7978
HardCoRe-NAS: Hard Constrained diffeRentiable Neural Architecture Search
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:7979-7990
Emergent Social Learning via Multi-agent Reinforcement Learning
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:7991-8004
[abs][Download PDF]
Bayesian Algorithm Execution: Estimating Computable Properties of Black-box Functions Using Mutual Information
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:8005-8015
Continuous Coordination As a Realistic Scenario for Lifelong Learning
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:8016-8024
Policy Caches with Successor Features
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:8025-8033
Causality-aware counterfactual confounding adjustment as an alternative to linear residualization in anticausal prediction tasks based on linear learners
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:8034-8044
Incentivizing Compliance with Algorithmic Instruments
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:8045-8055
On the Proof of Global Convergence of Gradient Descent for Deep ReLU Networks with Linear Widths
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:8056-8062
[abs][Download PDF]
Value-at-Risk Optimization with Gaussian Processes
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:8063-8072
Cross-model Back-translated Distillation for Unsupervised Machine Translation
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:8073-8083
Optimal Transport Kernels for Sequential and Parallel Neural Architecture Search
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:8084-8095
Interactive Learning from Activity Description
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:8096-8108
Nonmyopic Multifidelity Acitve Search
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:8109-8118
Tight Bounds on the Smallest Eigenvalue of the Neural Tangent Kernel for Deep ReLU Networks
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:8119-8129
Temporal Predictive Coding For Model-Based Planning In Latent Space
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:8130-8139
Differentially Private Densest Subgraph Detection
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:8140-8151
[abs][Download PDF]
Data Augmentation for Meta-Learning
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:8152-8161
Improved Denoising Diffusion Probabilistic Models
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:8162-8171
Smooth $p$-Wasserstein Distance: Structure, Empirical Approximation, and Statistical Applications
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:8172-8183
AdaXpert: Adapting Neural Architecture for Growing Data
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:8184-8194
Asynchronous Decentralized Optimization With Implicit Stochastic Variance Reduction
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:8195-8204
WGAN with an Infinitely Wide Generator Has No Spurious Stationary Points
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:8205-8215
The Impact of Record Linkage on Learning from Feature Partitioned Data
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:8216-8226
Accuracy, Interpretability, and Differential Privacy via Explainable Boosting
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:8227-8237
Posterior Value Functions: Hindsight Baselines for Policy Gradient Methods
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:8238-8247
Global inducing point variational posteriors for Bayesian neural networks and deep Gaussian processes
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:8248-8259
Regularizing towards Causal Invariance: Linear Models with Proxies
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:8260-8270
Sparsity-Agnostic Lasso Bandit
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:8271-8280
Autoencoder Image Interpolation by Shaping the Latent Space
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:8281-8290
Generalization Guarantees for Neural Architecture Search with Train-Validation Split
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:8291-8301
Vector Quantized Models for Planning
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:8302-8313
Training Adversarially Robust Sparse Networks via Bayesian Connectivity Sampling
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:8314-8324
Opening the Blackbox: Accelerating Neural Differential Equations by Regularizing Internal Solver Heuristics
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:8325-8335
[abs][Download PDF]
RNN with Particle Flow for Probabilistic Spatio-temporal Forecasting
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:8336-8348
Inference for Network Regression Models with Community Structure
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:8349-8358
Latent Space Energy-Based Model of Symbol-Vector Coupling for Text Generation and Classification
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:8359-8370
[abs][Download PDF]
Leveraging Good Representations in Linear Contextual Bandits
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:8371-8380
Wasserstein Distributional Normalization For Robust Distributional Certification of Noisy Labeled Data
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:8381-8390
Unsupervised Representation Learning via Neural Activation Coding
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:8391-8400
Conditional Distributional Treatment Effect with Kernel Conditional Mean Embeddings and U-Statistic Regression
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:8401-8412
Generative Adversarial Networks for Markovian Temporal Dynamics: Stochastic Continuous Data Generation
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:8413-8421
Optimal Counterfactual Explanations in Tree Ensembles
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:8422-8431
PHEW : Constructing Sparse Networks that Learn Fast and Generalize Well without Training Data
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:8432-8442
CombOptNet: Fit the Right NP-Hard Problem by Learning Integer Programming Constraints
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:8443-8453
Ensemble Bootstrapping for Q-Learning
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:8454-8463
Homomorphic Sensing: Sparsity and Noise
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:8464-8475
How could Neural Networks understand Programs?
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:8476-8486
Privacy-Preserving Video Classification with Convolutional Neural Networks
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:8487-8499
Rissanen Data Analysis: Examining Dataset Characteristics via Description Length
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:8500-8513
Modelling Behavioural Diversity for Learning in Open-Ended Games
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:8514-8524
From Poincaré Recurrence to Convergence in Imperfect Information Games: Finding Equilibrium via Regularization
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:8525-8535
Spectral Smoothing Unveils Phase Transitions in Hierarchical Variational Autoencoders
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:8536-8545
Differentiable Sorting Networks for Scalable Sorting and Ranking Supervision
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:8546-8555
Megaverse: Simulating Embodied Agents at One Million Experiences per Second
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:8556-8566
Towards Practical Mean Bounds for Small Samples
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:8567-8576
DG-LMC: A Turn-key and Scalable Synchronous Distributed MCMC Algorithm via Langevin Monte Carlo within Gibbs
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:8577-8587
GeomCA: Geometric Evaluation of Data Representations
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:8588-8598
Grad-TTS: A Diffusion Probabilistic Model for Text-to-Speech
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:8599-8608
Bias-Free Scalable Gaussian Processes via Randomized Truncations
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:8609-8619
Dense for the Price of Sparse: Improved Performance of Sparsely Initialized Networks via a Subspace Offset
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:8620-8629
BANG: Bridging Autoregressive and Non-autoregressive Generation with Large Scale Pretraining
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:8630-8639
[abs][Download PDF]
A Probabilistic Approach to Neural Network Pruning
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:8640-8649
Global Prosody Style Transfer Without Text Transcriptions
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:8650-8660
Efficient Differentiable Simulation of Articulated Bodies
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:8661-8671
Oneshot Differentially Private Top-k Selection
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:8672-8681
Density Constrained Reinforcement Learning
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:8682-8692
Budgeted Heterogeneous Treatment Effect Estimation
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:8693-8702
Neural Transformation Learning for Deep Anomaly Detection Beyond Images
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:8703-8714
Provably Efficient Fictitious Play Policy Optimization for Zero-Sum Markov Games with Structured Transitions
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:8715-8725
Optimization Planning for 3D ConvNets
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:8726-8736
[abs][Download PDF]
On Reward-Free RL with Kernel and Neural Function Approximations: Single-Agent MDP and Markov Game
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:8737-8747
Learning Transferable Visual Models From Natural Language Supervision
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:8748-8763
A General Framework For Detecting Anomalous Inputs to DNN Classifiers
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:8764-8775
Towards Open Ad Hoc Teamwork Using Graph-based Policy Learning
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:8776-8786
Decoupling Value and Policy for Generalization in Reinforcement Learning
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:8787-8798
Hierarchical Clustering of Data Streams: Scalable Algorithms and Approximation Guarantees
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:8799-8809
Differentially Private Sliced Wasserstein Distance
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:8810-8820
Zero-Shot Text-to-Image Generation
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:8821-8831
[abs][Download PDF]
End-to-End Learning of Coherent Probabilistic Forecasts for Hierarchical Time Series
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:8832-8843
MSA Transformer
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:8844-8856
Autoregressive Denoising Diffusion Models for Multivariate Probabilistic Time Series Forecasting
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:8857-8868
Generative Particle Variational Inference via Estimation of Functional Gradients
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:8869-8879
Enhancing Robustness of Neural Networks through Fourier Stabilization
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:8880-8889
[abs][Download PDF]
Disentangling Sampling and Labeling Bias for Learning in Large-output Spaces
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:8890-8901
Cross-domain Imitation from Observations
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:8902-8912
Implicit Regularization in Tensor Factorization
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:8913-8924
Align, then memorise: the dynamics of learning with feedback alignment
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:8925-8935
Classifying high-dimensional Gaussian mixtures: Where kernel methods fail and neural networks succeed
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:8936-8947
Sharf: Shape-conditioned Radiance Fields from a Single View
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:8948-8958
[abs][Download PDF]
LEGO: Latent Execution-Guided Reasoning for Multi-Hop Question Answering on Knowledge Graphs
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:8959-8970
Interpreting and Disentangling Feature Components of Various Complexity from DNNs
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:8971-8981
Integrated Defense for Resilient Graph Matching
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:8982-8997
Solving high-dimensional parabolic PDEs using the tensor train format
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:8998-9009
Best Arm Identification in Graphical Bilinear Bandits
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:9010-9019
Principled Simplicial Neural Networks for Trajectory Prediction
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:9020-9029
On Linear Identifiability of Learned Representations
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:9030-9039
Representation Matters: Assessing the Importance of Subgroup Allocations in Training Data
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:9040-9051
TeachMyAgent: a Benchmark for Automatic Curriculum Learning in Deep RL
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:9052-9063
Discretization Drift in Two-Player Games
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:9064-9074
On the Predictability of Pruning Across Scales
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:9075-9083
Benchmarks, Algorithms, and Metrics for Hierarchical Disentanglement
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:9084-9094
Simultaneous Similarity-based Self-Distillation for Deep Metric Learning
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:9095-9106
Multi-group Agnostic PAC Learnability
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:9107-9115
PACOH: Bayes-Optimal Meta-Learning with PAC-Guarantees
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:9116-9126
An Algorithm for Stochastic and Adversarial Bandits with Switching Costs
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:9127-9135
Improving Lossless Compression Rates via Monte Carlo Bits-Back Coding
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:9136-9147
On Signal-to-Noise Ratio Issues in Variational Inference for Deep Gaussian Processes
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:9148-9156
Tilting the playing field: Dynamical loss functions for machine learning
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:9157-9167
UnICORNN: A recurrent model for learning very long time dependencies
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:9168-9178
Simple and Effective VAE Training with Calibrated Decoders
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:9179-9189
Model-Based Reinforcement Learning via Latent-Space Collocation
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:9190-9201
Training Data Subset Selection for Regression with Controlled Generalization Error
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:9202-9212
Unsupervised Part Representation by Flow Capsules
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:9213-9223
[abs][Download PDF]
Stochastic Sign Descent Methods: New Algorithms and Better Theory
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:9224-9234
Adversarial Dueling Bandits
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:9235-9244
Dueling Convex Optimization
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:9245-9254
Optimal regret algorithm for Pseudo-1d Bandit Convex Optimization
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:9255-9264
Asymptotics of Ridge Regression in Convolutional Models
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:9265-9275
Momentum Residual Neural Networks
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:9276-9287
Meta-Learning Bidirectional Update Rules
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:9288-9300
Recomposing the Reinforcement Learning Building Blocks with Hypernetworks
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:9301-9312
Towards Understanding Learning in Neural Networks with Linear Teachers
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:9313-9322
E(n) Equivariant Graph Neural Networks
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:9323-9332
A Representation Learning Perspective on the Importance of Train-Validation Splitting in Meta-Learning
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:9333-9343
Low-Rank Sinkhorn Factorization
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:9344-9354
Linear Transformers Are Secretly Fast Weight Programmers
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:9355-9366
Descending through a Crowded Valley - Benchmarking Deep Learning Optimizers
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:9367-9376
Equivariant message passing for the prediction of tensorial properties and molecular spectra
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:9377-9388
Just How Toxic is Data Poisoning? A Unified Benchmark for Backdoor and Data Poisoning Attacks
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:9389-9398
[abs][Download PDF]
Connecting Sphere Manifolds Hierarchically for Regularization
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:9399-9409
Learning Intra-Batch Connections for Deep Metric Learning
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:9410-9421
Top-k eXtreme Contextual Bandits with Arm Hierarchy
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:9422-9433
Pure Exploration and Regret Minimization in Matching Bandits
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:9434-9442
[abs][Download PDF]
State Entropy Maximization with Random Encoders for Efficient Exploration
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:9443-9454
Online Submodular Resource Allocation with Applications to Rebalancing Shared Mobility Systems
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:9455-9464
RRL: Resnet as representation for Reinforcement Learning
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:9465-9476
Equivariant Networks for Pixelized Spheres
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:9477-9488
Personalized Federated Learning using Hypernetworks
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:9489-9502
[abs][Download PDF]
On the Power of Localized Perceptron for Label-Optimal Learning of Halfspaces with Adversarial Noise
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:9503-9514
Sample-Optimal PAC Learning of Halfspaces with Malicious Noise
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:9515-9524
Backdoor Scanning for Deep Neural Networks through K-Arm Optimization
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:9525-9536
State Relevance for Off-Policy Evaluation
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:9537-9546
SparseBERT: Rethinking the Importance Analysis in Self-attention
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:9547-9557
Learning Gradient Fields for Molecular Conformation Generation
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:9558-9568
Segmenting Hybrid Trajectories using Latent ODEs
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:9569-9579
Deeply-Debiased Off-Policy Interval Estimation
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:9580-9591
GANMEX: One-vs-One Attributions using GAN-based Model Explainability
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:9592-9602
Large-Scale Meta-Learning with Continual Trajectory Shifting
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:9603-9613
AGENT: A Benchmark for Core Psychological Reasoning
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:9614-9625
Zoo-Tuning: Adaptive Transfer from A Zoo of Models
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:9626-9637
Aggregating From Multiple Target-Shifted Sources
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:9638-9648
Testing Group Fairness via Optimal Transport Projections
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:9649-9659
On Characterizing GAN Convergence Through Proximal Duality Gap
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:9660-9670
A Precise Performance Analysis of Support Vector Regression
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:9671-9680
Directed Graph Embeddings in Pseudo-Riemannian Manifolds
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:9681-9690
Collaborative Bayesian Optimization with Fair Regret
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:9691-9701
Dynamic Planning and Learning under Recovering Rewards
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:9702-9711
PopSkipJump: Decision-Based Attack for Probabilistic Classifiers
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:9712-9721
Geometry of the Loss Landscape in Overparameterized Neural Networks: Symmetries and Invariances
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:9722-9732
Flow-based Attribution in Graphical Models: A Recursive Shapley Approach
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:9733-9743
Structured World Belief for Reinforcement Learning in POMDP
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:9744-9755
Skew Orthogonal Convolutions
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:9756-9766
Multi-Task Reinforcement Learning with Context-based Representations
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:9767-9779
Shortest-Path Constrained Reinforcement Learning for Sparse Reward Tasks
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:9780-9790
Accelerating Feedforward Computation via Parallel Nonlinear Equation Solving
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:9791-9800
PC-MLP: Model-based Reinforcement Learning with Policy Cover Guided Exploration
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:9801-9811
Fast Sketching of Polynomial Kernels of Polynomial Degree
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:9812-9823
Variance Reduction via Primal-Dual Accelerated Dual Averaging for Nonsmooth Convex Finite-Sums
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:9824-9834
Oblivious Sketching-based Central Path Method for Linear Programming
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:9835-9847
Causal Curiosity: RL Agents Discovering Self-supervised Experiments for Causal Representation Learning
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:9848-9858
Decomposed Mutual Information Estimation for Contrastive Representation Learning
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:9859-9869
Decoupling Representation Learning from Reinforcement Learning
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:9870-9879
K-shot NAS: Learnable Weight-Sharing for NAS with K-shot Supernets
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:9880-9890
More Powerful and General Selective Inference for Stepwise Feature Selection using Homotopy Method
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:9891-9901
Not All Memories are Created Equal: Learning to Forget by Expiring
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:9902-9912
Nondeterminism and Instability in Neural Network Optimization
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:9913-9922
AutoSampling: Search for Effective Data Sampling Schedules
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:9923-9933
[abs][Download PDF]
What Makes for End-to-End Object Detection?
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:9934-9944
DFAC Framework: Factorizing the Value Function via Quantile Mixture for Multi-Agent Distributional Q-Learning
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:9945-9954
Scalable Variational Gaussian Processes via Harmonic Kernel Decomposition
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:9955-9965
Reasoning Over Virtual Knowledge Bases With Open Predicate Relations
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:9966-9977
[abs][Download PDF]
PAC-Learning for Strategic Classification
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:9978-9988
Reinforcement Learning for Cost-Aware Markov Decision Processes
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:9989-9999
Model-Targeted Poisoning Attacks with Provable Convergence
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:10000-10010
Generalization Error Bound for Hyperbolic Ordinal Embedding
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:10011-10021
Of Moments and Matching: A Game-Theoretic Framework for Closing the Imitation Gap
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:10022-10032
Parallel tempering on optimized paths
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:10033-10042
Robust Representation Learning via Perceptual Similarity Metrics
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:10043-10053
DriftSurf: Stable-State / Reactive-State Learning under Concept Drift
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:10054-10064
Sinkhorn Label Allocation: Semi-Supervised Classification via Annealed Self-Training
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:10065-10075
Approximation Theory Based Methods for RKHS Bandits
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:10076-10085
Supervised Tree-Wasserstein Distance
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:10086-10095
EfficientNetV2: Smaller Models and Faster Training
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:10096-10106
[abs][Download PDF]
SGA: A Robust Algorithm for Partial Recovery of Tree-Structured Graphical Models with Noisy Samples
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:10107-10117
1-bit Adam: Communication Efficient Large-Scale Training with Adam’s Convergence Speed
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:10118-10129
Taylor Expansion of Discount Factors
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:10130-10140
REPAINT: Knowledge Transfer in Deep Reinforcement Learning
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:10141-10152
Understanding the Dynamics of Gradient Flow in Overparameterized Linear models
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:10153-10161
Sequential Domain Adaptation by Synthesizing Distributionally Robust Experts
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:10162-10172
A Language for Counterfactual Generative Models
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:10173-10182
Synthesizer: Rethinking Self-Attention for Transformer Models
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:10183-10192
[abs][Download PDF]
OmniNet: Omnidirectional Representations from Transformers
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:10193-10202
[abs][Download PDF]
T-SCI: A Two-Stage Conformal Inference Algorithm with Guaranteed Coverage for Cox-MLP
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:10203-10213
Moreau-Yosida $f$-divergences
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:10214-10224
Understanding Invariance via Feedforward Inversion of Discriminatively Trained Classifiers
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:10225-10235
Resource Allocation in Multi-armed Bandit Exploration: Overcoming Sublinear Scaling with Adaptive Parallelism
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:10236-10246
Monte Carlo Variational Auto-Encoders
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:10247-10257
Efficient Generative Modelling of Protein Structure Fragments using a Deep Markov Model
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:10258-10267
[abs][Download PDF]
Understanding self-supervised learning dynamics without contrastive pairs
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:10268-10278
Online Learning in Unknown Markov Games
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:10279-10288
BORE: Bayesian Optimization by Density-Ratio Estimation
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:10289-10300
Nonparametric Decomposition of Sparse Tensors
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:10301-10311
Probabilistic Programs with Stochastic Conditioning
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:10312-10323
Deep Continuous Networks
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:10324-10335
Diffusion Earth Mover’s Distance and Distribution Embeddings
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:10336-10346
Training data-efficient image transformers & distillation through attention
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:10347-10357
Conservative Objective Models for Effective Offline Model-Based Optimization
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:10358-10368
Sparse within Sparse Gaussian Processes using Neighbor Information
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:10369-10378
SMG: A Shuffling Gradient-Based Method with Momentum
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:10379-10389
Bayesian Optimistic Optimisation with Exponentially Decaying Regret
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:10390-10400
On Disentangled Representations Learned from Correlated Data
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:10401-10412
A New Formalism, Method and Open Issues for Zero-Shot Coordination
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:10413-10423
Learning a Universal Template for Few-shot Dataset Generalization
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:10424-10433
Provable Meta-Learning of Linear Representations
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:10434-10443
Cumulants of Hawkes Processes are Robust to Observation Noise
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:10444-10454
PixelTransformer: Sample Conditioned Signal Generation
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:10455-10464
[abs][Download PDF]
A Framework for Private Matrix Analysis in Sliding Window Model
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:10465-10475
Fast Projection Onto Convex Smooth Constraints
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:10476-10486
[abs][Download PDF]
SGLB: Stochastic Gradient Langevin Boosting
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:10487-10496
LTL2Action: Generalizing LTL Instructions for Multi-Task RL
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:10497-10508
Active Deep Probabilistic Subsampling
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:10509-10518
CURI: A Benchmark for Productive Concept Learning Under Uncertainty
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:10519-10529
Towards Domain-Agnostic Contrastive Learning
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:10530-10541
Sparsifying Networks via Subdifferential Inclusion
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:10542-10552
Unbiased Gradient Estimation in Unrolled Computation Graphs with Persistent Evolution Strategies
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:10553-10563
Online Graph Dictionary Learning
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:10564-10574
Neuro-algorithmic Policies Enable Fast Combinatorial Generalization
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:10575-10585
Efficient Training of Robust Decision Trees Against Adversarial Examples
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:10586-10595
[abs][Download PDF]
Object Segmentation Without Labels with Large-Scale Generative Models
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:10596-10606
[abs][Download PDF]
Principal Component Hierarchy for Sparse Quadratic Programs
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:10607-10616
Whitening and Second Order Optimization Both Make Information in the Dataset Unusable During Training, and Can Reduce or Prevent Generalization
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:10617-10629
Safe Reinforcement Learning Using Advantage-Based Intervention
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:10630-10640
Task-Optimal Exploration in Linear Dynamical Systems
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:10641-10652
Learning and Planning in Average-Reward Markov Decision Processes
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:10653-10662
Think Global and Act Local: Bayesian Optimisation over High-Dimensional Categorical and Mixed Search Spaces
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:10663-10674
Zero-Shot Knowledge Distillation from a Decision-Based Black-Box Model
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:10675-10685
Fairness of Exposure in Stochastic Bandits
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:10686-10696
A Proxy Variable View of Shared Confounding
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:10697-10707
Fast Algorithms for Stackelberg Prediction Game with Least Squares Loss
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:10708-10716
Accelerate CNNs from Three Dimensions: A Comprehensive Pruning Framework
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:10717-10726
Explainable Automated Graph Representation Learning with Hyperparameter Importance
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:10727-10737
Self-Tuning for Data-Efficient Deep Learning
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:10738-10748
Label Distribution Learning Machine
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:10749-10759
AlphaNet: Improved Training of Supernets with Alpha-Divergence
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:10760-10771
Global Convergence of Policy Gradient for Linear-Quadratic Mean-Field Control/Game in Continuous Time
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:10772-10782
SG-PALM: a Fast Physically Interpretable Tensor Graphical Model
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:10783-10793
Deep Generative Learning via Schrödinger Bridge
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:10794-10804
Robust Inference for High-Dimensional Linear Models via Residual Randomization
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:10805-10815
A Modular Analysis of Provable Acceleration via Polyak’s Momentum: Training a Wide ReLU Network and a Deep Linear Network
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:10816-10827
Optimal Non-Convex Exact Recovery in Stochastic Block Model via Projected Power Method
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:10828-10838
ConvexVST: A Convex Optimization Approach to Variance-stabilizing Transformation
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:10839-10848
The Implicit Bias for Adaptive Optimization Algorithms on Homogeneous Neural Networks
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:10849-10858
Robust Learning for Data Poisoning Attacks
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:10859-10869
SketchEmbedNet: Learning Novel Concepts by Imitating Drawings
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:10870-10881
Directional Bias Amplification
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:10882-10893
An exact solver for the Weston-Watkins SVM subproblem
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:10894-10904
SCC: an efficient deep reinforcement learning agent mastering the game of StarCraft II
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:10905-10915
Quantum algorithms for reinforcement learning with a generative model
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:10916-10926
Matrix Completion with Model-free Weighting
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:10927-10936
UniSpeech: Unified Speech Representation Learning with Labeled and Unlabeled Data
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:10937-10947
[abs][Download PDF]
Instabilities of Offline RL with Pre-Trained Neural Representation
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:10948-10960
Learning to Weight Imperfect Demonstrations
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:10961-10970
Evolving Attention with Residual Convolutions
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:10971-10980
Guarantees for Tuning the Step Size using a Learning-to-Learn Approach
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:10981-10990
Bridging Multi-Task Learning and Meta-Learning: Towards Efficient Training and Effective Adaptation
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:10991-11002
Towards Better Laplacian Representation in Reinforcement Learning with Generalized Graph Drawing
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:11003-11012
Robust Asymmetric Learning in POMDPs
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:11013-11023
A Unified Generative Adversarial Network Training via Self-Labeling and Self-Attention
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:11024-11034
[abs][Download PDF]
Decision-Making Under Selective Labels: Optimal Finite-Domain Policies and Beyond
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:11035-11046
Inferring serial correlation with dynamic backgrounds
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:11047-11057
Meta-learning Hyperparameter Performance Prediction with Neural Processes
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:11058-11067
A Structured Observation Distribution for Generative Biological Sequence Prediction and Forecasting
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:11068-11079
Thinking Like Transformers
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:11080-11090
Leveraged Weighted Loss for Partial Label Learning
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:11091-11100
Characterizing the Gap Between Actor-Critic and Policy Gradient
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:11101-11111
Toward Understanding the Feature Learning Process of Self-supervised Contrastive Learning
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:11112-11122
[abs][Download PDF]
Keyframe-Focused Visual Imitation Learning
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:11123-11133
Learning de-identified representations of prosody from raw audio
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:11134-11145
[abs][Download PDF]
Solving Inverse Problems with a Flow-based Noise Model
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:11146-11157
Composing Normalizing Flows for Inverse Problems
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:11158-11169
Which transformer architecture fits my data? A vocabulary bottleneck in self-attention
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:11170-11181
Prediction-Centric Learning of Independent Cascade Dynamics from Partial Observations
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:11182-11192
Leveraging Language to Learn Program Abstractions and Search Heuristics
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:11193-11204
Leveraging Sparse Linear Layers for Debuggable Deep Networks
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:11205-11216
Learning Neural Network Subspaces
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:11217-11227
Conjugate Energy-Based Models
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:11228-11239
Making Paper Reviewing Robust to Bid Manipulation Attacks
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:11240-11250
LIME: Learning Inductive Bias for Primitives of Mathematical Reasoning
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:11251-11262
ChaCha for Online AutoML
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:11263-11273
Temporally Correlated Task Scheduling for Sequence Learning
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:11274-11284
Class2Simi: A Noise Reduction Perspective on Learning with Noisy Labels
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:11285-11295
On Reinforcement Learning with Adversarial Corruption and Its Application to Block MDP
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:11296-11306
Generative Video Transformer: Can Objects be the Words?
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:11307-11318
Uncertainty Weighted Actor-Critic for Offline Reinforcement Learning
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:11319-11328
Towards Open-World Recommendation: An Inductive Model-based Collaborative Filtering Approach
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:11329-11339
Data-efficient Hindsight Off-policy Option Learning
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:11340-11350
A Bit More Bayesian: Domain-Invariant Learning with Uncertainty
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:11351-11361
On the Optimality of Batch Policy Optimization Algorithms
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:11362-11371
CRFL: Certifiably Robust Federated Learning against Backdoor Attacks
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:11372-11382
RNNRepair: Automatic RNN Repair via Model-based Analysis
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:11383-11392
Deep Reinforcement Learning amidst Continual Structured Non-Stationarity
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:11393-11403
Batch Value-function Approximation with Only Realizability
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:11404-11413
Interaction-Grounded Learning
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:11414-11423
Composed Fine-Tuning: Freezing Pre-Trained Denoising Autoencoders for Improved Generalization
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:11424-11435
Learning While Playing in Mean-Field Games: Convergence and Optimality
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:11436-11447
Positive-Negative Momentum: Manipulating Stochastic Gradient Noise to Improve Generalization
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:11448-11458
A Hybrid Variance-Reduced Method for Decentralized Stochastic Non-Convex Optimization
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:11459-11469
Explore Visual Concept Formation for Image Classification
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:11470-11479
[abs][Download PDF]
CRPO: A New Approach for Safe Reinforcement Learning with Convergence Guarantee
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:11480-11491
To be Robust or to be Fair: Towards Fairness in Adversarial Training
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:11492-11501
Interpretable Stein Goodness-of-fit Tests on Riemannian Manifold
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:11502-11513
Rethinking Neural vs. Matrix-Factorization Collaborative Filtering: the Theoretical Perspectives
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:11514-11524
Dash: Semi-Supervised Learning with Dynamic Thresholding
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:11525-11536
An End-to-End Framework for Molecular Conformation Generation via Bilevel Programming
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:11537-11547
Self-supervised Graph-level Representation Learning with Local and Global Structure
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:11548-11558
Conformal prediction interval for dynamic time-series
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:11559-11569
Learner-Private Convex Optimization
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:11570-11580
Doubly Robust Off-Policy Actor-Critic: Convergence and Optimality
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:11581-11591
Optimization of Graph Neural Networks: Implicit Acceleration by Skip Connections and More Depth
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:11592-11602
Group-Sparse Matrix Factorization for Transfer Learning of Word Embeddings
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:11603-11612
[abs][Download PDF]
KNAS: Green Neural Architecture Search
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:11613-11625
[abs][Download PDF]
Structured Convolutional Kernel Networks for Airline Crew Scheduling
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:11626-11636
Mediated Uncoupled Learning: Learning Functions without Direct Input-output Correspondences
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:11637-11647
EL-Attention: Memory Efficient Lossless Attention for Generation
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:11648-11658
Link Prediction with Persistent Homology: An Interactive View
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:11659-11669
CATE: Computation-aware Neural Architecture Encoding with Transformers
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:11670-11681
On Perceptual Lossy Compression: The Cost of Perceptual Reconstruction and An Optimal Training Framework
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:11682-11692
CIFS: Improving Adversarial Robustness of CNNs via Channel-wise Importance-based Feature Selection
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:11693-11703
Exact Gap between Generalization Error and Uniform Convergence in Random Feature Models
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:11704-11715
Learning Optimal Auctions with Correlated Valuations from Samples
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:11716-11726
Tensor Programs IV: Feature Learning in Infinite-Width Neural Networks
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:11727-11737
LARNet: Lie Algebra Residual Network for Face Recognition
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:11738-11750
BASGD: Buffered Asynchronous SGD for Byzantine Learning
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:11751-11761
Tensor Programs IIb: Architectural Universality Of Neural Tangent Kernel Training Dynamics
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:11762-11772
Graph Neural Networks Inspired by Classical Iterative Algorithms
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:11773-11783
Representation Matters: Offline Pretraining for Sequential Decision Making
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:11784-11794
Accelerating Safe Reinforcement Learning with Constraint-mismatched Baseline Policies
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:11795-11807
Voice2Series: Reprogramming Acoustic Models for Time Series Classification
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:11808-11819
When All We Need is a Piece of the Pie: A Generic Framework for Optimizing Two-way Partial AUC
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:11820-11829
Rethinking Rotated Object Detection with Gaussian Wasserstein Distance Loss
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:11830-11841
Delving into Deep Imbalanced Regression
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:11842-11851
Backpropagated Neighborhood Aggregation for Accurate Training of Spiking Neural Networks
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:11852-11862
SimAM: A Simple, Parameter-Free Attention Module for Convolutional Neural Networks
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:11863-11874
HAWQ-V3: Dyadic Neural Network Quantization
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:11875-11886
Improving Generalization in Meta-learning via Task Augmentation
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:11887-11897
Deep Learning for Functional Data Analysis with Adaptive Basis Layers
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:11898-11908
Addressing Catastrophic Forgetting in Few-Shot Problems
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:11909-11919
Reinforcement Learning with Prototypical Representations
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:11920-11931
[abs][Download PDF]
Elementary superexpressive activations
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:11932-11940
[abs][Download PDF]
Break-It-Fix-It: Unsupervised Learning for Program Repair
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:11941-11952
[abs][Download PDF]
Improving Gradient Regularization using Complex-Valued Neural Networks
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:11953-11963
Neighborhood Contrastive Learning Applied to Online Patient Monitoring
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:11964-11974
From Local Structures to Size Generalization in Graph Neural Networks
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:11975-11986
Improved OOD Generalization via Adversarial Training and Pretraing
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:11987-11997
Regret and Cumulative Constraint Violation Analysis for Online Convex Optimization with Long Term Constraints
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:11998-12008
Continuous-time Model-based Reinforcement Learning
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:12009-12018
Distributed Nyström Kernel Learning with Communications
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:12019-12028
Path Planning using Neural A* Search
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:12029-12039
SinIR: Efficient General Image Manipulation with Single Image Reconstruction
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:12040-12050
Conditional Temporal Neural Processes with Covariance Loss
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:12051-12061
Adversarial Purification with Score-based Generative Models
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:12062-12072
Federated Continual Learning with Weighted Inter-client Transfer
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:12073-12086
[abs][Download PDF]
Autoencoding Under Normalization Constraints
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:12087-12097
Accelerated Algorithms for Smooth Convex-Concave Minimax Problems with O(1/k^2) Rate on Squared Gradient Norm
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:12098-12109
Lower-Bounded Proper Losses for Weakly Supervised Classification
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:12110-12120
Graph Contrastive Learning Automated
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:12121-12132
LogME: Practical Assessment of Pre-trained Models for Transfer Learning
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:12133-12143
Exponentially Many Local Minima in Quantum Neural Networks
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:12144-12155
DAGs with No Curl: An Efficient DAG Structure Learning Approach
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:12156-12166
Provably Efficient Algorithms for Multi-Objective Competitive RL
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:12167-12176
Whittle Networks: A Deep Likelihood Model for Time Series
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:12177-12186
Deep Latent Graph Matching
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:12187-12197
Learning Generalized Intersection Over Union for Dense Pixelwise Prediction
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:12198-12207
Large Scale Private Learning via Low-rank Reparametrization
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:12208-12218
Federated Deep AUC Maximization for Hetergeneous Data with a Constant Communication Complexity
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:12219-12229
Neural Tangent Generalization Attacks
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:12230-12240
On Explainability of Graph Neural Networks via Subgraph Explorations
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:12241-12252
Federated Composite Optimization
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:12253-12266
Three Operator Splitting with a Nonconvex Loss Function
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:12267-12277
Grey-box Extraction of Natural Language Models
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:12278-12286
Exponential Lower Bounds for Batch Reinforcement Learning: Batch RL can be Exponentially Harder than Online RL
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:12287-12297
Learning Binary Decision Trees by Argmin Differentiation
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:12298-12309
Barlow Twins: Self-Supervised Learning via Redundancy Reduction
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:12310-12320
You Only Sample (Almost) Once: Linear Cost Self-Attention Via Bernoulli Sampling
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:12321-12332
DouZero: Mastering DouDizhu with Self-Play Deep Reinforcement Learning
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:12333-12344
DORO: Distributional and Outlier Robust Optimization
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:12345-12355
Can Subnetwork Structure Be the Key to Out-of-Distribution Generalization?
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:12356-12367
Towards Certifying L-infinity Robustness using Neural Networks with L-inf-dist Neurons
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:12368-12379
Efficient Lottery Ticket Finding: Less Data is More
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:12380-12390
Robust Policy Gradient against Strong Data Corruption
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:12391-12401
Near Optimal Reward-Free Reinforcement Learning
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:12402-12412
Bayesian Attention Belief Networks
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:12413-12426
[abs][Download PDF]
Understanding Failures in Out-of-Distribution Detection with Deep Generative Models
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:12427-12436
Poolingformer: Long Document Modeling with Pooling Attention
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:12437-12446
[abs][Download PDF]
Probabilistic Generating Circuits
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:12447-12457
PAPRIKA: Private Online False Discovery Rate Control
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:12458-12467
Learning from Noisy Labels with No Change to the Training Process
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:12468-12478
Progressive-Scale Boundary Blackbox Attack via Projective Gradient Estimation
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:12479-12490
FOP: Factorizing Optimal Joint Policy of Maximum-Entropy Multi-Agent Reinforcement Learning
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:12491-12500
Learning Noise Transition Matrix from Only Noisy Labels via Total Variation Regularization
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:12501-12512
Quantile Bandits for Best Arms Identification
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:12513-12523
Towards Better Robust Generalization with Shift Consistency Regularization
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:12524-12534
On-Policy Deep Reinforcement Learning for the Average-Reward Criterion
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:12535-12545
Differentiable Dynamic Quantization with Mixed Precision and Adaptive Resolution
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:12546-12556
iDARTS: Differentiable Architecture Search with Stochastic Implicit Gradients
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:12557-12566
Deep Coherent Exploration for Continuous Control
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:12567-12577
Average-Reward Off-Policy Policy Evaluation with Function Approximation
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:12578-12588
Matrix Sketching for Secure Collaborative Machine Learning
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:12589-12599
MetaCURE: Meta Reinforcement Learning with Empowerment-Driven Exploration
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:12600-12610
World Model as a Graph: Learning Latent Landmarks for Planning
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:12611-12620
Breaking the Deadly Triad with a Target Network
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:12621-12631
Multiscale Invertible Generative Networks for High-Dimensional Bayesian Inference
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:12632-12641
Meta Learning for Support Recovery in High-dimensional Precision Matrix Estimation
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:12642-12652
Model-Free Reinforcement Learning: from Clipped Pseudo-Regret to Sample Complexity
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:12653-12662
Learning to Rehearse in Long Sequence Memorization
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:12663-12673
Dataset Condensation with Differentiable Siamese Augmentation
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:12674-12685
[abs][Download PDF]
Joining datasets via data augmentation in the label space for neural networks
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:12686-12696
Calibrate Before Use: Improving Few-shot Performance of Language Models
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:12697-12706
Few-Shot Neural Architecture Search
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:12707-12718
Expressive 1-Lipschitz Neural Networks for Robust Multiple Graph Learning against Adversarial Attacks
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:12719-12735
Fused Acoustic and Text Encoding for Multimodal Bilingual Pretraining and Speech Translation
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:12736-12746
[abs][Download PDF]
Two Heads are Better Than One: Hypergraph-Enhanced Graph Reasoning for Visual Event Ratiocination
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:12747-12760
[abs][Download PDF]
How Framelets Enhance Graph Neural Networks
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:12761-12771
Probabilistic Sequential Shrinking: A Best Arm Identification Algorithm for Stochastic Bandits with Corruptions
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:12772-12781
Towards Distraction-Robust Active Visual Tracking
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:12782-12792
Provably Efficient Reinforcement Learning for Discounted MDPs with Feature Mapping
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:12793-12802
Amortized Conditional Normalized Maximum Likelihood: Reliable Out of Distribution Uncertainty Estimation
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:12803-12812
Optimal Estimation of High Dimensional Smooth Additive Function Based on Noisy Observations
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:12813-12823
Incentivized Bandit Learning with Self-Reinforcing User Preferences
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:12824-12834
Towards Defending against Adversarial Examples via Attack-Invariant Features
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:12835-12845
Asymmetric Loss Functions for Learning with Noisy Labels
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:12846-12856
Examining and Combating Spurious Features under Distribution Shift
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:12857-12867
Sparse and Imperceptible Adversarial Attack via a Homotopy Algorithm
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:12868-12877
Data-Free Knowledge Distillation for Heterogeneous Federated Learning
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:12878-12889
Spectral vertex sparsifiers and pair-wise spanners over distributed graphs
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:12890-12900
Few-shot Language Coordination by Modeling Theory of Mind
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:12901-12911
Clusterability as an Alternative to Anchor Points When Learning with Noisy Labels
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:12912-12923
Commutative Lie Group VAE for Disentanglement Learning
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:12924-12934
Accumulated Decoupled Learning with Gradient Staleness Mitigation for Convolutional Neural Networks
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:12935-12944
Demystifying Inductive Biases for (Beta-)VAE Based Architectures
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:12945-12954
Recovering AES Keys with a Deep Cold Boot Attack
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:12955-12966
[abs][Download PDF]
Learning Fair Policies in Decentralized Cooperative Multi-Agent Reinforcement Learning
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:12967-12978
Contrastive Learning Inverts the Data Generating Process
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:12979-12990
Exploration in Approximate Hyper-State Space for Meta Reinforcement Learning
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:12991-13001
Provable Robustness of Adversarial Training for Learning Halfspaces with Noise
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:13002-13011
On the Convergence of Hamiltonian Monte Carlo with Stochastic Gradients
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:13012-13022
A Functional Perspective on Learning Symmetric Functions with Neural Networks
; Proceedings of the 38th International Conference on Machine Learning, PMLR 139:13023-13032
subscribe via RSS