![[International Conference on Machine Learning Logo]](/v202/assets/images/logo-pmlr.svg){kind=logo}
[edit]
Volume 202: International Conference on Machine Learning, 23-29 July 2023, Honolulu, Hawaii, USA
[edit]
Editors: Andreas Krause, Emma Brunskill, Kyunghyun Cho, Barbara Engelhardt, Sivan Sabato, Jonathan Scarlett
Data Structures for Density Estimation
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:1-18
ClusterFuG: Clustering Fully connected Graphs by Multicut
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:19-30
Generalization on the Unseen, Logic Reasoning and Degree Curriculum
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:31-60
Toward Large Kernel Models
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:61-78
Expertise Trees Resolve Knowledge Limitations in Collective Decision-Making
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:79-90
Comparison of meta-learners for estimating multi-valued treatment heterogeneous effects
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:91-132
BNN-DP: Robustness Certification of Bayesian Neural Networks via Dynamic Programming
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:133-151
SAM operates far from home: eigenvalue regularization as a dynamical phenomenon
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:152-168
Second-order regression models exhibit progressive sharpening to the edge of stability
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:169-195
Global optimality of Elman-type RNNs in the mean-field regime
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:196-227
SemSup-XC: Semantic Supervision for Zero and Few-shot Extreme Classification
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:228-247
Adaptive IMLE for Few-shot Pretraining-free Generative Modelling
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:248-264
Scaling Laws for Generative Mixed-Modal Language Models
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:265-279
Hypothesis Transfer Learning with Surrogate Classification Losses: Generalization Bounds through Algorithmic Stability
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:280-303
Constrained Causal Bayesian Optimization
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:304-321
Explaining the effects of non-convergent MCMC in the training of Energy-Based Models
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:322-336
Using Large Language Models to Simulate Multiple Humans and Replicate Human Subject Studies
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:337-371
Interventional Causal Representation Learning
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:372-407
Sequential Underspecified Instrument Selection for Cause-Effect Estimation
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:408-420
Atari-5: Distilling the Arcade Learning Environment down to Five Games
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:421-438
Towards credible visual model interpretation with path attribution
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:439-457
Convergence of First-Order Methods for Constrained Nonconvex Optimization with Dependent Data
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:458-489
Recasting Self-Attention with Holographic Reduced Representations
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:490-507
The Saddle-Point Method in Differential Privacy
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:508-528
Nonlinear Advantage: Trained Networks Might Not Be As Complex as You Think
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:529-546
A Simple Zero-shot Prompt Weighting Technique to Improve Prompt Ensembling in Text-Image Models
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:547-568
On the Privacy-Robustness-Utility Trilemma in Distributed Learning
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:569-626
Differentially Private Distributed Bayesian Linear Regression with MCMC
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:627-641
Robust and Scalable Bayesian Online Changepoint Detection
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:642-663
Neural Wasserstein Gradient Flows for Discrepancies with Riesz Kernels
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:664-690
Distributed Contextual Linear Bandits with Minimax Optimal Communication Cost
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:691-717
A Kernelized Stein Discrepancy for Biological Sequences
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:718-767
The Optimal Approximation Factors in Misspecified Off-Policy Value Function Estimation
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:768-790
Meta Optimal Transport
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:791-813
Near-Optimal $Φ$-Regret Learning in Extensive-Form Games
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:814-839
A Modern Look at the Relationship between Sharpness and Generalization
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:840-902
SGD with Large Step Sizes Learns Sparse Features
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:903-925
Neural Continuous-Discrete State Space Models for Irregularly-Sampled Time Series
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:926-951
Paging with Succinct Predictions
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:952-968
Mixing Predictions for Online Metric Algorithms
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:969-983
Exponential Smoothing for Off-Policy Learning
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:984-1017
Polynomial Time and Private Learning of Unbounded Gaussian Mixture Models
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:1018-1040
Principled Acceleration of Iterative Numerical Methods Using Machine Learning
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:1041-1059
Faster Rates of Convergence to Stationary Points in Differentially Private Optimization
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:1060-1092
Prototype-Sample Relation Distillation: Towards Replay-Free Continual Learning
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:1093-1106
Near-Optimal Algorithms for Private Online Optimization in the Realizable Regime
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:1107-1120
From Robustness to Privacy and Back
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:1121-1146
SGD with AdaGrad Stepsizes: Full Adaptivity with High Probability to Unknown Parameters, Unbounded Gradients and Affine Variance
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:1147-1171
Adversarially Robust PAC Learnability of Real-Valued Functions
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:1172-1199
Infusing Lattice Symmetry Priors in Attention Mechanisms for Sample-Efficient Abstract Geometric Reasoning
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:1200-1217
Learning to Initiate and Reason in Event-Driven Cascading Processes
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:1218-1243
On the convergence of the MLE as an estimator of the learning rate in the Exp3 algorithm
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:1244-1275
Dirichlet Diffusion Score Model for Biological Sequence Generation
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:1276-1301
Gradient Descent Converges Linearly for Logistic Regression on Separable Data
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:1302-1319
Naive imputation implicitly regularizes high-dimensional linear models
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:1320-1340
Half-Hop: A graph upsampling approach for slowing down message passing
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:1341-1360
CLUTR: Curriculum Learning via Unsupervised Task Representation Learning
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:1361-1395
Personalized Subgraph Federated Learning
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:1396-1415
Efficient Self-supervised Learning with Contextualized Target Representations for Vision, Speech and Language
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:1416-1429
Efficient preconditioned stochastic gradient descent for estimation in latent variable models
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:1430-1453
Feed Two Birds with One Scone: Exploiting Wild Data for Both Out-of-Distribution Generalization and Detection
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:1454-1471
Answering Complex Logical Queries on Knowledge Graphs via Query Computation Tree Optimization
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:1472-1491
Linear optimal partial transport embedding
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:1492-1520
Implicit Graph Neural Networks: A Monotone Operator Viewpoint
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:1521-1548
Tensor Decompositions Meet Control Theory: Learning General Mixtures of Linear Dynamical Systems
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:1549-1563
Block Subsampled Randomized Hadamard Transform for Nyström Approximation on Distributed Architectures
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:1564-1576
Efficient Online Reinforcement Learning with Offline Data
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:1577-1594
Mirror Sinkhorn: Fast Online Optimization on Transport Polytopes
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:1595-1613
On the Functional Similarity of Robust and Non-Robust Neural Representations
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:1614-1635
Robust Budget Pacing with a Single Sample
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:1636-1659
Dynamic Constrained Submodular Optimization with Polylogarithmic Update Time
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:1660-1691
One Transformer Fits All Distributions in Multi-Modal Diffusion at Scale
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:1692-1717
Optimizing the Collaboration Structure in Cross-Silo Federated Learning
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:1718-1736
MultiDiffusion: Fusing Diffusion Paths for Controlled Image Generation
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:1737-1752
Reinforcement Learning with General Utilities: Simpler Variance Reduction and Large State-Action Space
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:1753-1800
Interpretable Neural-Symbolic Concept Reasoning
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:1801-1825
Moccasin: Efficient Tensor Rematerialization for Neural Networks
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:1826-1837
User-level Private Stochastic Convex Optimization with Optimal Rates
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:1838-1851
A Statistical Perspective on Retrieval-Based Models
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:1852-1886
Human-Timescale Adaptation in an Open-Ended Task Space
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:1887-1935
A Kernel Stein Test of Goodness of Fit for Sequential Models
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:1936-1953
Individually Fair Learning with One-Sided Feedback
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:1954-1977
Predicting Ordinary Differential Equations with Transformers
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:1978-2002
Explaining Reinforcement Learning with Shapley Values
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:2003-2014
TIDE: Time Derivative Diffusion for Deep Learning on Graphs
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:2015-2030
Fast as CHITA: Neural Network Pruning with Combinatorial Optimization
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:2031-2049
Continuously Parameterized Mixture Models
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:2050-2062
Controllable Neural Symbolic Regression
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:2063-2077
On Second-Order Scoring Rules for Epistemic Uncertainty Quantification
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:2078-2091
Certified Robust Neural Networks: Generalization and Corruption Resistance
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:2092-2112
Gaussian processes at the Helm(holtz): A more fluid model for ocean currents
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:2113-2163
Optimal Rates and Efficient Algorithms for Online Bayesian Persuasion
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:2164-2183
Constrained Phi-Equilibria
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:2184-2205
Differentiable and Transportable Structure Learning
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:2206-2233
Polyhedral Complex Extraction from ReLU Networks using Edge Subdivision
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:2234-2244
Robust One-Class Classification with Signed Distance Function using 1-Lipschitz Neural Networks
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:2245-2271
Neural Algorithmic Reasoning with Causal Regularisation
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:2272-2288
Optimally-weighted Estimators of the Maximum Mean Discrepancy for Likelihood-Free Inference
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:2289-2312
Bandit Online Linear Optimization with Hints and Queries
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:2313-2336
Improved Online Conformal Prediction via Strongly Adaptive Online Learning
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:2337-2363
Data-Copying in Generative Models: A Formal Framework
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:2364-2396
Pythia: A Suite for Analyzing Large Language Models Across Training and Scaling
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:2397-2430
StriderNet: A Graph Reinforcement Learning Approach to Optimize Atomic Structures on Rough Energy Landscapes
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:2431-2451
Modeling Temporal Data as Continuous Functions with Stochastic Process Diffusion
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:2452-2470
In or Out? Fixing ImageNet Out-of-Distribution Detection Evaluation
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:2471-2506
Invariant Slot Attention: Object Discovery with Slot-Centric Reference Frames
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:2507-2527
Understanding Oversquashing in GNNs through the Lens of Effective Resistance
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:2528-2547
Unit Scaling: Out-of-the-Box Low-Precision Training
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:2548-2576
FLEX: an Adaptive Exploration Algorithm for Nonlinear Systems
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:2577-2591
Not all Strongly Rayleigh Distributions Have Small Probabilistic Generating Circuits
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:2592-2602
Learning the Dynamics of Sparsely Observed Interacting Systems
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:2603-2640
Subset Selection Based On Multiple Rankings in the Presence of Bias: Effectiveness of Fairness Constraints for Multiwinner Voting Score Functions
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:2641-2688
Properties of the Mallows Model Depending on the Number of Alternatives: A Warning for an Experimentalist
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:2689-2711
A Robust Optimisation Perspective on Counterexample-Guided Repair of Neural Networks
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:2712-2737
Beyond the Universal Law of Robustness: Sharper Laws for Random Features and Neural Tangent Kernels
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:2738-2776
Sliced-Wasserstein on Symmetric Positive Definite Matrices for M/EEG Signals
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:2777-2805
Spherical Fourier Neural Operators: Learning Stable Dynamics on the Sphere
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:2806-2823
The Regret of Exploration and the Control of Bad Episodes in Reinforcement Learning
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:2824-2856
Model-agnostic Measure of Generalization Difficulty
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:2857-2884
Returning The Favour: When Regression Benefits From Probabilistic Causal Knowledge
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:2885-2913
In Search for a Generalizable Method for Source Free Domain Adaptation
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:2914-2931
Quantum Speedups for Zero-Sum Games via Improved Dynamic Gibbs Sampling
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:2932-2952
Diffusion Models as Artists: Are we Closing the Gap between Humans and Machines?
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:2953-3002
Settling the Reward Hypothesis
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:3003-3020
ILLUME: Rationalizing Vision-Language Models through Human Interactions
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:3021-3037
Provably Learning Object-Centric Representations
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:3038-3062
Quantifying Human Priors over Social and Navigation Networks
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:3063-3105
Critical Points and Convergence Analysis of Generative Deep Linear Networks Trained with Bures-Wasserstein Loss
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:3106-3147
Emergence of Sparse Representations from Noise
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:3148-3191
Differentially Private Optimization on Large Model at Small Cost
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:3192-3218
Machine Learning Force Fields with Data Cost Aware Training
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:3219-3232
Label differential privacy and private training data release
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:3233-3251
The SSL Interplay: Augmentations, Inductive Bias, and Generalization
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:3252-3298
Online Mechanism Design for Information Acquisition
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:3299-3326
MyoDex: A Generalizable Prior for Dexterous Manipulation
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:3327-3346
What Can Be Learnt With Wide Convolutional Neural Networks?
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:3347-3379
Causal Discovery with Latent Confounders Based on Higher-Order Cumulants
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:3380-3407
On the Connection Between MPNN and Graph Transformer
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:3408-3430
Ske2Grid: Skeleton-to-Grid Representation Learning for Action Recognition
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:3431-3441
Extrapolated Random Tree for Regression
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:3442-3468
Cyclic Block Coordinate Descent With Variance Reduction for Composite Nonconvex Optimization
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:3469-3494
Robust Weight Signatures: Gaining Robustness as Easy as Patching Weights?
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:3495-3506
Doubly Optimal No-Regret Learning in Monotone Games
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:3507-3524
Multi-Agent Learning from Learners
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:3525-3540
Efficient Learning of Mesh-Based Physical Simulation with Bi-Stride Multi-Scale Graph Neural Network
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:3541-3558
Variational Sparse Inverse Cholesky Approximation for Latent Gaussian Processes via Double Kullback-Leibler Minimization
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:3559-3576
Learning Lightweight Object Detectors via Multi-Teacher Progressive Distillation
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:3577-3598
One-sided Matrix Completion from Two Observations Per Row
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:3599-3624
State and parameter learning with PARIS particle Gibbs
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:3625-3675
Grounding Large Language Models in Interactive Environments with Online Reinforcement Learning
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:3676-3713
Stein Variational Goal Generation for adaptive Exploration in Multi-Goal Reinforcement Learning
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:3714-3731
Scalable Safe Policy Improvement via Monte Carlo Tree Search
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:3732-3756
LESS-VFL: Communication-Efficient Feature Selection for Vertical Federated Learning
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:3757-3781
On the Robustness of Text Vectorizers
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:3782-3814
Learning Globally Smooth Functions on Manifolds
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:3815-3854
Tighter Lower Bounds for Shuffling SGD: Random Permutations and Beyond
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:3855-3912
Orthogonality-Enforced Latent Space in Autoencoders: An Approach to Learning Disentangled Representations
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:3913-3948
STEERING : Stein Information Directed Exploration for Model-Based Reinforcement Learning
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:3949-3978
Thompson Sampling for High-Dimensional Sparse Linear Contextual Bandits
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:3979-4008
Representations and Exploration for Deep Reinforcement Learning using Singular Value Decomposition
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:4009-4034
Memory-Based Dual Gaussian Processes for Sequential Learning
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:4035-4054
Muse: Text-To-Image Generation via Masked Generative Transformers
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:4055-4075
On Investigating the Conservative Property of Score-Based Generative Models
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:4076-4095
Robust and private stochastic linear bandits
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:4096-4115
Streaming Submodular Maximization with Differential Privacy
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:4116-4143
Why does Throwing Away Data Improve Worst-Group Error?
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:4144-4188
Collaborative Multi-Agent Heterogeneous Multi-Armed Bandits
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:4189-4217
Correcting discount-factor mismatch in on-policy policy gradient methods
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:4218-4240
Fast Federated Machine Unlearning with Nonlinear Functional Theory
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:4241-4268
On the Statistical Benefits of Temporal Difference Learning
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:4269-4293
Multi-Layer Neural Networks as Trainable Ladders of Hilbert Spaces
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:4294-4329
Beyond the Edge of Stability via Two-step Gradient Updates
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:4330-4391
Trompt: Towards a Better Deep Neural Network for Tabular Data
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:4392-4434
Differentially Private Stochastic Convex Optimization under a Quantile Loss Function
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:4435-4461
Restoration-Degradation Beyond Linear Diffusions: A Non-Asymptotic Analysis For DDIM-type Samplers
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:4462-4484
Provably Convergent Schrödinger Bridge with Applications to Probabilistic Time Series Imputation
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:4485-4513
ED-Batch: Efficient Automatic Batching of Dynamic Neural Networks via Learned Finite State Machines
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:4514-4528
Is Learning Summary Statistics Necessary for Likelihood-free Inference?
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:4529-4544
Subequivariant Graph Reinforcement Learning in 3D Environments
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:4545-4565
GuardHFL: Privacy Guardian for Heterogeneous Federated Learning
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:4566-4584
Efficient and Degree-Guided Graph Generation via Discrete Diffusion Modeling
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:4585-4610
Evolving Semantic Prototype Improves Generative Zero-Shot Learning
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:4611-4622
Explore and Exploit the Diverse Knowledge in Model Zoo for Domain Generalization
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:4623-4640
Decentralized Stochastic Bilevel Optimization with Improved per-Iteration Complexity
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:4641-4671
Score Approximation, Estimation and Distribution Recovery of Diffusion Models on Low-Dimensional Data
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:4672-4712
Sample Complexity of Probability Divergences under Group Symmetry
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:4713-4734
Improved Analysis of Score-based Generative Modeling: User-Friendly Bounds under Minimal Smoothness Assumptions
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:4735-4763
Bidirectional Looking with A Novel Double Exponential Moving Average to Adaptive and Non-adaptive Momentum Optimizers
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:4764-4803
HarsanyiNet: Computing Accurate Shapley Values in a Single Forward Propagation
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:4804-4825
Generalized Implicit Follow-The-Regularized-Leader
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:4826-4838
Fisher Information Embedding for Node and Graph Learning
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:4839-4855
Rethinking Visual Reconstruction: Experience-Based Content Completion Guided by Visual Cues
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:4856-4866
Stratified Adversarial Robustness with Rejection
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:4867-4894
Multi-task Hierarchical Adversarial Inverse Reinforcement Learning
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:4895-4920
Model Transferability with Responsive Decision Subjects
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:4921-4952
Layered State Discovery for Incremental Autonomous Exploration
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:4953-5001
Optimistic Online Mirror Descent for Bridging Stochastic and Adversarial Online Convex Optimization
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:5002-5035
Learning to Optimize Differentiable Games
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:5036-5051
Coordinated Dynamic Bidding in Repeated Second-Price Auctions with Budgets
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:5052-5086
Semi-Offline Reinforcement Learning for Optimized Text Generation
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:5087-5103
Lower Bounds for Learning in Revealing POMDPs
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:5104-5161
Implicit Neural Spatial Representations for Time-dependent PDEs
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:5162-5177
BEATs: Audio Pre-Training with Acoustic Tokenizers
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:5178-5193
Learning to Incentivize Information Acquisition: Proper Scoring Rules Meet Principal-Agent Model
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:5194-5218
Faster Gradient-Free Algorithms for Nonsmooth Nonconvex Stochastic Optimization
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:5219-5233
Efficient Personalized Federated Learning via Sparse Model-Adaptation
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:5234-5256
A Gromov-Wasserstein Geometric View of Spectrum-Preserving Graph Coarsening
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:5257-5281
How to address monotonicity for model risk management?
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:5282-5295
Sketched Ridgeless Linear Regression: The Role of Downsampling
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:5296-5326
Context-Aware Bayesian Network Actor-Critic Methods for Cooperative Multi-Agent Reinforcement Learning
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:5327-5350
Bidirectional Learning for Offline Model-based Biological Sequence Design
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:5351-5366
Learning to Jump: Thinning and Thickening Latent Counts for Generative Modeling
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:5367-5382
Lifelong Language Pretraining with Distribution-Specialized Experts
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:5383-5395
Generalized-Smooth Nonconvex Optimization is As Efficient As Smooth Nonconvex Optimization
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:5396-5427
Weakly Supervised Regression with Interval Targets
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:5428-5448
PLay: Parametrically Conditioned Layout Generation using Latent Diffusion
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:5449-5471
Identification of the Adversary from a Single Adversarial Example
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:5472-5484
Parallel Online Clustering of Bandits via Hedonic Game
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:5485-5503
Mu$^2$SLAM: Multitask, Multilingual Speech and Language Models
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:5504-5520
Understanding the Role of Feedback in Online Learning with Switching Costs
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:5521-5543
Tighter Bounds on the Expressivity of Transformer Encoders
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:5544-5562
Provably Learning Diverse Features in Multi-View Data with Midpoint Mixup
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:5563-5599
Hiding Data Helps: On the Benefits of Masking for Sparse Coding
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:5600-5615
PINA: Leveraging Side Information in eXtreme Multi-label Classification via Predicted Instance Neighborhood Aggregation
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:5616-5630
Tight Certification of Adversarially Trained Neural Networks via Nonconvex Low-Rank Semidefinite Relaxations
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:5631-5660
Neural Latent Aligner: Cross-trial Alignment for Learning Representations of Complex, Naturalistic Neural Data
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:5661-5676
On the Convergence of Federated Averaging with Cyclic Client Participation
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:5677-5721
GREAD: Graph Neural Reaction-Diffusion Networks
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:5722-5747
Is Overfitting Necessary for Implicit Video Representation?
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:5748-5770
Semi-Parametric Contextual Pricing Algorithm using Cox Proportional Hazards Model
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:5771-5786
Restoration based Generative Models
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:5787-5816
Concept-based Explanations for Out-of-Distribution Detectors
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:5817-5837
Active causal structure learning with advice
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:5838-5867
New metrics and search algorithms for weighted causal DAGs
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:5868-5903
Computational Doob h-transforms for Online Filtering of Discretely Observed Diffusions
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:5904-5923
Multi-Epoch Matrix Factorization Mechanisms for Private Machine Learning
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:5924-5963
Taming graph kernels with random features
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:5964-5977
Efficient Graph Field Integrators Meet Point Clouds
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:5978-6004
ContraBAR: Contrastive Bayes-Adaptive Deep RL
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:6005-6027
Forget Unlearning: Towards True Data-Deletion in Machine Learning
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:6028-6073
Patch-level Routing in Mixture-of-Experts is Provably Sample-efficient for Convolutional Neural Networks
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:6074-6114
What do CNNs Learn in the First Layer and Why? A Linear Systems Perspective
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:6115-6139
Unifying Molecular and Textual Representations via Multi-task Language Modelling
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:6140-6157
Wasserstein Barycenter Matching for Graph Size Generalization of Message Passing Neural Networks
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:6158-6184
Shape-Guided Dual-Memory Learning for 3D Anomaly Detection
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:6185-6194
Multiply Robust Off-policy Evaluation and Learning under Truncation by Death
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:6195-6227
InfoOT: Information Maximizing Optimal Transport
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:6228-6242
A Toy Model of Universality: Reverse Engineering how Networks Learn Group Operations
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:6243-6267
Distribution Free Prediction Sets for Node Classification
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:6268-6278
Sequential Strategic Screening
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:6279-6295
Few-Sample Feature Selection via Feature Manifold Learning
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:6296-6319
Spatial Implicit Neural Representations for Global-Scale Species Mapping
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:6320-6342
K-SHAP: Policy Clustering Algorithm for Anonymous Multi-Agent State-Action Pairs
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:6343-6363
Inferring Relational Potentials in Interacting Systems
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:6364-6383
Task-specific experimental design for treatment effect estimation
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:6384-6401
A Mathematical Model for Curriculum Learning for Parities
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:6402-6423
Learning to Maximize Mutual Information for Dynamic Feature Selection
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:6424-6447
Rethinking Weak Supervision in Helping Contrastive Learning
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:6448-6467
Bayes-optimal Learning of Deep Random Networks of Extensive-width
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:6468-6521
A General Representation Learning Framework with Generalization Performance Guarantees
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:6522-6544
IRNeXt: Rethinking Convolutional Network Design for Image Restoration
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:6545-6564
Scaling Up Dataset Distillation to ImageNet-1K with Constant Memory
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:6565-6590
Learning Dynamic Query Combinations for Transformer-based Object Detection and Segmentation
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:6591-6602
Adaptive Identification of Populations with Treatment Benefit in Clinical Trials: Machine Learning Challenges and Solutions
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:6603-6622
In Search of Insights, Not Magic Bullets: Towards Demystification of the Model Selection Dilemma in Heterogeneous Treatment Effect Estimation
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:6623-6642
Optimal Stochastic Non-smooth Non-convex Optimization through Online-to-Non-convex Conversion
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:6643-6670
Monge, Bregman and Occam: Interpretable Optimal Transport in High-Dimensions with Feature-Sparse Maps
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:6671-6682
From Noisy Fixed-Point Iterations to Private ADMM for Centralized and Federated Learning
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:6683-6711
Chameleon: Adapting to Peer Images for Planting Durable Backdoors in Federated Learning
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:6712-6725
Refined Regret for Adversarial MDPs with Linear Function Approximation
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:6726-6759
MultiRobustBench: Benchmarking Robustness Against Multiple Attacks
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:6760-6785
Moderately Distributional Exploration for Domain Generalization
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:6786-6817
Trajectory-Aware Eligibility Traces for Off-Policy Reinforcement Learning
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:6818-6835
Efficient displacement convex optimization with particle gradient descent
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:6836-6854
Multiple Thinking Achieving Meta-Ability Decoupling for Object Navigation
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:6855-6872
Neural Collapse in Deep Linear Networks: From Balanced to Imbalanced Data
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:6873-6947
Reinforcement Learning Can Be More Efficient with Multiple Rewards
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:6948-6967
Best of Both Worlds Policy Optimization
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:6968-7008
Image generation with shortest path diffusion
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:7009-7024
Efficient List-Decodable Regression using Batches
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:7025-7065
Beyond Uniform Lipschitz Condition in Differentially Private Optimization
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:7066-7101
Understanding Self-Distillation in the Presence of Label Noise
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:7102-7140
Interval Bound Interpolation for Few-shot Learning with Few Tasks
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:7141-7166
Hypervolume Knowledge Gradient: A Lookahead Approach for Multi-Objective Bayesian Optimization with Partial Information
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:7167-7204
Fast Combinatorial Algorithms for Min Max Correlation Clustering
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:7205-7230
Predictive Flows for Faster Ford-Fulkerson
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:7231-7248
The Persistent Laplacian for Data Science: Evaluating Higher-Order Persistent Spectral Representations of Data
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:7249-7263
Mitigating Propagation Failures in Physics-informed Neural Networks using Retain-Resample-Release (R3) Sampling
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:7264-7302
On the Robustness of Randomized Ensembles to Adversarial Perturbations
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:7303-7328
Pre-computed memory or on-the-fly encoding? A hybrid approach to retrieval augmentation makes the most of your compute
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:7329-7342
Continuous Spatiotemporal Transformer
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:7343-7365
The Value of Out-of-Distribution Data
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:7366-7389
High Fidelity Image Counterfactuals with Probabilistic Causal Models
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:7390-7425
Learning Noisy OR Bayesian Networks with Max-Product Belief Propagation
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:7426-7448
Learning-Rate-Free Learning by D-Adaptation
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:7449-7479
Scaling Vision Transformers to 22 Billion Parameters
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:7480-7512
Efficient Bound of Lipschitz Constant for Convolutional Layers by Gram Iteration
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:7513-7532
Blossom: an Anytime Algorithm for Computing Optimal Decision Trees
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:7533-7562
Optimizing NOTEARS Objectives via Topological Swaps
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:7563-7595
Uncertainty Estimation by Fisher Information-based Evidential Deep Learning
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:7596-7616
Multi-channel Autobidding with Budget and ROI Constraints
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:7617-7644
Surrogate Module Learning: Reduce the Gradient Error Accumulation in Training Spiking Neural Networks
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:7645-7657
Confidence and Dispersity Speak: Characterizing Prediction Matrix for Unsupervised Accuracy Estimation
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:7658-7674
Great Models Think Alike: Improving Model Reliability via Inter-Model Latent Agreement
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:7675-7693
Hyperbolic Image-text Representations
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:7694-7731
Hardware-Aware Compression with Random Operation Access Specific Tile (ROAST) Hashing
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:7732-7749
The case for 4-bit precision: k-bit Inference Scaling Laws
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:7750-7774
Fairness in Matching under Uncertainty
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:7775-7794
Efficient Parametric Approximations of Neural Network Function Space Distance
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:7795-7812
A Large-Scale Study of Probabilistic Calibration in Neural Network Regression
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:7813-7836
Nearly Minimax Optimal Regret for Learning Linear Mixture Stochastic Shortest Path
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:7837-7864
On Over-Squashing in Message Passing Neural Networks: The Impact of Width, Depth, and Topology
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:7865-7885
Nearly-Linear Time and Streaming Algorithms for Outlier-Robust PCA
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:7886-7921
Near-Optimal Cryptographic Hardness of Agnostically Learning Halfspaces and ReLU Regression under Gaussian Marginals
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:7922-7938
Improving Graph Generation by Restricting Graph Bandwidth
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:7939-7959
Forward-Backward Gaussian Variational Inference via JKO in the Bures-Wasserstein Space
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:7960-7991
Subset-Based Instance Optimality in Private Estimation
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:7992-8014
Pareto Manifold Learning: Tackling multiple tasks via ensembles of single-task models
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:8015-8052
Bayesian Reparameterization of Reward-Conditioned Reinforcement Learning with Energy-based Models
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:8053-8066
DSGD-CECA: Decentralized SGD with Communication-Optimal Exact Consensus Algorithm
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:8067-8089
Open-Vocabulary Universal Image Segmentation with MaskCLIP
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:8090-8102
Entity Divider with Language Grounding in Multi-Agent Reinforcement Learning
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:8103-8119
PixelAsParam: A Gradient View on Diffusion Sampling with Guidance
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:8120-8137
Second-Order Optimization with Lazy Hessians
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:8138-8161
Polynomial Preconditioning for Gradient Methods
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:8162-8187
On Data Manifolds Entailed by Structural Causal Models
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:8188-8201
Towards Understanding and Reducing Graph Structural Noise for GNNs
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:8202-8226
SpeedDETR: Speed-aware Transformers for End-to-end Object Detection
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:8227-8243
Understand and Modularize Generator Optimization in ELECTRA-style Pretraining
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:8244-8259
Diversity-enhancing Generative Network for Few-shot Hypothesis Adaptation
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:8260-8275
PASTA: Pessimistic Assortment Optimization
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:8276-8295
Adaptively Weighted Data Augmentation Consistency Regularization for Robust Optimization under Concept Shift
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:8296-8316
Does Sparsity Help in Learning Misspecified Linear Bandits?
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:8317-8333
Symmetry-Aware Robot Design with Structured Subgroups
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:8334-8355
DoCoFL: Downlink Compression for Cross-Device Federated Learning
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:8356-8388
Meta-Learning the Inductive Bias of Simple Neural Circuits
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:8389-8402
Self-Repellent Random Walks on General Graphs - Achieving Minimal Sampling Variance via Nonlinear Markov Chains
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:8403-8423
Linear Time GPs for Inferring Latent Trajectories from Neural Spike Trains
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:8424-8448
On the Convergence Rate of Gaussianization with Random Rotations
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:8449-8468
PaLM-E: An Embodied Multimodal Language Model
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:8469-8488
Reduce, Reuse, Recycle: Compositional Generation with Energy-Based Diffusion Models and MCMC
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:8489-8510
Multi-task Representation Learning for Pure Exploration in Linear Bandits
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:8511-8564
Nonparametric Generative Modeling with Conditional Sliced-Wasserstein Flows
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:8565-8584
Subsample Ridge Ensembles: Equivalences and Generalized Cross-Validation
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:8585-8631
On Uni-Modal Feature Learning in Supervised Multi-Modal Learning
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:8632-8656
Guiding Pretraining in Reinforcement Learning with Large Language Models
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:8657-8677
A Flexible Diffusion Model
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:8678-8696
Fast Excess Risk Rates via Offset Rademacher Complexity
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:8697-8716
Are Diffusion Models Vulnerable to Membership Inference Attacks?
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:8717-8730
Bayesian Progressive Deep Topic Model with Knowledge Informed Textual Data Coarsening Process
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:8731-8746
Are Equivariant Equilibrium Approximators Beneficial?
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:8747-8778
Evaluating Self-Supervised Learning via Risk Decomposition
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:8779-8820
Fully Dynamic Submodular Maximization over Matroids
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:8821-8835
Optimal No-Regret Learning for One-Sided Lipschitz Functions
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:8836-8850
Integrating Prior Knowledge in Contrastive Learning with Kernel
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:8851-8878
Q-Flow: Generative Modeling for Differential Equations of Open Quantum Dynamics with Normalizing Flows
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:8879-8901
Adaptive Whitening in Neural Populations with Gain-modulating Interneurons
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:8902-8921
Generalization Bounds using Data-Dependent Fractal Dimensions
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:8922-8968
Multi-Objective Population Based Training
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:8969-8989
Neural Diffusion Processes
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:8990-9012
FAENet: Frame Averaging Equivariant GNN for Materials Modeling
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:9013-9033
Blackout Diffusion: Generative Diffusion Models in Discrete-State Spaces
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:9034-9059
The Computational Complexity of Concise Hypersphere Classification
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:9060-9070
E$(n)$ Equivariant Message Passing Simplicial Networks
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:9071-9081
Performative Recommendation: Diversifying Content via Strategic Incentives
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:9082-9103
Hyperparameters in Reinforcement Learning and How To Tune Them
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:9104-9149
Fairness in Streaming Submodular Maximization over a Matroid Constraint
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:9150-9171
Difference of submodular minimization via DC programming
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:9172-9201
Graph Positional Encoding via Random Feature Propagation
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:9202-9223
Improving Graph Neural Networks with Learnable Propagation Operators
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:9224-9245
Phase Transitions in the Detection of Correlated Databases
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:9246-9266
A new near-linear time algorithm for k-nearest neighbor search using a compressed cover tree
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:9267-9311
Motion Question Answering via Modular Motion Programs
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:9312-9328
Learning Perturbations to Explain Time Series Predictions
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:9329-9342
Regret Minimization and Convergence to Equilibria in General-sum Markov Games
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:9343-9373
Delayed Bandits: When Do Intermediate Observations Help?
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:9374-9395
Scaling Spherical CNNs
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:9396-9411
Stochastic Gradient Descent under Markovian Sampling Schemes
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:9412-9439
Continual Learning in Linear Classification on Separable Data
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:9440-9484
A Connection between One-Step RL and Critic Regularization in Reinforcement Learning
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:9485-9507
Neural Status Registers
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:9508-9522
Learning Rate Schedules in the Presence of Distribution Shift
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:9523-9546
Predicting Rare Events by Shrinking Towards Proportional Odds
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:9547-9602
Free-Form Variational Inference for Gaussian Process State-Space Models
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:9603-9622
Optimizing DDPM Sampling with Shortcut Fine-Tuning
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:9623-9639
LSDS++ : Dual Sampling for Accelerated k-means++
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:9640-9649
Smart Initial Basis Selection for Linear Programs
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:9650-9664
General Covariance Data Augmentation for Neural PDE Solvers
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:9665-9688
The Fast Johnson-Lindenstrauss Transform Is Even Faster
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:9689-9715
Regression with Label Permutation in Generalized Linear Model
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:9716-9760
Robust Collaborative Learning with Linear Gradient Overhead
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:9761-9813
Neural FIM for learning Fisher information metrics from point cloud data
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:9814-9826
Stochastic Policy Gradient Methods: Improved Sample Complexity for Fisher-non-degenerate Policies
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:9827-9869
Parallel Neurosymbolic Integration with Concordia
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:9870-9885
Why Target Networks Stabilise Temporal Difference Methods
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:9886-9909
Weighted Sampling without Replacement for Deep Top-$k$ Classification
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:9910-9920
Improved Online Learning Algorithms for CTR Prediction in Ad Auctions
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:9921-9937
Fractional Denoising for 3D Molecular Pre-training
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:9938-9961
Improved Algorithms for White-Box Adversarial Streams
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:9962-9975
Non-stationary Reinforcement Learning under General Function Approximation
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:9976-10007
Random Matrix Analysis to Balance between Supervised and Unsupervised Learning under the Low Density Separation Assumption
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:10008-10033
SurCo: Learning Linear SURrogates for COmbinatorial Nonlinear Optimization Problems
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:10034-10052
Scaling Laws for Multilingual Neural Machine Translation
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:10053-10071
Constant Matters: Fine-grained Error Bound on Differentially Private Continual Observation
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:10072-10092
Adapting to game trees in zero-sum imperfect information games
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:10093-10135
User-defined Event Sampling and Uncertainty Quantification in Diffusion Models for Physical Dynamical Systems
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:10136-10152
ACAT: Adversarial Counterfactual Attention for Classification and Detection in Medical Imaging
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:10153-10169
Explainable Data-Driven Optimization: From Context to Decision and Back Again
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:10170-10187
Hardness of Independent Learning and Sparse Equilibrium Computation in Markov Games
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:10188-10221
Disentangled Generative Models for Robust Prediction of System Dynamics
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:10222-10248
Can Forward Gradient Match Backpropagation?
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:10249-10264
Last Switch Dependent Bandits with Monotone Payoff Functions
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:10265-10284
A Theoretical Analysis of the Learning Dynamics under Class Imbalance
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:10285-10322
SparseGPT: Massive Language Models Can be Accurately Pruned in One-Shot
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:10323-10337
Learning Temporally AbstractWorld Models without Online Experimentation
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:10338-10356
A Coupled Flow Approach to Imitation Learning
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:10357-10372
Simple Hardware-Efficient Long Convolutions for Sequence Modeling
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:10373-10391
MonoNeRF: Learning Generalizable NeRFs from Monocular Videos without Camera Poses
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:10392-10404
Go Beyond Imagination: Maximizing Episodic Reachability with World Models
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:10405-10420
Specializing Smaller Language Models towards Multi-Step Reasoning
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:10421-10430
Accelerated Stochastic Optimization Methods under Quasar-convexity
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:10431-10460
Meta-learning Parameterized Skills
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:10461-10481
NeRFool: Uncovering the Vulnerability of Generalizable Neural Radiance Fields against Adversarial Perturbations
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:10482-10493
Hierarchies of Reward Machines
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:10494-10541
Why Random Pruning Is All We Need to Start Sparse
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:10542-10570
Cell-Free Latent Go-Explore
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:10571-10586
Graph Reinforcement Learning for Network Control via Bi-Level Optimization
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:10587-10610
Why Is Public Pretraining Necessary for Private Model Training?
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:10611-10627
Do Perceptually Aligned Gradients Imply Robustness?
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:10628-10648
Solving Linear Programs with Fast Online Learning Algorithms
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:10649-10675
Gradient Descent Finds the Global Optima of Two-Layer Physics-Informed Neural Networks
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:10676-10707
Generalizing Neural Wave Functions
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:10708-10726
On the Impact of Algorithmic Recourse on Social Segregation
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:10727-10743
DDGR: Continual Learning with Deep Diffusion-based Generative Replay
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:10744-10763
PAL: Program-aided Language Models
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:10764-10799
Out-of-Domain Robustness via Targeted Augmentations
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:10800-10834
Scaling Laws for Reward Model Overoptimization
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:10835-10866
The Unreasonable Effectiveness of Few-shot Learning for Machine Translation
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:10867-10878
RLSbench: Domain Adaptation Under Relaxed Label Shift
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:10879-10928
RankMe: Assessing the Downstream Performance of Pretrained Self-Supervised Representations by Their Rank
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:10929-10974
Self-supervised learning of Split Invariant Equivariant representations
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:10975-10996
Federated Heavy Hitter Recovery under Linear Sketching
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:10997-11012
On the Global Convergence of Fitted Q-Iteration with Two-layer Neural Network Parametrization
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:11013-11049
A Reinforcement Learning Framework for Dynamic Mediation Analysis
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:11050-11097
Compositional Score Modeling for Simulation-Based Inference
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:11098-11116
Cramming: Training a Language Model on a single GPU in one day.
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:11117-11143
Transformers Meet Directed Graphs
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:11144-11172
Memory-Based Meta-Learning on Non-Stationary Distributions
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:11173-11195
Towards Reliable Neural Specifications
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:11196-11212
Oracles & Followers: Stackelberg Equilibria in Deep Multi-Agent Reinforcement Learning
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:11213-11236
Approximately Optimal Core Shapes for Tensor Decompositions
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:11237-11254
GAT: Guided Adversarial Training with Pareto-optimal Auxiliary Tasks
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:11255-11282
On User-Level Private Convex Optimization
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:11283-11299
Contextual Reliability: When Different Features Matter in Different Contexts
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:11300-11320
Reinforcement Learning from Passive Data via Latent Intentions
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:11321-11339
Harmonic Neural Networks
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:11340-11359
Dividing and Conquering a BlackBox to a Mixture of Interpretable Models: Route, Interpret, Repeat
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:11360-11397
Looped Transformers as Programmable Computers
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:11398-11442
Generalized Disparate Impact for Configurable Fairness Solutions in ML
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:11443-11458
Multicalibration as Boosting for Regression
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:11459-11492
Adversarial robustness of amortized Bayesian inference
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:11493-11524
Efficient RL via Disentangled Environment and Agent Representations
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:11525-11545
Aligning Language Models with Preferences through $f$-divergence Minimization
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:11546-11583
Robust Consensus in Ranking Data Analysis: Definitions, Properties and Computational Issues
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:11584-11597
Learning Distributions over Quantum Measurement Outcomes
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:11598-11613
Convergence of Proximal Point and Extragradient-Based Methods Beyond Monotonicity: the Case of Negative Comonotonicity
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:11614-11641
Adaptive Annealed Importance Sampling with Constant Rate Progress
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:11642-11658
Formalizing Preferences Over Runtime Distributions
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:11659-11682
Topological Point Cloud Clustering
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:11683-11697
On Sampling with Approximate Transport Maps
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:11698-11733
Hidden Symmetries of ReLU Networks
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:11734-11760
EF21-P and Friends: Improved Theoretical Communication Complexity for Distributed Optimization with Bidirectional Compression
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:11761-11807
NerfDiff: Single-image View Synthesis with NeRF-guided Distillation from 3D-aware Diffusion
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:11808-11826
DecompDiff: Diffusion Models with Decomposed Priors for Structure-Based Drug Design
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:11827-11846
On Excess Mass Behavior in Gaussian Mixture Models with Orlicz-Wasserstein Distances
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:11847-11870
Conformalization of Sparse Generalized Linear Models
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:11871-11887
Privacy-Aware Compression for Federated Learning Through Numerical Mechanism Design
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:11888-11904
Out-of-Distribution Generalization of Federated Learning via Implicit Invariant Relationships
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:11905-11933
FeDXL: Provable Federated Learning for Deep X-Risk Optimization
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:11934-11966
Provably Efficient Representation Learning with Tractable Planning in Low-Rank POMDP
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:11967-11997
Analyzing Privacy Leakage in Machine Learning via Multiple Hypothesis Testing: A Lesson From Fano
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:11998-12011
Linkless Link Prediction via Relational Distillation
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:12012-12033
FedBR: Improving Federated Learning on Heterogeneous Data via Local Learning Bias Reduction
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:12034-12054
Hierarchical Grammar-Induced Geometry for Data-Efficient Molecular Property Prediction
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:12055-12076
Graph Neural Networks with Learnable and Optimal Polynomial Bases
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:12077-12097
LongCoder: A Long-Range Pre-trained Language Model for Code Completion
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:12098-12107
Estimating Heterogeneous Treatment Effects: Mutual Information Bounds and Learning Algorithms
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:12108-12121
Identifying Useful Learnwares for Heterogeneous Label Spaces
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:12122-12131
High-dimensional Location Estimation via Norm Concentration for Subgamma Vectors
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:12132-12164
GRAFENNE: Learning on Graphs with Heterogeneous and Dynamic Feature Sets
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:12165-12181
Online Platt Scaling with Calibeating
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:12182-12204
Multi-Task Structural Learning using Local Task Similarity induced Neuron Creation and Removal
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:12205-12223
Conditionally Strongly Log-Concave Generative Models
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:12224-12251
DRew: Dynamically Rewired Message Passing with Delay
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:12252-12267
Kernel Logistic Regression Approximation of an Understandable ReLU Neural Network
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:12268-12291
Conformal Prediction Sets for Graph Neural Networks
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:12292-12318
Social learning spontaneously emerges by searching optimal heuristics with deep reinforcement learning
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:12319-12338
Convex Geometry of ReLU-layers, Injectivity on the Ball and Local Reconstruction
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:12339-12350
Robust Counterfactual Explanations for Neural Networks With Probabilistic Guarantees
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:12351-12367
Wrapped Cauchy Distributed Angular Softmax for Long-Tailed Visual Recognition
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:12368-12388
On the Impact of Knowledge Distillation for Model Interpretability
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:12389-12410
Alternately Optimized Graph Neural Networks
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:12411-12429
System Identification of Neural Systems: If We Got It Right, Would We Know?
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:12430-12444
Total Variation Graph Neural Networks
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:12445-12468
Learning Physical Models that Can Respect Conservation Laws
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:12469-12510
On Pre-Training for Visuo-Motor Control: Revisiting a Learning-from-Scratch Baseline
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:12511-12526
Leveraging Demonstrations to Improve Online Learning: Quality Matters
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:12527-12545
Coupled Variational Autoencoder
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:12546-12555
GNOT: A General Neural Operator Transformer for Operator Learning
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:12556-12569
Algorithmic Collective Action in Machine Learning
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:12570-12586
Gaussian Process Priors for Systems of Linear Partial Differential Equations with Constant Coefficients
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:12587-12615
Theoretical Guarantees of Learning Ensembling Strategies with Applications to Time Series Forecasting
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:12616-12632
Global Context Vision Transformers
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:12633-12646
Counterfactual Analysis in Dynamic Latent State Models
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:12647-12677
Sampling-based Nyström Approximation and Kernel Quadrature
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:12678-12699
Width and Depth Limits Commute in Residual Networks
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:12700-12723
A Generalization of ViT/MLP-Mixer to Graphs
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:12724-12745
Domain Adaptation for Time Series Under Feature and Label Shifts
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:12746-12774
Contrastive Learning Meets Homophily: Two Birds with One Stone
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:12775-12789
Nearly Minimax Optimal Reinforcement Learning for Linear Markov Decision Processes
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:12790-12822
CRISP: Curriculum based Sequential neural decoders for Polar code family
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:12823-12845
Sketch-Flip-Merge: Mergeable Sketches for Private Distinct Counting
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:12846-12865
Functional Neural Networks: Shift invariant models for functional data with applications to EEG classification
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:12866-12881
Distance Weighted Supervised Learning for Offline Interaction Data
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:12882-12906
Group Equivariant Fourier Neural Operators for Partial Differential Equations
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:12907-12930
Training-Free Neural Active Learning with Initialization-Robustness Guarantees
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:12931-12971
A Study of Global and Episodic Bonuses for Exploration in Contextual MDPs
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:12972-12999
Robust Camera Pose Refinement for Multi-Resolution Hash Encoding
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:13000-13016
Generalized Teacher Forcing for Learning Chaotic Dynamics
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:13017-13049
Causal Modeling of Policy Interventions From Treatment-Outcome Sequences
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:13050-13084
Monotonicity and Double Descent in Uncertainty Estimation with Gaussian Processes
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:13085-13117
AdaBoost is not an Optimal Weak to Strong Learner
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:13118-13140
Dual Propagation: Accelerating Contrastive Hebbian Learning with Dyadic Neurons
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:13141-13156
Multi-Task Off-Policy Learning from Bandit Feedback
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:13157-13173
Constrained Optimization via Exact Augmented Lagrangian and Randomized Iterative Sketching
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:13174-13198
Revisiting Data-Free Knowledge Distillation with Poisoned Teachers
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:13199-13212
simple diffusion: End-to-end diffusion for high resolution images
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:13213-13232
Causal Strategic Classification: A Tale of Two Shifts
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:13233-13253
Fair and Accurate Decision Making through Group-Aware Learning
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:13254-13269
Approximation Algorithms for Fair Range Clustering
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:13270-13284
Decoding Layer Saliency in Language Transformers
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:13285-13308
PromptBoosting: Black-Box Text Classification with Ten Forward Passes
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:13309-13324
Sparse Learning of Dynamical Systems in RKHS: An Operator-Theoretic Approach
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:13325-13352
Probably Anytime-Safe Stochastic Combinatorial Semi-Bandits
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:13353-13409
Automatic Data Augmentation via Invariance-Constrained Learning
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:13410-13433
Thompson Sampling with Diffusion Generative Prior
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:13434-13468
Tighter Analysis for ProxSkip
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:13469-13496
Omnipredictors for Constrained Optimization
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:13497-13527
GFlowNet-EM for Learning Compositional Latent Variable Models
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:13528-13549
Blockwise Stochastic Variance-Reduced Methods with Parallel Speedup for Multi-Block Bilevel Optimization
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:13550-13583
Language Instructed Reinforcement Learning for Human-AI Coordination
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:13584-13598
Surface Snapping Optimization Layer for Single Image Object Shape Reconstruction
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:13599-13609
Learning to Learn from APIs: Black-Box Data-Free Meta-Learning
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:13610-13627
For Pre-Trained Vision Models in Motor Control, Not All Policy Learning Methods are Created Equal
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:13628-13651
Beyond Lipschitz Smoothness: A Tighter Analysis for Nonconvex Optimization
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:13652-13678
Understanding the Impact of Adversarial Robustness on Accuracy Disparity
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:13679-13709
Reinforcement Learning in Low-rank MDPs with Density Features
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:13710-13752
Composer: Creative and Controllable Image Synthesis with Composable Conditions
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:13753-13773
Model-Aware Contrastive Learning: Towards Escaping the Dilemmas
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:13774-13790
High-dimensional Clustering onto Hamiltonian Cycle
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:13791-13813
Banker Online Mirror Descent: A Universal Approach for Delayed Online Bandit Learning
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:13814-13844
Fast Algorithms for Distributed k-Clustering with Outliers
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:13845-13868
Searching Large Neighborhoods for Integer Linear Programs with Contrastive Learning
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:13869-13890
On Coresets for Clustering in Small Dimensional Euclidean spaces
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:13891-13915
Make-An-Audio: Text-To-Audio Generation with Prompt-Enhanced Diffusion Models
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:13916-13932
The Power of Uniform Sampling for k-Median
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:13933-13956
Reparameterized Policy Learning for Multimodal Trajectory Optimization
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:13957-13975
Theoretical Bounds on the Network Community Profile from Low-rank Semi-definite Programming
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:13976-13992
NeuralStagger: Accelerating Physics-constrained Neural PDE Solver with Spatial-temporal Decomposition
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:13993-14006
Policy Contrastive Imitation Learning
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:14007-14022
Are Large Kernels Better Teachers than Transformers for ConvNets?
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:14023-14038
Achieving Linear Speedup in Non-IID Federated Bilevel Learning
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:14039-14059
Federated Linear Contextual Bandits with User-level Differential Privacy
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:14060-14095
Straightening Out the Straight-Through Estimator: Overcoming Optimization Challenges in Vector Quantized Networks
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:14096-14113
Cut your Losses with Squentropy
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:14114-14131
SOM-CPC: Unsupervised Contrastive Learning with Self-Organizing Maps for Structured Representations of High-Rate Time Series
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:14132-14152
One-Shot Federated Conformal Prediction
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:14153-14177
The Impact of Exploration on Convergence and Performance of Multi-Agent Q-Learning Dynamics
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:14178-14202
Combinatorial Neural Bandits
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:14203-14236
MAGANet: Achieving Combinatorial Generalization by Modeling a Group Action
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:14237-14248
Information-Theoretic State Space Model for Multi-View Reinforcement Learning
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:14249-14282
Under-Counted Tensor Completion with Neural Incorporation of Attributes
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:14283-14315
On the Identifiability and Estimation of Causal Location-Scale Noise Models
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:14316-14332
Stochastic Marginal Likelihood Gradients using Neural Tangent Kernels
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:14333-14352
Differentially Private Hierarchical Clustering with Provable Approximation Guarantees
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:14353-14375
Neural Network Accelerated Implicit Filtering: Integrating Neural Network Surrogates With Provably Convergent Derivative Free Optimization Methods
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:14376-14389
Principled Offline RL in the Presence of Rich Exogenous Information
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:14390-14421
Unveiling the Latent Space Geometry of Push-Forward Generative Models
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:14422-14444
CO-BED: Information-Theoretic Contextual Optimization via Bayesian Experimental Design
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:14445-14464
DoG is SGD’s Best Friend: A Parameter-Free Dynamic Step Size Schedule
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:14465-14499
Maximal Initial Learning Rates in Deep ReLU Networks
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:14500-14530
Data-Driven Subgroup Identification for Linear Regression
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:14531-14552
Efficient Training of Language Models using Few-Shot Learning
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:14553-14568
Scalable Adaptive Computation for Iterative Generation
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:14569-14589
Unconstrained Online Learning with Unbounded Losses
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:14590-14630
Multi-Objective GFlowNets
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:14631-14653
The Price of Differential Privacy under Continual Observation
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:14654-14678
Graph Ladling: Shockingly Simple Parallel GNN Training without Intermediate Communication
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:14679-14690
Instant Soup: Cheap Pruning Ensembles in A Single Pass Can Draw Lottery Tickets from Large Models
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:14691-14701
Exploring the Benefits of Training Expert Language Models over Instruction Tuning
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:14702-14729
Learning to Boost Training by Periodic Nowcasting Near Future Weights
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:14730-14757
Unscented Autoencoder
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:14758-14779
Curiosity in Hindsight: Intrinsic Exploration in Stochastic Environments
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:14780-14816
BiRT: Bio-inspired Replay in Vision Transformers for Continual Learning
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:14817-14835
Recovering Top-Two Answers and Confusion Probability in Multi-Choice Crowdsourcing
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:14836-14868
Leveraging Label Non-Uniformity for Node Classification in Graph Neural Networks
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:14869-14885
Bidirectional Adaptation for Robust Semi-Supervised Learning with Inconsistent Data Distributions
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:14886-14901
Short-lived High-volume Bandits
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:14902-14929
Smooth Non-stationary Bandits
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:14930-14944
A Unified Optimization Framework of ANN-SNN Conversion: Towards Optimal Mapping from Activation Values to Firing Rates
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:14945-14974
VIMA: Robot Manipulation with Multimodal Prompts
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:14975-15022
Estimating Causal Effects using a Multi-task Deep Ensemble
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:15023-15040
Online Restless Bandits with Unobserved States
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:15041-15066
Detecting Out-of-distribution Data through In-distribution Class Prior
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:15067-15088
Towards Stable and Efficient Adversarial Training against $l_1$ Bounded Adversarial Attacks
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:15089-15104
Learning Unnormalized Statistical Models via Compositional Optimization
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:15105-15124
Approximate Causal Effect Identification under Weak Confounding
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:15125-15143
MEWL: Few-shot multimodal word learning with referential uncertainty
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:15144-15169
NeuralSlice: Neural 3D Triangle Mesh Reconstruction via Slicing 4D Tetrahedral Meshes
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:15170-15185
Effective Structured Prompting by Meta-Learning and Representative Verbalizer
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:15186-15199
Understanding Incremental Learning of Gradient Descent: A Fine-grained Analysis of Matrix Sensing
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:15200-15238
Thompson Sampling with Less Exploration is Fast and Optimal
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:15239-15261
R-U-SURE? Uncertainty-Aware Code Suggestions By Maximizing Utility Across Random User Intents
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:15262-15306
Automatically Auditing Large Language Models via Discrete Optimization
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:15307-15329
On the Expressive Power of Geometric Graph Neural Networks
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:15330-15355
Data-Efficient Contrastive Self-supervised Learning: Most Beneficial Examples for Supervised Learning Contribute the Least
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:15356-15370
Robust Subtask Learning for Compositional Generalization
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:15371-15387
On Bridging the Gap between Mean Field and Finite Width Deep Random Multilayer Perceptron with Batch Normalization
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:15388-15400
FARE: Provably Fair Representation Learning with Practical Certificates
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:15401-15420
Scaling of Class-wise Training Losses for Post-hoc Calibration
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:15421-15434
Fighting Fire with Fire: Contrastive Debiasing without Bias-free Data via Generative Bias-transformation
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:15435-15450
Estimating Joint Treatment Effects by Combining Multiple Experiments
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:15451-15527
The Catalog Problem: Clustering and Ordering Variable-Sized Sets
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:15528-15545
Equivariance with Learned Canonicalization Functions
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:15546-15566
Biases in Evaluation of Molecular Optimization Methods and Bias Reduction Strategies
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:15567-15585
Statistical Indistinguishability of Learning Algorithms
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:15586-15622
Identifying Interpretable Subspaces in Image Representations
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:15623-15638
Nonlinear Causal Discovery with Latent Confounders
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:15639-15654
Deep Generative Symbolic Regression with Monte-Carlo-Tree-Search
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:15655-15668
One-vs-the-Rest Loss to Focus on Important Samples in Adversarial Training
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:15669-15695
Large Language Models Struggle to Learn Long-Tail Knowledge
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:15696-15707
Git-Theta: A Git Extension for Collaborative Development of Machine Learning Models
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:15708-15719
A Deep Conjugate Direction Method for Iteratively Solving Linear Systems
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:15720-15736
Leveraging Proxy of Training Data for Test-Time Adaptation
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:15737-15752
Beyond Reward: Offline Preference-guided Policy Optimization
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:15753-15768
Poisoning Generative Replay in Continual Learning to Promote Forgetting
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:15769-15785
Node Embedding from Neural Hamiltonian Orbits in Graph Neural Networks
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:15786-15808
Understanding Gradient Regularization in Deep Learning: Efficient Finite-Difference Computation and Implicit Bias
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:15809-15827
Langevin Thompson Sampling with Logarithmic Communication: Bandits and Reinforcement Learning
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:15828-15860
On the Relationship Between Explanation and Prediction: A Causal View
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:15861-15883
Cocktail Party Attack: Breaking Aggregation-Based Privacy in Federated Learning Using Independent Component Analysis
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:15884-15899
General Sequential Episodic Memory Model
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:15900-15910
Regression with Sensor Data Containing Incomplete Observations
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:15911-15927
Data Representations’ Study of Latent Image Manifolds
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:15928-15945
Multi-Modal Classifiers for Open-Vocabulary Object Detection
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:15946-15969
Learning Mixtures of Markov Chains and MDPs
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:15970-16017
Curious Replay for Model-based Adaptation
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:16018-16048
How Does Information Bottleneck Help Deep Learning?
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:16049-16096
Instrumental Variable Estimation of Average Partial Causal Effects
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:16097-16130
The Test of Tests: A Framework for Differentially Private Hypothesis Testing
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:16131-16151
Exact Inference in High-order Structured Prediction
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:16152-16167
Neural Wave Machines: Learning Spatiotemporally Structured Representations with Locally Coupled Oscillatory Recurrent Neural Networks
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:16168-16189
Homomorphism AutoEncoder -- Learning Group Structured Representations from Observed Transitions
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:16190-16215
Rethinking Backdoor Attacks
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:16216-16236
PAC Prediction Sets for Large Language Models of Code
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:16237-16249
Accelerated Primal-Dual Methods for Convex-Strongly-Concave Saddle Point Problems
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:16250-16270
Loss Balancing for Fair Supervised Learning
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:16271-16290
Linearly Constrained Bilevel Optimization: A Smoothed Implicit Gradient Approach
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:16291-16325
Emergent Asymmetry of Precision and Recall for Measuring Fidelity and Diversity of Generative Models in High Dimensions
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:16326-16343
Learning-augmented private algorithms for multiple quantile release
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:16344-16376
CrossSplit: Mitigating Label Noise Memorization through Data Splitting
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:16377-16392
Trainability, Expressivity and Interpretability in Gated Neural ODEs
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:16393-16423
SAAL: Sharpness-Aware Active Learning
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:16424-16440
Demonstration-free Autonomous Reinforcement Learning via Implicit and Bidirectional Curriculum
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:16441-16457
Improved Algorithms for Multi-period Multi-class Packing Problems with Bandit Feedback
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:16458-16501
Efficient Latency-Aware CNN Depth Compression via Two-Stage Dynamic Programming
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:16502-16520
Probabilistic Concept Bottleneck Models
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:16521-16540
DevFormer: A Symmetric Transformer for Context-Aware Device Placement
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:16541-16566
Refining Generative Process with Discriminator Guidance in Score-based Diffusion Models
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:16567-16598
Robust Non-Linear Feedback Coding via Power-Constrained Deep Learning
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:16599-16618
LESSON: Learning to Integrate Exploration Strategies for Reinforcement Learning via an Option Framework
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:16619-16638
BPipe: Memory-Balanced Pipeline Parallelism for Training Large Language Models
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:16639-16653
Probabilistic Imputation for Time-series Classification with Missing Data
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:16654-16667
Variational Curriculum Reinforcement Learning for Unsupervised Discovery of Skills
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:16668-16695
Margin-based Neural Network Watermarking
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:16696-16711
Regularizing Towards Soft Equivariance Under Mixed Symmetries
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:16712-16727
Model-based Offline Reinforcement Learning with Count-based Conservatism
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:16728-16746
Transformer-based Stagewise Decomposition for Large-Scale Multistage Stochastic Optimization
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:16747-16770
SurProGenes: Survival Risk-Ordered Representation of Cancer Patients and Genes for the Identification of Prognostic Genes
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:16771-16786
Stable and Consistent Prediction of 3D Characteristic Orientation via Invariant Residual Learning
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:16787-16806
Prefer to Classify: Improving Text Classifiers via Auxiliary Preference Learning
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:16807-16828
An Adaptive Entropy-Regularization Framework for Multi-Agent Reinforcement Learning
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:16829-16852
Practical and Matching Gradient Variance Bounds for Black-Box Variational Bayesian Inference
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:16853-16876
Learnability and Algorithm for Continual Learning
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:16877-16896
Unifying Nesterov’s Accelerated Gradient Methods for Convex and Strongly Convex Objective Functions
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:16897-16954
Denoising MCMC for Accelerating Diffusion-Based Generative Models
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:16955-16977
Structure Learning of Latent Factors via Clique Search on Correlation Thresholded Graphs
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:16978-16996
Fair and Robust Estimation of Heterogeneous Treatment Effects for Policy Learning
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:16997-17014
Proper Losses for Discrete Generative Models
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:17015-17040
Controlling Posterior Collapse by an Inverse Lipschitz Constraint on the Decoder Network
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:17041-17060
A Watermark for Large Language Models
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:17061-17084
Probabilistic Contrastive Learning Recovers the Correct Aleatoric Uncertainty of Ambiguous Inputs
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:17085-17104
Training Normalizing Flows from Dependent Data
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:17105-17121
IncDSI: Incrementally Updatable Document Retrieval
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:17122-17134
Regularization and Variance-Weighted Regression Achieves Minimax Optimality in Linear MDPs: Theory and Practice
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:17135-17175
Drug Discovery under Covariate Shift with Domain-Informed Prior Distributions over Functions
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:17176-17197
Deep Laplacian-based Options for Temporally-Extended Exploration
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:17198-17217
Generalized Reductions: Making any Hierarchical Clustering Fair and Balanced with Low Cost
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:17218-17242
Can We Scale Transformers to Predict Parameters of Diverse ImageNet Models?
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:17243-17259
Online Learning with Feedback Graphs: The True Shape of Regret
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:17260-17282
Grounding Language Models to Images for Multimodal Inputs and Outputs
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:17283-17300
Rigid Body Flows for Sampling Molecular Crystal Structures
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:17301-17326
Enabling First-Order Gradient-Based Learning for Equilibrium Computation in Markets
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:17327-17342
Revisiting Gradient Clipping: Stochastic bias and tight convergence guarantees
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:17343-17363
On Computing Optimal Tree Ensembles
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:17364-17374
GOAT: A Global Transformer on Large-scale Graphs
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:17375-17390
Autoregressive Diffusion Model for Graph Generation
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:17391-17408
End-to-End Full-Atom Antibody Design
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:17409-17429
Covariate balancing using the integral probability metric for causal inference
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:17430-17461
Masked Bayesian Neural Networks : Theoretical Guarantee and its Posterior Inference
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:17462-17491
Parameter-Level Soft-Masking for Continual Learning
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:17492-17505
Pretraining Language Models with Human Preferences
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:17506-17533
Detecting Adversarial Directions in Deep Reinforcement Learning to Make Robust Decisions
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:17534-17543
Ewald-based Long-Range Message Passing for Molecular Graphs
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:17544-17563
TabDDPM: Modelling Tabular Data with Diffusion Models
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:17564-17579
Randomized Schur Complement Views for Graph Contrastive Learning
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:17580-17614
Benign Overfitting in Two-layer ReLU Convolutional Neural Networks
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:17615-17659
Variational Mixture of HyperGenerators for Learning Distributions over Functions
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:17660-17683
Gradient Descent Monotonically Decreases the Sharpness of Gradient Flow Solutions in Scalar Networks and Beyond
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:17684-17744
Estimation Beyond Data Reweighting: Kernel Method of Moments
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:17745-17783
Multi-Task Differential Privacy Under Distribution Skew
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:17784-17807
Towards Bridging the Gaps between the Right to Explanation and the Right to be Forgotten
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:17808-17826
Graph Neural Tangent Kernel: Convergence on Large Graphs
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:17827-17841
Diffusion Models for Black-Box Optimization
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:17842-17857
Learning to Design Analog Circuits to Meet Threshold Specifications
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:17858-17873
Variance Control for Distributional Reinforcement Learning
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:17874-17895
Hierarchical Imitation Learning with Vector Quantized Models
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:17896-17919
SinDDM: A Single Image Denoising Diffusion Model
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:17920-17930
Towards Explaining Distribution Shifts
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:17931-17952
Featured Graph Coarsening with Similarity Guarantees
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:17953-17975
Modeling Dynamic Environments with Scene Graph Memory
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:17976-17993
Tied-Augment: Controlling Representation Similarity Improves Data Augmentation
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:17994-18007
Cooperation in the Latent Space: The Benefits of Adding Mixture Components in Variational Autoencoders
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:18008-18022
GeCoNeRF: Few-shot Neural Radiance Fields via Geometric Consistency
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:18023-18036
Rotation and Translation Invariant Representation Learning with Implicit Neural Representations
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:18037-18056
Reward-Mixing MDPs with Few Latent Contexts are Learnable
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:18057-18082
A Fully First-Order Method for Stochastic Bilevel Optimization
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:18083-18113
Complexity of Block Coordinate Descent with Proximal Regularization and Applications to Wasserstein CP-dictionary Learning
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:18114-18134
Data-OOB: Out-of-bag Estimate as a Simple and Efficient Data Value
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:18135-18152
Emergence of Adaptive Circadian Rhythms in Deep Reinforcement Learning
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:18153-18170
Synergies between Disentanglement and Sparsity: Generalization and Identifiability in Multi-Task Learning
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:18171-18206
Nearly-Optimal Hierarchical Clustering for Well-Clustered Graphs
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:18207-18249
Hybrid Energy Based Model in the Feature Space for Out-of-Distribution Detection
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:18250-18268
A theory of continuous generative flow networks
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:18269-18300
Automatically marginalized MCMC in probabilistic programming
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:18301-18318
DS-1000: A Natural and Reliable Benchmark for Data Science Code Generation
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:18319-18345
ChiPFormer: Transferable Chip Placement via Offline Decision Transformer
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:18346-18364
FP-Diffusion: Improving Score-based Diffusion Models by Enforcing the Underlying Score Fokker-Planck Equation
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:18365-18398
Private Statistical Estimation of Many Quantiles
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:18399-18418
Bootstrap in High Dimension with Low Computation
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:18419-18453
LegendreTron: Uprising Proper Multiclass Loss Learning
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:18454-18470
Metagenomic Binning using Connectivity-constrained Variational Autoencoders
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:18471-18481
Delay-Adapted Policy Optimization and Improved Regret for Adversarial MDP with Delayed Bandit Feedback
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:18482-18534
Lottery Tickets in Evolutionary Optimization: On Sparse Backpropagation-Free Trainability
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:18535-18547
On the Occupancy Measure of Non-Markovian Policies in Continuous MDPs
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:18548-18562
Minimalistic Predictions to Schedule Jobs with Online Precedence Constraints
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:18563-18583
Speeding Up Bellman Ford via Minimum Violation Permutations
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:18584-18598
Who Needs to Know? Minimal Knowledge for Optimal Coordination
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:18599-18613
Target-based Surrogates for Stochastic Optimization
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:18614-18651
Cluster Explanation via Polyhedral Descriptions
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:18652-18666
Pre-training for Speech Translation: CTC Meets Optimal Transport
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:18667-18685
Bootstrapped Representations in Reinforcement Learning
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:18686-18713
Strategic Classification with Unknown User Manipulations
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:18714-18732
Learning in POMDPs is Sample-Efficient with Hindsight Observability
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:18733-18773
Towards Deep Attention in Graph Neural Networks: Problems and Remedies
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:18774-18795
InGram: Inductive Knowledge Graph Embedding via Relation Graphs
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:18796-18809
Optimality of Thompson Sampling with Noninformative Priors for Pareto Bandits
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:18810-18851
Conditional Graph Information Bottleneck for Molecular Relational Learning
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:18852-18871
Exploring Chemical Space with Score-based Out-of-distribution Generation
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:18872-18892
Pix2Struct: Screenshot Parsing as Pretraining for Visual Language Understanding
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:18893-18912
FlexRound: Learnable Rounding based on Element-wise Division for Post-Training Quantization
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:18913-18939
CoDi: Co-evolving Contrastive Diffusion Models for Mixed-type Tabular Synthesis
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:18940-18956
Minimizing Trajectory Curvature of ODE-based Generative Models
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:18957-18973
H-Likelihood Approach to Deep Neural Networks with Temporal-Spatial Random Effects for High-Cardinality Categorical Features
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:18974-18987
On the Importance of Feature Decorrelation for Unsupervised Representation Learning in Reinforcement Learning
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:18988-19009
HETAL: Efficient Privacy-preserving Transfer Learning with Homomorphic Encryption
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:19010-19035
QASA: Advanced Question Answering on Scientific Articles
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:19036-19052
Demystifying Disagreement-on-the-Line in High Dimensions
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:19053-19093
On the Correctness of Automatic Differentiation for Neural Networks with Machine-Representable Parameters
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:19094-19140
Implicit Jacobian regularization weighted with impurity of probability output
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:19141-19184
Unsupervised Skill Discovery for Learning Shared Structures across Changing Environments
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:19185-19199
Generalization Analysis for Contrastive Representation Learning
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:19200-19227
Learning Control by Iterative Inversion
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:19228-19255
Sampling-Based Accuracy Testing of Posterior Estimators for General Inference
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:19256-19273
Fast Inference from Transformers via Speculative Decoding
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:19274-19286
Efficient Rate Optimal Regret for Adversarial Contextual MDPs Using Online Function Approximation
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:19287-19314
GLOBE-CE: A Translation Based Approach for Global Counterfactual Explanations
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:19315-19342
TIPS: Topologically Important Path Sampling for Anytime Neural Networks
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:19343-19359
MAHALO: Unifying Offline Reinforcement Learning and Imitation Learning from Observations
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:19360-19384
Internet Explorer: Targeted Representation Learning on the Open Web
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:19385-19406
Prototype-oriented unsupervised anomaly detection for multivariate time series
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:19407-19424
Learning Preconditioners for Conjugate Gradient PDE Solvers
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:19425-19439
Parallel $Q$-Learning: Scaling Off-policy Reinforcement Learning under Massively Parallel Simulation
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:19440-19459
Minimum Width of Leaky-ReLU Neural Networks for Uniform Universal Approximation
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:19460-19470
FAIRER: Fairness as Decision Rationale Alignment
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:19471-19489
RACE: Improve Multi-Agent Reinforcement Learning with Representation Asymmetry and Collaborative Evolution
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:19490-19503
Adversarial Collaborative Learning on Non-IID Features
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:19504-19526
Near-optimal Conservative Exploration in Reinforcement Learning under Episode-wise Constraints
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:19527-19564
Transformers as Algorithms: Generalization and Stability in In-context Learning
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:19565-19594
Improving Hyperparameter Learning under Approximate Inference in Gaussian Process Models
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:19595-19615
Local Vertex Colouring Graph Neural Networks
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:19616-19637
Analysis of Error Feedback in Federated Non-Convex Optimization with Biased Compression: Fast Convergence and Partial Participation
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:19638-19688
How Do Transformers Learn Topic Structure: Towards a Mechanistic Understanding
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:19689-19729
BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:19730-19742
Nearly Optimal Algorithms with Sublinear Computational Complexity for Online Kernel Regression
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:19743-19766
Revisiting Weighted Aggregation in Federated Learning with Neural Networks
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:19767-19788
Distribution-dependent McDiarmid-type Inequalities for Functions of Unbounded Interaction
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:19789-19810
Optimal Convergence Rates for Agnostic Nyström Kernel Learning
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:19811-19836
Reconstructive Neuron Pruning for Backdoor Defense
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:19837-19854
Meta Learning of Interface Conditions for Multi-Domain Physics-Informed Neural Networks
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:19855-19881
Deep Anomaly Detection under Labeling Budget Constraints
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:19882-19910
On the Initialization of Graph Neural Networks
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:19911-19931
Federated Adversarial Learning: A Framework with Convergence Analysis
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:19932-19959
How Powerful are Shallow Neural Networks with Bandlimited Random Weights?
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:19960-19981
Efficient Quantum Algorithms for Quantum Optimal Control
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:19982-19994
Low-Switching Policy Gradient with Exploration via Online Sensitivity Sampling
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:19995-20034
Hierarchical Diffusion for Offline Decision Making
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:20035-20064
Divide and Conquer Dynamic Programming: An Almost Linear Time Change Point Detection Methodology in High Dimensions
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:20065-20148
Architecture-Agnostic Masked Image Modeling -- From ViT back to CNN
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:20149-20167
Learning Antidote Data to Individual Unfairness
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:20168-20181
Propensity Matters: Measuring and Enhancing Balancing for Recommendation
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:20182-20194
GraphCleaner: Detecting Mislabelled Samples in Popular Graph Learning Benchmarks
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:20195-20209
SMURF-THP: Score Matching-based UnceRtainty quantiFication for Transformer Hawkes Process
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:20210-20220
Horizon-free Learning for Markov Decision Processes and Games: Stochastically Bounded Rewards and Improved Bounds
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:20221-20252
Transcendental Idealism of Planner: Evaluating Perception from Planning Perspective for Autonomous Driving
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:20253-20275
Learning for Edge-Weighted Online Bipartite Matching with Robustness Guarantees
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:20276-20295
FedVS: Straggler-Resilient and Privacy-Preserving Vertical Federated Learning for Split Models
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:20296-20311
Achieving Hierarchy-Free Approximation for Bilevel Programs with Equilibrium Constraints
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:20312-20335
LoSparse: Structured Compression of Large Language Models based on Low-Rank and Sparse Approximation
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:20336-20350
Nesterov Meets Optimism: Rate-Optimal Separable Minimax Optimization
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:20351-20383
Alternating Local Enumeration (TnALE): Solving Tensor Network Structure Search with Fewer Evaluations
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:20384-20411
Understanding the Complexity Gains of Single-Task RL with a Curriculum
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:20412-20451
Does a Neural Network Really Encode Symbolic Concepts?
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:20452-20469
Cooperative Open-ended Learning Framework for Zero-Shot Coordination
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:20470-20484
Offline Reinforcement Learning with Closed-Form Policy Improvement Operators
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:20485-20528
Optimal Arms Identification with Knapsacks
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:20529-20555
Internally Rewarded Reinforcement Learning
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:20556-20574
Trustworthy Policy Learning under the Counterfactual No-Harm Criterion
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:20575-20598
Structured Cooperative Learning with Graphical Model Priors
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:20599-20622
Low Complexity Homeomorphic Projection to Ensure Neural-Network Solution Feasibility for Optimization over (Non-)Convex Set
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:20623-20649
Consistency of Multiple Kernel Clustering
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:20650-20676
A Distribution Optimization Framework for Confidence Bounds of Risk Measures
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:20677-20705
Accuracy on the Curve: On the Nonlinear Correlation of ML Performance Between Data Subpopulations
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:20706-20724
AdaptDiffuser: Diffusion Models as Adaptive Self-evolving Planners
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:20725-20745
Learning Compiler Pass Orders using Coreset and Normalized Value Prediction
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:20746-20762
Adversarial Example Does Good: Preventing Painting Imitation from Diffusion Models via Adversarial Examples
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:20763-20786
CLUSTSEG: Clustering for Universal Segmentation
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:20787-20809
Conformal Inference is (almost) Free for Neural Networks Trained with Early Stopping
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:20810-20851
Less is More: Task-aware Layer-wise Distillation for Language Model Compression
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:20852-20867
Statistical Inference and A/B Testing for First-Price Pacing Equilibria
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:20868-20905
Supervised Metric Learning to Rank for Retrieval via Contextual Similarity Optimization
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:20906-20938
Revisiting Domain Randomization via Relaxed State-Adversarial Policy Optimization
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:20939-20949
Variational Open-Domain Question Answering
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:20950-20977
Generating Novel, Designable, and Diverse Protein Structures by Equivariantly Diffusing Oriented Residue Clouds
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:20978-21002
Hyperbolic Diffusion Embedding and Distance for Hierarchical Representation Learning
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:21003-21025
Simplifying Momentum-based Positive-definite Submanifold Optimization with Applications to Deep Learning
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:21026-21050
Text Generation with Diffusion Language Models: A Pre-training Approach with Continuous Paragraph Denoise
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:21051-21064
Self-supervised Neural Factor Analysis for Disentangling Utterance-level Speech Representations
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:21065-21077
Theory on Forgetting and Generalization of Continual Learning
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:21078-21100
Accelerated Cyclic Coordinate Dual Averaging with Extrapolation for Composite Convex Optimization
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:21101-21126
Safe Offline Reinforcement Learning with Real-Time Budget Constraints
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:21127-21152
Probabilistic Unrolling: Scalable, Inverse-Free Maximum Likelihood Estimation for Latent Gaussian Models
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:21153-21181
Fast Online Value-Maximizing Prediction Sets with Conformal Cost Control
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:21182-21203
Unveiling The Mask of Position-Information Pattern Through the Mist of Image Features
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:21204-21222
Fair yet Asymptotically Equal Collaborative Learning
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:21223-21259
Efficient Approximations of Complete Interatomic Potentials for Crystal Property Prediction
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:21260-21287
Continuation Path Learning for Homotopy Optimization
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:21288-21311
Speed-Oblivious Online Scheduling: Knowing (Precise) Speeds is not Necessary
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:21312-21334
Graph Mixup with Soft Alignments
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:21335-21349
Deep Graph Representation Learning and Optimization for Influence Maximization
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:21350-21361
Emergent Agentic Transformer from Chain of Hindsight Experience
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:21362-21374
Shapley Based Residual Decomposition for Instance Analysis
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:21375-21387
Learning Representations without Compositional Assumptions
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:21388-21403
Byzantine-Robust Learning on Heterogeneous Data via Gradient Splitting
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:21404-21425
Towards Constituting Mathematical Structures for Learning to Optimize
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:21426-21449
AudioLDM: Text-to-Audio Generation with Latent Diffusion Models
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:21450-21474
Identifiability of Label Noise Transition Matrix
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:21475-21496
A Group Symmetric Stochastic Differential Equation Model for Molecule Multi-modal Pretraining
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:21497-21526
Using Perturbation to Improve Goodness-of-Fit Tests based on Kernelized Stein Discrepancy
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:21527-21547
Cones: Concept Neurons in Diffusion Models for Customized Generation
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:21548-21566
Opponent-Limited Online Search for Imperfect Information Games
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:21567-21585
Towards Robust and Safe Reinforcement Learning with Benign Off-policy Data
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:21586-21610
Constrained Decision Transformer for Offline Safe Reinforcement Learning
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:21611-21630
Understanding and Defending Patched-based Adversarial Attacks for Vision Transformer
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:21631-21657
NUNO: A General Framework for Learning Parametric PDEs with Non-Uniform Data
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:21658-21671
Hierarchical Programmatic Reinforcement Learning via Learning to Compose Programs
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:21672-21697
Online Local Differential Private Quantile Inference via Self-normalization
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:21698-21714
GFlowOut: Dropout with Generative Flow Networks
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:21715-21729
2D-Shapley: A Framework for Fragmented Data Valuation
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:21730-21755
Causal Structure Learning for Latent Intervened Non-stationary Data
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:21756-21777
Structural Re-weighting Improves Graph Domain Adaptation
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:21778-21793
Dink-Net: Neural Clustering on Large Graphs
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:21794-21812
Oscillation-free Quantization for Low-bit Vision Transformers
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:21813-21824
Understanding the Distillation Process from Deep Generative Models to Tractable Probabilistic Circuits
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:21825-21838
Averaged Method of Multipliers for Bi-Level Optimization without Lower-Level Strong Convexity
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:21839-21866
Graph Switching Dynamical Systems
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:21867-21883
High Probability Convergence of Stochastic Gradient Methods
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:21884-21914
OMS-DPM: Optimizing the Model Schedule for Diffusion Probabilistic Models
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:21915-21936
Lazy Agents: A New Perspective on Solving Sparse Reward Problem in Multi-agent Reinforcement Learning
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:21937-21950
RSC: Accelerate Graph Neural Networks Training via Randomized Sparse Computations
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:21951-21968
Algorithms for bounding contribution for histogram estimation under user-level privacy
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:21969-21996
Simple Embodied Language Learning as a Byproduct of Meta-Reinforcement Learning
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:21997-22008
Generating Private Synthetic Data with Genetic Algorithms
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:22009-22027
FusionRetro: Molecule Representation Fusion via In-Context Learning for Retrosynthetic Planning
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:22028-22041
I$^2$SB: Image-to-Image Schrödinger Bridge
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:22042-22062
What can online reinforcement learning with function approximation benefit from general coverage conditions?
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:22063-22091
TR0N: Translator Networks for 0-Shot Plug-and-Play Conditional Generation
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:22092-22112
Global Optimization with Parametric Function Approximation
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:22113-22136
Deja Vu: Contextual Sparsity for Efficient LLMs at Inference Time
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:22137-22176
Trapdoor Normalization with Irreversible Ownership Verification
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:22177-22187
Same Pre-training Loss, Better Downstream: Implicit Bias Matters for Language Models
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:22188-22214
Taxonomy-Structured Domain Adaptation
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:22215-22232
Dropout Reduces Underfitting
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:22233-22248
Revisiting Pseudo-Label for Single-Positive Multi-Label Learning
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:22249-22265
Retrosynthetic Planning with Dual Value Networks
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:22266-22276
Online Nonstochastic Control with Adversarial and Static Constraints
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:22277-22288
Optimization for Amortized Inverse Problems
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:22289-22319
Active Policy Improvement from Multiple Black-box Oracles
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:22320-22337
Gradient-based Wang-Landau Algorithm: A Novel Sampler for Output Distribution of Neural Networks over the Input Space
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:22338-22351
VectorMapNet: End-to-end Vectorized HD Map Learning
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:22352-22369
Partially Observable Multi-agent RL with (Quasi-)Efficiency: The Blessing of Information Sharing
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:22370-22419
Prometheus: Taming Sample and Communication Complexities in Constrained Decentralized Stochastic Bilevel Learning
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:22420-22453
D2Match: Leveraging Deep Learning and Degeneracy for Subgraph Matching
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:22454-22472
Image Shortcut Squeezing: Countering Perturbative Availability Poisons with Compression
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:22473-22487
Which Invariance Should We Transfer? A Causal Minimax Learning Approach
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:22488-22527
Unsupervised Out-of-Distribution Detection with Diffusion Inpainting
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:22528-22538
N$\text{A}^{\text{2}}$Q: Neural Attention Additive Model for Interpretable Multi-Agent Q-Learning
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:22539-22558
Contextual Combinatorial Bandits with Probabilistically Triggered Arms
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:22559-22593
Flipping Coins to Estimate Pseudocounts for Exploration in Reinforcement Learning
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:22594-22613
Multi-Symmetry Ensembles: Improving Diversity and Generalization via Opposing Symmetries
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:22614-22630
The Flan Collection: Designing Data and Methods for Effective Instruction Tuning
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:22631-22648
Dataset Distillation with Convexified Implicit Gradients
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:22649-22674
Reflected Diffusion Models
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:22675-22701
Never mind the metrics---what about the uncertainty? Visualising binary confusion matrix metric distributions to put performance in perspective
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:22702-22757
Bilevel Optimization with Coupled Decision-Dependent Distributions
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:22758-22789
Two-Scale Gradient Descent Ascent Dynamics Finds Mixed Nash Equilibria of Continuous Games: A Mean-Field Perspective
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:22790-22811
STEP: Learning N:M Structured Sparsity Masks from Scratch with Precondition
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:22812-22824
Contrastive Energy Prediction for Exact Energy-Guided Diffusion Sampling in Offline Reinforcement Learning
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:22825-22855
Exploring the Limits of Model-Targeted Indiscriminate Data Poisoning Attacks
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:22856-22879
QAS-Bench: Rethinking Quantum Architecture Search and A Benchmark
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:22880-22898
Learning Dense Correspondences between Photos and Sketches
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:22899-22916
Adversarial Cheap Talk
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:22917-22941
Federated Conformal Predictors for Distributed Uncertainty Quantification
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:22942-22964
Mechanistic Mode Connectivity
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:22965-23004
A Unifying Framework to the Analysis of Interaction Methods using Synergy Functions
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:23005-23032
SegCLIP: Patch Aggregation with Learnable Centers for Open-Vocabulary Semantic Segmentation
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:23033-23044
Image Restoration with Mean-Reverting Stochastic Differential Equations
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:23045-23066
Dimensionality Reduction for General KDE Mode Finding
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:23067-23082
Iterative Approximate Cross-Validation
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:23083-23102
A Closer Look at Few-shot Classification Again
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:23103-23123
HOPE: High-order Graph ODE For Modeling Interacting Dynamics
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:23124-23139
Stabilizing GANs’ Training with Brownian Motion Controller
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:23140-23156
OCD: Learning to Overfit with Conditional Diffusion Models
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:23157-23169
DiscoBAX: Discovery of optimal intervention sets in genomic experiment design
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:23170-23189
Understanding Plasticity in Neural Networks
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:23190-23211
Bandits with Knapsacks: Advice on Time-Varying Demands
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:23212-23238
Pairwise Ranking Losses of Click-Through Rates Prediction for Welfare Maximization in Ad Auctions
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:23239-23263
Which Tricks are Important for Learning to Rank?
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:23264-23278
Learning Neural Constitutive Laws from Motion Observations for Generalizable PDE Dynamics
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:23279-23300
LIV: Language-Image Representations and Rewards for Robotic Control
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:23301-23320
Graph Inductive Biases in Transformers without Message Passing
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:23321-23337
Learning Signed Distance Functions from Noisy 3D Point Clouds via Noise to Noise Mapping
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:23338-23357
Learning Intuitive Policies Using Action Features
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:23358-23372
Over-parametrization via Lifting for Low-rank Matrix Sensing: Conversion of Spurious Solutions to Strict Saddle Points
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:23373-23387
Buying Information for Stochastic Optimization
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:23388-23411
Generated Graph Detection
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:23412-23428
Calibrating Multimodal Learning
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:23429-23450
AutoCoreset: An Automatic Practical Coreset Construction Framework
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:23451-23466
Learning GFlowNets From Partial Episodes For Improved Convergence And Stability
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:23467-23483
Applied Online Algorithms with Heterogeneous Predictors
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:23484-23497
CSP: Self-Supervised Contrastive Spatial Pre-Training for Geospatial-Visual Representations
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:23498-23515
Vertical Federated Graph Neural Network for Recommender System
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:23516-23535
Can Neural Network Memorization Be Localized?
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:23536-23557
Fundamental Tradeoffs in Learning with Prior Information
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:23558-23573
Additive Causal Bandits with Unknown Graph
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:23574-23589
Weighted Tallying Bandits: Overcoming Intractability via Repeated Exposure Optimality
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:23590-23609
A Kernel-Based View of Language Model Fine-Tuning
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:23610-23641
Performative Reinforcement Learning
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:23642-23680
Differential Privacy has Bounded Impact on Fairness in Classification
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:23681-23705
Random Classification Noise does not defeat All Convex Potential Boosters Irrespective of Model Choice
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:23706-23742
$H$-Consistency Bounds for Pairwise Misranking Loss Surrogates
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:23743-23802
Cross-Entropy Loss Functions: Theoretical Analysis and Applications
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:23803-23828
Supported Trust Region Optimization for Offline Reinforcement Learning
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:23829-23851
Robust Perception through Equivariance
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:23852-23870
Reliable Measures of Spread in High Dimensional Latent Spaces
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:23871-23885
SRATTA: Sample Re-ATTribution Attack of Secure Aggregation in Federated Learning.
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:23886-23914
Neuro-Symbolic Continual Learning: Knowledge, Reasoning Shortcuts and Concept Rehearsal
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:23915-23936
Evaluating Unsupervised Denoising Requires Unsupervised Metrics
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:23937-23957
Regions of Reliability in the Evaluation of Multivariate Probabilistic Forecasts
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:23958-24004
Analyzing Diffusion as Serial Reproduction
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:24005-24019
Quantized Distributed Training of Large Models with Convergence Guarantees
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:24020-24044
Efficient Transformed Gaussian Processes for Non-Stationary Dependent Multi-class Classification
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:24045-24081
Computational Asymmetries in Robust Classification
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:24082-24138
Neural Network Approximations of PDEs Beyond Linearity: A Representational Perspective
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:24139-24172
Generative Pretraining for Black-Box Optimization
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:24173-24197
Improved Policy Evaluation for Randomized Trials of Algorithmic Resource Allocation
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:24198-24213
Multi-Fidelity Covariance Estimation in the Log-Euclidean Geometry
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:24214-24235
Communication-Constrained Bandits under Additive Gaussian Noise
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:24236-24250
Nonparametric Density Estimation under Distribution Drift
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:24251-24270
PAC-Bayesian Generalization Bounds for Adversarial Generative Models
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:24271-24290
Robustness in Multimodal Learning under Train-Test Modality Mismatch
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:24291-24303
A Model-free Closeness-of-influence Test for Features in Supervised Learning
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:24304-24324
Stochastic Gradient Succeeds for Bandits
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:24325-24360
Normalizing Flows for Interventional Density Estimation
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:24361-24397
Reprogramming Pretrained Language Models for Antibody Sequence Infilling
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:24398-24419
Superhuman Fairness
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:24420-24435
A Model-Based Method for Minimizing CVaR and Beyond
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:24436-24456
Tuning Language Models as Training Data Generators for Augmentation-Enhanced Few-Shot Learning
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:24457-24477
On Preemption and Learning in Stochastic Scheduling
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:24478-24516
Quantile Credit Assignment
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:24517-24531
Is Consensus Acceleration Possible in Decentralized Optimization over Slowly Time-Varying Networks?
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:24532-24554
Towards Theoretical Understanding of Inverse Reinforcement Learning
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:24555-24591
Quantum Policy Gradient Algorithm with Optimized Action Decoding
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:24592-24613
Training Deep Surrogate Models with Large Scale Online Learning
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:24614-24630
MANSA: Learning Fast and Slow in Multi-Agent Systems
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:24631-24658
Representation Learning with Multi-Step Inverse Kinematics: An Efficient and Optimal Approach to Rich-Observation RL
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:24659-24700
Single Point-Based Distributed Zeroth-Order Optimization with a Non-Convex Stochastic Objective Function
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:24701-24719
Learning Instance-Specific Augmentations by Capturing Local Invariances
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:24720-24736
Path Neural Networks: Expressive and Accurate Graph Neural Networks
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:24737-24755
Learning to acquire novel cognitive tasks with evolution, plasticity and meta-meta-learning
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:24756-24774
Generative Decoding of Visual Stimuli
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:24775-24784
Cooperative Multi-Agent Reinforcement Learning: Asynchronous Communication and Linear Function Approximation
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:24785-24811
Directed Chain Generative Adversarial Networks
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:24812-24830
An Information-Theoretic Analysis of Nonstationary Bandit Learning
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:24831-24849
On the Convergence of Gradient Flow on Multi-layer Linear Models
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:24850-24887
Optimal Sets and Solution Paths of ReLU Networks
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:24888-24924
The Numerical Stability of Hyperbolic Representation Learning
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:24925-24949
DetectGPT: Zero-Shot Machine-Generated Text Detection using Probability Curvature
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:24950-24962
Diffusion Based Representation Learning
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:24963-24982
Disentangled Multiplex Graph Representation Learning
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:24983-25005
A Unified Audio-Visual Learning Framework for Localization, Separation, and Recognition
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:25006-25017
Pruning via Sparsity-indexed ODE: a Continuous Sparsity Viewpoint
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:25018-25036
Text-To-Concept (and Back) via Cross-Model Alignment
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:25037-25060
A Fast, Well-Founded Approximation to the Empirical Neural Tangent Kernel
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:25061-25081
Special Properties of Gradient Descent with Large Learning Rates
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:25082-25104
Neural Inverse Operators for Solving PDE Inverse Problems
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:25105-25139
Input uncertainty propagation through trained neural networks
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:25140-25173
Compressing Tabular Data via Latent Variable Estimation
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:25174-25208
An SDE for Modeling SAM: Theory and Insights
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:25209-25253
Learning Deductive Reasoning from Synthetic Corpus based on Formal Logic
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:25254-25274
WL meet VC
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:25275-25302
ReLOAD: Reinforcement Learning with Optimistic Ascent-Descent for Last-Iterate Convergence in Constrained MDPs
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:25303-25336
Optimistic Planning by Regularized Dynamic Programming
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:25337-25357
Neural signature kernels as infinite-width-depth-limits of controlled ResNets
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:25358-25425
Improving Statistical Fidelity for Neural Image Compression with Implicit Local Likelihood Models
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:25426-25443
PFNs4BO: In-Context Learning for Bayesian Optimization
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:25444-25470
Achieving High Accuracy with PINNs via Energy Natural Gradient Descent
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:25471-25485
Uncertain Evidence in Probabilistic Models and Stochastic Simulators
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:25486-25500
GibbsDDRM: A Partially Collapsed Gibbs Sampler for Solving Blind Inverse Problems with Denoising Diffusion Restoration
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:25501-25522
DIFF2: Differential Private Optimization via Gradient Differences for Nonconvex Distributed Learning
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:25523-25548
Efficiently predicting high resolution mass spectra with graph neural networks
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:25549-25562
Dynamical Linear Bandits
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:25563-25587
Representation-Driven Reinforcement Learning
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:25588-25603
DADAO: Decoupled Accelerated Decentralized Asynchronous Optimization
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:25604-25626
Multi-User Reinforcement Learning with Low Rank Rewards
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:25627-25659
Statistical Foundations of Prior-Data Fitted Networks
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:25660-25676
Do Machine Learning Models Learn Statistical Rules Inferred from Data?
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:25677-25693
Sample and Predict Your Latent: Modality-free Sequential Disentanglement via Contrastive Estimation
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:25694-25717
Effectively Using Public Data in Privacy Preserving Machine Learning
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:25718-25732
Counterfactual Identifiability of Bijective Causal Models
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:25733-25754
Discovering Object-Centric Generalized Value Functions From Pixels
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:25755-25768
On Many-Actions Policy Gradient
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:25769-25789
Equivariant Architectures for Learning in Deep Weight Spaces
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:25790-25816
Scalable Multi-Agent Reinforcement Learning through Intelligent Information Aggregation
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:25817-25833
Geometric Autoencoders - What You See is What You Decode
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:25834-25857
Action Matching: Learning Stochastic Dynamics from Samples
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:25858-25889
Extending Conformal Prediction to Hidden Markov Models with Exact Validity via de Finetti’s Theorem for Markov Chains
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:25890-25903
ClimaX: A foundation model for weather and climate
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:25904-25938
Provable Reset-free Reinforcement Learning by No-Regret Reduction
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:25939-25955
Revisiting Over-smoothing and Over-squashing Using Ollivier-Ricci Curvature
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:25956-25979
Deep Clustering with Incomplete Noisy Pairwise Annotations: A Geometric Regularization Approach
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:25980-26007
Self-Attention Amortized Distributional Projection Optimization for Sliced Wasserstein Point-Cloud Reconstruction
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:26008-26030
Building Neural Networks on Matrix Manifolds: A Gyrovector Space Approach
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:26031-26062
Simple Disentanglement of Style and Content in Visual Representations
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:26063-26086
MetaDiffuser: Diffusion Model as Conditional Planner for Offline Meta-RL
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:26087-26105
LEVER: Learning to Verify Language-to-Code Generation with Execution
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:26106-26128
Continual Vision-Language Representation Learning with Off-Diagonal Information
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:26129-26149
Attributing Image Generative Models using Latent Fingerprints
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:26150-26165
A Framework for Adapting Offline Algorithms to Solve Combinatorial Multi-Armed Bandit Problems with Bandit Feedback
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:26166-26198
SinFusion: Training Diffusion Models on a Single Image or Video
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:26199-26214
SparseProp: Efficient Sparse Backpropagation for Faster Training of Neural Networks at the Edge
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:26215-26227
Anti-Exploration by Random Network Distillation
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:26228-26244
Input Perturbation Reduces Exposure Bias in Diffusion Models
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:26245-26265
Primal and Dual Analysis of Entropic Fictitious Play for Finite-sum Problems
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:26266-26282
The Statistical Scope of Multicalibration
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:26283-26310
Do Embodied Agents Dream of Pixelated Sheep: Embodied Decision Making using Language Guided World Modelling
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:26311-26325
Gradient-Free Structured Pruning with Unlabeled Data
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:26326-26341
CHiLS: Zero-Shot Image Classification with Hierarchical Label Sets
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:26342-26362
Few-bit Backward: Quantized Gradients of Activation Functions for Memory Footprint Reduction
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:26363-26381
Efficient Exploration via Epistemic-Risk-Seeking Policy Optimization
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:26382-26402
Provable Benefit of Mixup for Finding Optimal Decision Boundaries
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:26403-26450
Shedding a PAC-Bayesian Light on Adaptive Sliced-Wasserstein Distances
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:26451-26473
Reasons for the Superiority of Stochastic Estimators over Deterministic Ones: Robustness, Consistency and Perceptual Quality
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:26474-26494
On the Within-Group Fairness of Screening Classifiers
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:26495-26516
Diffusion Models are Minimax Optimal Distribution Estimators
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:26517-26582
How Many Perturbations Break This Model? Evaluating Robustness Beyond Adversarial Accuracy
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:26583-26598
B-Learner: Quasi-Oracle Bounds on Heterogeneous Causal Effects Under Hidden Confounding
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:26599-26618
Measuring the Impact of Programming Language Distribution
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:26619-26645
When does Privileged information Explain Away Label Noise?
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:26646-26669
Resurrecting Recurrent Neural Networks for Long Sequences
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:26670-26698
Improving Adversarial Robustness Through the Contrastive-Guided Diffusion Process
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:26699-26723
On the Role of Attention in Prompt-tuning
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:26724-26768
Revisiting the Linear-Programming Framework for Offline RL with General Function Approximation
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:26769-26791
Extrapolative Controlled Sequence Generation via Iterative Refinement
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:26792-26808
Locally Regularized Neural Differential Equations: Some Black Boxes were meant to remain closed!
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:26809-26819
Controlled Differential Equations on Long Sequences via Non-standard Wavelets
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:26820-26836
Do the Rewards Justify the Means? Measuring Trade-Offs Between Rewards and Ethical Behavior in the Machiavelli Benchmark
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:26837-26867
Beyond Homophily: Reconstructing Structure for Graph-agnostic Clustering
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:26868-26877
Better Training of GFlowNets with Local Credit and Incomplete Trajectories
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:26878-26890
A Hybrid Quantum-Classical Approach based on the Hadamard Transform for the Convolutional Layer
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:26891-26903
Semi Bandit dynamics in Congestion Games: Convergence to Nash Equilibrium and No-Regret Guarantees.
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:26904-26930
Flash: Concept Drift Adaptation in Federated Learning
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:26931-26962
Learn to Accumulate Evidence from All Training Samples: Theory and Practice
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:26963-26989
Secure Federated Correlation Test and Entropy Estimation
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:26990-27010
Task-Specific Skill Localization in Fine-tuned Language Models
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:27011-27033
Kernel Sufficient Dimension Reduction and Variable Selection for Compositional Data via Amalgamation
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:27034-27047
Learning Affinity with Hyperbolic Representation for Spatial Propagation
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:27048-27073
TRAK: Attributing Model Behavior at Scale
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:27074-27113
Test-Time Style Shifting: Handling Arbitrary Styles in Domain Generalization
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:27114-27131
Towards Understanding Ensemble Distillation in Federated Learning
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:27132-27187
Learning Controllable Degradation for Real-World Super-Resolution via Constrained Flows
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:27188-27203
Differentially Private Sharpness-Aware Training
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:27204-27224
Controllability-Aware Unsupervised Skill Discovery
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:27225-27245
Predictable MDP Abstraction for Unsupervised Model-Based RL
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:27246-27268
Neural Stochastic Differential Games for Time-series Analysis
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:27269-27293
Accelerated Infeasibility Detection of Constrained Optimization and Fixed-Point Iterations
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:27294-27345
Model-based Reinforcement Learning with Scalable Composite Policy Gradient Estimators
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:27346-27377
PAC Generalization via Invariant Representations
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:27378-27400
Stochastic Gradient Descent-Induced Drift of Representation in a Two-Layer Neural Network
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:27401-27419
Reducing SO(3) Convolutions to SO(2) for Efficient Equivariant GNNs
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:27420-27438
Federated Online and Bandit Convex Optimization
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:27439-27460
Brauer’s Group Equivariant Neural Networks
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:27461-27482
How Jellyfish Characterise Alternating Group Equivariant Neural Networks
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:27483-27495
Can Large Language Models Reason about Program Invariants?
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:27496-27520
Dynamics-inspired Neuromorphic Visual Representation Learning
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:27521-27541
Feature Directions Matter: Long-Tailed Learning via Rotated Balanced Representation
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:27542-27563
Fair Neighbor Embedding
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:27564-27584
The Ideal Continual Learner: An Agent That Never Forgets
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:27585-27610
MolDiff: Addressing the Atom-Bond Inconsistency Problem in 3D Molecule Diffusion Generation
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:27611-27629
Diagnosis, Feedback, Adaptation: A Human-in-the-Loop Framework for Test-Time Policy Adaptation
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:27630-27641
Learning Hidden Markov Models When the Locations of Missing Observations are Unknown
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:27642-27667
Estimating the Contamination Factor’s Distribution in Unsupervised Anomaly Detection
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:27668-27679
Are Gaussian Data All You Need? The Extents and Limits of Universality in High-Dimensional Generalized Linear Estimation
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:27680-27708
Certifying Ensembles: A General Certification Theory with S-Lipschitzness
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:27709-27736
The Power of Learned Locally Linear Models for Nonlinear Policy Optimization
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:27737-27821
A Scalable Frank-Wolfe-Based Algorithm for the Max-Cut SDP
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:27822-27839
Attention-Based Recurrence for Multi-Agent Reinforcement Learning under Stochastic Partial Observability
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:27840-27853
HyperTuning: Toward Adapting Large Language Models without Back-propagation
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:27854-27875
Linear CNNs Discover the Statistical Structure of the Dataset Using Only the Most Dominant Frequencies
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:27876-27906
Conformal Prediction for Federated Uncertainty Quantification Under Label Shift
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:27907-27947
Universal Physics-Informed Neural Networks: Symbolic Differential Operator Discovery with Sparse Data
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:27948-27956
Sequential Kernelized Independence Testing
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:27957-27993
Truncating Trajectories in Monte Carlo Reinforcement Learning
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:27994-28042
Hyena Hierarchy: Towards Larger Convolutional Language Models
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:28043-28078
Spurious Valleys and Clustering Behavior of Neural Networks
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:28079-28099
Multisample Flow Matching: Straightening Flows with Minibatch Couplings
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:28100-28127
Minimax estimation of discontinuous optimal transport maps: The semi-discrete case
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:28128-28150
Test-time Adaptation with Slot-Centric Models
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:28151-28166
JAWS-X: Addressing Efficiency Bottlenecks of Conformal Prediction Under Standard and Feedback Covariate Shift
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:28167-28190
Equivariant Polynomials for Graph Neural Networks
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:28191-28222
Contrast with Reconstruct: Contrastive 3D Representation Learning Guided by Generative Pretraining
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:28223-28243
An Effective Meaningful Way to Evaluate Survival Models
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:28244-28276
Coarse-to-Fine: a Hierarchical Diffusion Model for Molecule Generation in 3D
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:28277-28299
Collaborative Causal Inference with Fair Incentives
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:28300-28320
FREDIS: A Fusion Framework of Refinement and Disambiguation for Unreliable Partial Label Learning
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:28321-28336
Nugget: Neural Agglomerative Embeddings of Text
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:28337-28350
BiBench: Benchmarking and Analyzing Network Binarization
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:28351-28388
Not All Semantics are Created Equal: Contrastive Self-supervised Learning with Automatic Temperature Individualization
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:28389-28421
Shortest Edit Path Crossover: A Theory-driven Solution to the Permutation Problem in Evolutionary Neural Architecture Search
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:28422-28447
Simple and Fast Group Robustness by Automatic Feature Reweighting
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:28448-28467
DRCFS: Doubly Robust Causal Feature Selection
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:28468-28491
Robust Speech Recognition via Large-Scale Weak Supervision
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:28492-28518
Shiftable Context: Addressing Training-Inference Context Mismatch in Simultaneous Speech Translation
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:28519-28530
Sequential Multi-Dimensional Self-Supervised Learning for Clinical Time Series
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:28531-28548
Recovery Bounds on Class-Based Optimal Transport: A Sum-of-Norms Regularization Framework
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:28549-28577
Algorithmic Stability of Heavy-Tailed SGD with General Loss Functions
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:28578-28597
Mastering the Unsupervised Reinforcement Learning Benchmark from Pixels
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:28598-28617
SpotEM: Efficient Video Search for Episodic Memory
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:28618-28636
How much does Initialization Affect Generalization?
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:28637-28655
Model Ratatouille: Recycling Diverse Models for Out-of-Distribution Generalization
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:28656-28679
A Picture of the Space of Typical Learnable Tasks
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:28680-28700
Policy Regularization with Dataset Constraint for Offline Reinforcement Learning
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:28701-28717
SpENCNN: Orchestrating Encoding and Sparsity for Fast Homomorphically Encrypted Neural Network Inference
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:28718-28728
Feature learning in deep classifiers through Intermediate Neural Collapse
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:28729-28745
The Unintended Consequences of Discount Regularization: Improving Regularization in Certainty Equivalence Reinforcement Learning
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:28746-28767
Beam Tree Recursive Cells
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:28768-28791
Monotonic Location Attention for Length Generalization
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:28792-28808
Automated Search for Conjectures on Mathematical Constants using Analysis of Integer Sequences
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:28809-28842
Neural networks trained with SGD learn distributions of increasing complexity
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:28843-28863
Simplex Random Features
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:28864-28888
Bayesian Neural Networks Avoid Encoding Complex and Perturbation-Sensitive Concepts
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:28889-28913
Escaping saddle points in zeroth-order optimization: the power of two-point estimators
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:28914-28975
Dimension-independent Certified Neural Network Watermarks via Mollifier Smoothing
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:28976-29008
Feature Programming for Multivariate Time Series Prediction
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:29009-29029
Run-off Election: Improved Provable Defense against Data Poisoning Attacks
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:29030-29050
Learning Control-Oriented Dynamical Structure from Data
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:29051-29062
The Edge of Orthogonality: A Simple View of What Makes BYOL Tick
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:29063-29081
Multi-Agent Best Arm Identification with Private Communications
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:29082-29102
A Two-Stage Active Learning Algorithm for k-Nearest Neighbors
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:29103-29129
Lowering the Pre-training Tax for Gradient-based Subset Training: A Lightweight Distributed Pre-Training Toolkit
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:29130-29142
The Role of Entropy and Reconstruction in Multi-View Self-Supervised Learning
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:29143-29160
RLang: A Declarative Language for Describing Partial World Knowledge to Reinforcement Learning Agents
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:29161-29178
Improving Fair Training under Correlation Shifts
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:29179-29209
The Statistical Benefits of Quantile Temporal-Difference Learning for Value Estimation
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:29210-29231
Robust Satisficing MDPs
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:29232-29258
Infinite Action Contextual Bandits with Reusable Data Exhaust
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:29259-29274
Function-Space Regularization in Neural Networks: A Probabilistic Perspective
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:29275-29290
A New PHO-rmula for Improved Performance of Semi-Structured Networks
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:29291-29305
Geometric Clifford Algebra Networks
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:29306-29337
Constrained Monotonic Neural Networks
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:29338-29353
Differential Privacy, Linguistic Fairness, and Training Data Influence: Impossibility and Possibility Theorems for Multilingual Language Models
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:29354-29387
Intrinsic Sliced Wasserstein Distances for Comparing Collections of Probability Distributions on Manifolds and Graphs
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:29388-29415
SWARM Parallelism: Training Large Models Can Be Surprisingly Communication-Efficient
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:29416-29440
Hiera: A Hierarchical Vision Transformer without the Bells-and-Whistles
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:29441-29454
End-to-End Learning for Stochastic Optimization: A Bayesian Perspective
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:29455-29472
Sequential Monte Carlo Learning for Time Series Structure Discovery
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:29473-29489
Active Ranking of Experts Based on their Performances in Many Tasks
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:29490-29513
Sample Complexity Bounds for Learning High-dimensional Simplices in Noisy Regimes
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:29514-29541
Global Selection of Contrastive Batches via Optimization on Sample Permutations
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:29542-29562
High-Probability Bounds for Stochastic Optimization and Variational Inequalities: the Case of Unbounded Variance
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:29563-29648
End-to-end Differentiable Clustering with Associative Memories
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:29649-29670
Learning to Suggest Breaks: Sustainable Optimization of Long-Term User Engagement
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:29671-29696
Multi-class Graph Clustering via Approximated Effective $p$-Resistance
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:29697-29733
Off-Policy Evaluation for Large Action Spaces via Conjunct Effect Modeling
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:29734-29759
Rethinking Warm-Starts with Predictions: Learning Predictions Close to Sets of Optimal Solutions for Faster $\text{L}$-/$\text{L}^\natural$-Convex Function Minimization
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:29760-29776
PAC-Bayesian Offline Contextual Bandits With Guarantees
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:29777-29799
Provably and Practically Efficient Neural Contextual Bandits
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:29800-29844
Distributed Linear Bandits under Communication Constraints
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:29845-29875
Optimizing Hyperparameters with Conformal Quantile Regression
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:29876-29893
Raising the Cost of Malicious AI-Powered Image Editing
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:29894-29918
Fast, Differentiable and Sparse Top-k: a Convex Analysis Perspective
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:29919-29936
TAN Without a Burn: Scaling Laws of DP-SGD
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:29937-29949
Discrete Continuous Optimization Framework for Simultaneous Clustering and Training in Mixture Models
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:29950-29970
Whose Opinions Do Language Models Reflect?
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:29971-30004
Streaming Active Learning with Deep Neural Networks
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:30005-30021
Random Teachers are Good Teachers
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:30022-30041
Posterior Sampling for Deep Reinforcement Learning
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:30042-30061
Graph Neural Networks can Recover the Hidden Features Solely from the Graph Structure
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:30062-30079
Existence and Estimation of Critical Batch Size for Training Generative Adversarial Networks with Two Time-Scale Update Rule
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:30080-30104
StyleGAN-T: Unlocking the Power of GANs for Fast Large-Scale Text-to-Image Synthesis
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:30105-30118
Facial Expression Recognition with Adaptive Frame Rate based on Multiple Testing Correction
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:30119-30129
Off-Policy Average Reward Actor-Critic with Deterministic Policy Search
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:30130-30203
Gibbsian Polar Slice Sampling
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:30204-30223
Identifiability and Generalizability in Constrained Inverse Reinforcement Learning
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:30224-30251
Learning Expressive Priors for Generalization and Uncertainty Estimation in Neural Networks
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:30252-30284
Deterministic equivalent and error universality of deep random features learning
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:30285-30320
The Acquisition of Physical Knowledge in Generative Neural Networks
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:30321-30341
Modality-Agnostic Variational Compression of Implicit Neural Representations
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:30342-30364
Bigger, Better, Faster: Human-level Atari with human-level efficiency
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:30365-30380
Dissecting the Effects of SGD Noise in Distinct Regimes of Deep Learning
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:30381-30405
A Fast Optimistic Method for Monotone Variational Inequalities
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:30406-30438
Double-Weighting for Covariate Shift Adaptation
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:30439-30457
Enhancing Activity Prediction Models in Drug Discovery with the Ability to Understand Human Language
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:30458-30490
Variational Autoencoding Neural Operators
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:30491-30522
Neural Markov Jump Processes
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:30523-30552
Bayesian online change point detection with Hilbert space approximate Student-t process
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:30553-30569
Incentivizing Exploration with Linear Contexts and Combinatorial Actions
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:30570-30583
Explainability as statistical inference
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:30584-30612
Multi-View Masked World Models for Visual Robotic Manipulation
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:30613-30632
One-Shot Compression of Large Edge-Exchangeable Graphs using Bits-Back Coding
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:30633-30645
ModelDiff: A Framework for Comparing Learning Algorithms
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:30646-30688
Auxiliary Learning as an Asymmetric Bargaining Game
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:30689-30705
Synthetic Prompting: Generating Chain-of-Thought Demonstrations for Large Language Models
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:30706-30775
Complementary Attention for Multi-Agent Reinforcement Learning
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:30776-30793
Regularization-free Diffeomorphic Temporal Alignment Nets
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:30794-30826
Toward Efficient Gradient-Based Value Estimation
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:30827-30849
Coin Sampling: Gradient-Based Bayesian Inference without Learning Rates
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:30850-30882
On Kinetic Optimal Probability Paths for Generative Models
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:30883-30907
Sequential Changepoint Detection via Backward Confidence Sequences
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:30908-30930
Cold Analysis of Rao-Blackwellized Straight-Through Gumbel-Softmax Gradient Estimator
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:30931-30955
Towards Understanding and Improving GFlowNet Training
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:30956-30975
On Balancing Bias and Variance in Unsupervised Multi-Source-Free Domain Adaptation
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:30976-30991
On Penalty-based Bilevel Gradient Descent Method
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:30992-31015
Non-autoregressive Conditional Diffusion Models for Time Series Prediction
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:31016-31029
Cross-Modal Fine-Tuning: Align then Refine
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:31030-31056
Auxiliary Modality Learning with Generalized Curriculum Distillation
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:31057-31076
TGRL: An Algorithm for Teacher Guided Reinforcement Learning
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:31077-31093
FlexGen: High-Throughput Generative Inference of Large Language Models with a Single GPU
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:31094-31116
Improved Regret for Efficient Online Reinforcement Learning with Linear Function Approximation
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:31117-31150
Fundamental Limits of Two-layer Autoencoders, and Achieving Them with Gradient Methods
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:31151-31209
Large Language Models Can Be Easily Distracted by Irrelevant Context
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:31210-31227
Everyone’s Preference Changes Differently: A Weighted Multi-Interest Model For Retrieval
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:31228-31242
A Near-Optimal Algorithm for Safe Reinforcement Learning Under Instantaneous Hard Constraints
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:31243-31268
Improving the Model Consistency of Decentralized Federated Learning
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:31269-31291
UPop: Unified and Progressive Pruning for Compressing Vision-Language Transformers
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:31292-31311
Sequence Modeling with Multiresolution Convolutional Memory
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:31312-31327
Statistical Inference on Multi-armed Bandits with Delayed Feedback
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:31328-31352
Provably Efficient Offline Reinforcement Learning with Perturbed Data Sources
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:31353-31388
On the Complexity of Bayesian Generalization
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:31389-31407
Understanding and Generalizing Contrastive Learning from the Inverse Optimal Transport Perspective
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:31408-31421
Long Horizon Temperature Scaling
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:31422-31434
Gradient Descent in Neural Networks as Sequential Learning in Reproducing Kernel Banach Space
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:31435-31488
SNeRL: Semantic-aware Neural Radiance Fields for Reinforcement Learning
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:31489-31503
A Closer Look at the Intervention Procedure of Concept Bottleneck Models
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:31504-31520
MetricGAN-OKD: Multi-Metric Optimization of MetricGAN via Online Knowledge Distillation for Speech Enhancement
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:31521-31538
Improved Learning-Augmented Algorithms for the Multi-Option Ski Rental Problem via Best-Possible Competitive Analysis
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:31539-31561
One-shot Imitation in a Non-Stationary Environment via Multi-Modal Skill
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:31562-31578
Context Consistency Regularization for Label Sparsity in Time Series
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:31579-31595
Generative Causal Representation Learning for Out-of-Distribution Motion Forecasting
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:31596-31612
Exphormer: Sparse Transformers for Graphs
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:31613-31632
Synthetic data for model selection
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:31633-31656
Probabilistic Attention-to-Influence Neural Models for Event Sequences
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:31657-31674
Causal Bounds in Quasi-Markovian Graphs
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:31675-31692
Repository-Level Prompt Generation for Large Language Models of Code
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:31693-31715
CLIPood: Generalizing CLIP to Out-of-Distributions
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:31716-31731
Semi-Autoregressive Energy Flows: Exploring Likelihood-Free Training of Normalizing Flows
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:31732-31753
Unearthing InSights into Mars: Unsupervised Source Separation with Limited Data
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:31754-31772
Quantitative Universal Approximation Bounds for Deep Belief Networks
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:31773-31787
Pricing Experimental Design: Causal Effect, Expected Revenue and Tail Risk
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:31788-31799
Statistical Learning under Heterogeneous Distribution Shift
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:31800-31851
On the Stepwise Nature of Self-Supervised Learning
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:31852-31876
Hindsight Learning for MDPs with Exogenous Inputs
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:31877-31914
Text-To-4D Dynamic Scene Generation
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:31915-31929
The Hessian perspective into the Nature of Convolutional Neural Networks
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:31930-31968
When do Minimax-fair Learning and Empirical Risk Minimization Coincide?
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:31969-31989
Differentiable Simulations for Enhanced Sampling of Rare Events
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:31990-32007
Preprocessors Matter! Realistic Decision-Based Attacks on Machine Learning Systems
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:32008-32032
Invariance in Policy Optimisation and Partial Identifiability in Reward Learning
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:32033-32058
A Game-Theoretic Framework for Managing Risk in Multi-Agent Systems
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:32059-32087
On the Effectiveness of Offline RL for Dialogue Response Generation
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:32088-32104
Fair Densities via Boosting the Sufficient Statistics of Exponential Families
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:32105-32144
The Dormant Neuron Phenomenon in Deep Reinforcement Learning
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:32145-32168
Abstracting Imperfect Information Away from Two-Player Zero-Sum Games
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:32169-32193
Meta-SAGE: Scale Meta-Learning Scheduled Adaptation with Guided Exploration for Mitigating Scale Shift on Combinatorial Optimization
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:32194-32210
Consistency Models
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:32211-32252
LipsNet: A Smooth and Robust Neural Network with Adaptive Lipschitz Constant for High Accuracy Optimal Control
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:32253-32272
Deep Perturbation Learning: Enhancing the Network Performance via Image Perturbations
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:32273-32287
Latent Traversals in Generative Models as Potential Flows
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:32288-32303
FedAvg Converges to Zero Training Loss Linearly for Overparameterized Multi-Layer Neural Networks
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:32304-32330
RGE: A Repulsive Graph Rectification for Node Classification via Influence
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:32331-32348
Importance Weighted Expectation-Maximization for Protein Sequence Design
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:32349-32364
Sketching for First Order Method: Efficient Algorithm for Low-Bandwidth Channel and Vulnerability
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:32365-32417
Sketching Meets Differential Privacy: Fast Algorithm for Dynamic Kronecker Projection Maintenance
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:32418-32462
A Nearly-Optimal Bound for Fast Regression with $\ell_∞$ Guarantee
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:32463-32482
Loss-Guided Diffusion Models for Plug-and-Play Controllable Generation
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:32483-32498
Differentiable Tree Operations Promote Compositional Generalization
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:32499-32520
Are labels informative in semi-supervised learning? Estimating and leveraging the missing-data mechanism.
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:32521-32539
Linear Causal Disentanglement via Interventions
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:32540-32560
Generating Language Corrections for Teaching Physical Control Tasks
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:32561-32574
FaDIn: Fast Discretized Inference for Hawkes Processes with General Parametric Kernels
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:32575-32597
Partial Optimality in Cubic Correlation Clustering
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:32598-32617
MODeL: Memory Optimizations for Deep Learning
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:32618-32632
Improving Expert Predictions with Conformal Prediction
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:32633-32653
Lookahead When It Matters: Adaptive Non-causal Transformers for Streaming Neural Transducers
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:32654-32676
Kernel QuantTree
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:32677-32697
Topologically Faithful Image Segmentation via Induced Matching of Persistence Barcodes
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:32698-32727
Towards Robust Graph Incremental Learning on Evolving Graphs
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:32728-32748
DUET: 2D Structured and Approximately Equivariant Representations
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:32749-32769
Long-Tailed Recognition by Mutual Information Maximization between Latent Features and Ground-Truth Labels
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:32770-32782
Adversarial Learning of Distributional Reinforcement Learning
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:32783-32796
Distilling Internet-Scale Vision-Language Models into Embodied Agents
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:32797-32818
Vector-Valued Control Variates
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:32819-32846
MetaModulation: Learning Variational Feature Hierarchies for Few-Shot Learning with Fewer Tasks
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:32847-32858
Revisiting Sampling for Combinatorial Optimization
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:32859-32874
What Makes Entities Similar? A Similarity Flooding Perspective for Multi-sourced Knowledge Graph Embeddings
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:32875-32885
Maximum Optimality Margin: A Unified Approach for Contextual Linear Programming and Inverse Linear Programming
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:32886-32912
Tensor Gaussian Process with Contraction for Multi-Channel Imaging Analysis
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:32913-32935
MABe22: A Multi-Species Multi-Task Benchmark for Learned Representations of Behavior
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:32936-32990
Dynamic Regularized Sharpness Aware Minimization in Federated Learning: Approaching Global Consistency and Smooth Landscape
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:32991-33013
When and How Does Known Class Help Discover Unknown Ones? Provable Understanding Through Spectral Analysis
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:33014-33043
Learning Prescriptive ReLU Networks
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:33044-33060
All in a Row: Compressed Convolution Networks for Graphs
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:33061-33076
Momentum Ensures Convergence of SIGNSGD under Weaker Assumptions
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:33077-33099
A Critical Revisit of Adversarial Robustness in 3D Point Cloud Recognition with Diffusion-Driven Purification
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:33100-33114
SDDM: Score-Decomposed Diffusion Models on Manifolds for Unpaired Image-to-Image Translation
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:33115-33134
A Neural PDE Solver with Temporal Stencil Modeling
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:33135-33155
Feature Expansion for Graph Neural Networks
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:33156-33176
Model-Bellman Inconsistency for Model-based Offline Reinforcement Learning
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:33177-33194
Inflow, Outflow, and Reciprocity in Machine Learning
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:33195-33208
When Personalization Harms Performance: Reconsidering the Use of Group Attributes in Prediction
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:33209-33228
Tuning Computer Vision Models With Task Rewards
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:33229-33239
Beyond Exponentially Fast Mixing in Average-Reward Reinforcement Learning via Multi-Level Monte Carlo Actor-Critic
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:33240-33267
Tight and fast generalization error bound of graph embedding in metric space
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:33268-33284
Proximal Causal Learning of Conditional Average Treatment Effects
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:33285-33298
Inverse Reinforcement Learning without Reinforcement Learning
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:33299-33318
Von Mises Mixture Distributions for Molecular Conformation Generation
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:33319-33342
Optimal randomized multilevel Monte Carlo for repeatedly nested expectations
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:33343-33364
Adaptive Coordination in Social Embodied Rearrangement
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:33365-33380
MG-GNN: Multigrid Graph Neural Networks for Learning Multilevel Domain Decomposition Methods
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:33381-33395
Learning Mixtures of Gaussians with Censored Data
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:33396-33415
Approximation and Estimation Ability of Transformers for Sequence-to-Sequence Functions with Infinite Dimensional Input
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:33416-33447
Learning Neural PDE Solvers with Parameter-Guided Channel Attention
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:33448-33467
Contextual Conservative Interleaving Bandits
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:33468-33489
Randomized Gaussian Process Upper Confidence Bound with Tighter Bayesian Regret Bounds
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:33490-33515
Towards Practical Preferential Bayesian Optimization with Skew Gaussian Processes
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:33516-33533
Robust Explanation for Free or At the Cost of Faithfulness
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:33534-33562
Provably Invariant Learning without Domain Information
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:33563-33580
Auto-Differentiation of Relational Computations for Very Large Scale Machine Learning
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:33581-33598
Regret-Minimizing Double Oracle for Extensive-Form Games
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:33599-33615
From Perception to Programs: Regularize, Overparameterize, and Amortize
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:33616-33631
Understanding Self-Predictive Learning for Reinforcement Learning
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:33632-33656
DoMo-AC: Doubly Multi-step Off-policy Actor-Critic Algorithm
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:33657-33673
Towards Understanding Generalization of Graph Neural Networks
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:33674-33719
Towards a better understanding of representation dynamics under TD-learning
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:33720-33738
VA-learning as a more efficient alternative to Q-learning
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:33739-33757
Defects of Convolutional Decoder Networks in Frequency Representation
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:33758-33791
Difference-in-Differences Meets Tree-based Methods: Heterogeneous Treatment Effects Estimation with Unmeasured Confounding
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:33792-33803
End-to-end Training of Deep Boltzmann Machines by Unbiased Contrastive Divergence with Local Mode Initialization
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:33804-33815
POUF: Prompt-Oriented Unsupervised Fine-tuning for Large Pre-trained Models
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:33816-33832
Dual Focal Loss for Calibration
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:33833-33849
Abstract-to-Executable Trajectory Translation for One-Shot Task Generalization
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:33850-33882
Data Feedback Loops: Model-driven Amplification of Dataset Biases
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:33883-33920
Deep Regression Unlearning
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:33921-33939
How to Trust Your Diffusion Model: A Convex Optimization Approach to Conformal Risk Control
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:33940-33960
Concurrent Shuffle Differential Privacy Under Continual Observation
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:33961-33982
Finding Generalization Measures by Contrasting Signal and Noise
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:33983-34010
Reinforcement Learning with History Dependent Dynamic Contexts
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:34011-34053
PWSHAP: A Path-Wise Explanation Model for Targeted Variables
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:34054-34089
On the Estimation of Gaussian Mixture Copula Models
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:34090-34104
Target-Aware Generative Augmentations for Single-Shot Adaptation
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:34105-34119
ELSA: Efficient Label Shift Adaptation through the Lens of Semiparametric Models
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:34120-34142
Spherical Inducing Features for Orthogonally-Decoupled Gaussian Processes
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:34143-34160
Fast Rates for Maximum Entropy Exploration
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:34161-34221
Margin-based sampling in high dimensions: When being active is less efficient than staying passive
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:34222-34262
Differentiable Multi-Target Causal Bayesian Experimental Design
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:34263-34279
PCA-based Multi-Task Learning: a Random Matrix Approach
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:34280-34300
Perturbation Analysis of Neural Collapse
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:34301-34329
Overcoming Simplicity Bias in Deep Networks using a Feature Sieve
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:34330-34343
Beyond In-Domain Scenarios: Robust Density-Aware Calibration
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:34344-34368
Distribution Free Domain Generalization
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:34369-34378
Extending Kernel PCA through Dualization: Sparsity, Robustness and Fast Algorithms
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:34379-34393
Robust Weak Supervision with Variational Auto-Encoders
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:34394-34408
Fully Bayesian Autoencoders with Latent Sparse Gaussian Processes
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:34409-34430
Discrete Key-Value Bottleneck
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:34431-34455
Mimetic Initialization of Self-Attention Layers
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:34456-34468
Representer Point Selection for Explaining Regularized High-dimensional Models
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:34469-34490
Expected Gradients of Maxout Networks and Consequences to Parameter Initialization
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:34491-34532
Provable Data Subset Selection For Efficient Neural Networks Training
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:34533-34555
Jump-Start Reinforcement Learning
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:34556-34583
Submodular Order Functions and Assortment Optimization
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:34584-34614
Computationally Efficient PAC RL in POMDPs with Latent Determinism and Conditional Embeddings
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:34615-34641
From Adaptive Query Release to Machine Unlearning
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:34642-34667
Private Federated Learning with Autotuned Compression
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:34668-34708
The Monge Gap: A Regularizer to Learn All Transport Maps
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:34709-34733
Semi-Dual Unbalanced Quadratic Optimal Transport: fast statistical rates and convergent algorithm.
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:34734-34758
Random Grid Neural Processes for Parametric Partial Differential Equations
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:34759-34778
Delayed Feedback in Kernel Bandits
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:34779-34792
Synthetic Data, Real Errors: How (Not) to Publish and Use Synthetic Data
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:34793-34808
Trading-Off Payments and Accuracy in Online Classification with Paid Stochastic Experts
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:34809-34830
Causal Isotonic Calibration for Heterogeneous Treatment Effects
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:34831-34854
Accounting For Informative Sampling When Learning to Forecast Treatment Outcomes Over Time
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:34855-34874
Best Arm Identification in Multi-Agent Multi-Armed Bandits
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:34875-34907
Conditional Tree Matching for Inference-Time Adaptation of Tree Prediction Models
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:34908-34923
Optimal LP Rounding and Linear-Time Approximation Algorithms for Clustering Edge-Colored Hypergraphs
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:34924-34951
Fast $(1+\varepsilon)$-Approximation Algorithms for Binary Matrix Factorization
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:34952-34977
The Virtues of Laziness in Model-based RL: A Unified Objective and Algorithms
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:34978-35005
Learning the Right Layers a Data-Driven Layer-Aggregation Strategy for Semi-Supervised Learning on Multilayer Graphs
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:35006-35023
Multi-Environment Pretraining Enables Transfer to Action Limited Datasets
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:35024-35036
AbODE: Ab initio antibody design using conjoined ODEs
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:35037-35050
TabLeak: Tabular Data Leakage in Federated Learning
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:35051-35083
Low-Variance Gradient Estimation in Unrolled Computation Graphs with ES-Single
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:35084-35119
Arithmetic Sampling: Parallel Diverse Decoding for Large Language Models
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:35120-35136
Eventual Discounting Temporal Logic Counterfactual Experience Replay
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:35137-35150
Transformers Learn In-Context by Gradient Descent
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:35151-35174
Topological Singularity Detection at Multiple Scales
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:35175-35197
Improving l1-Certified Robustness via Randomized Smoothing by Leveraging Box Constraints
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:35198-35222
Vector Quantized Wasserstein Auto-Encoder
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:35223-35242
Competitive Gradient Optimization
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:35243-35276
On Provable Copyright Protection for Generative Models
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:35277-35299
Leveraging Offline Data in Online Reinforcement Learning
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:35300-35338
Fast Private Kernel Density Estimation via Locality Sensitive Quantization
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:35339-35367
Investigating the Role of Model-Based Learning in Exploration and Transfer
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:35368-35383
UPSCALE: Unconstrained Channel Pruning
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:35384-35412
Poisoning Language Models During Instruction Tuning
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:35413-35425
SeMAIL: Eliminating Distractors in Visual Imitation via Separated Models
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:35426-35443
Multiplier Bootstrap-based Exploration
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:35444-35490
Bandit Multi-linear DR-Submodular Maximization and Its Applications on Adversarial Submodular Bandits
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:35491-35524
Tight Regret Bounds for Single-pass Streaming Multi-armed Bandits
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:35525-35547
Improved Active Multi-Task Representation Learning via Lasso
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:35548-35578
Tilted Sparse Additive Models
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:35579-35604
From Hypergraph Energy Functions to Hypergraph Neural Networks
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:35605-35623
A Closer Look at Self-Supervised Lightweight Vision Transformers
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:35624-35641
PreNAS: Preferred One-Shot Learning Towards Efficient Neural Architecture Search
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:35642-35654
Adversarial Policies Beat Superhuman Go AIs
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:35655-35739
On Regularization and Inference with Label Constraints
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:35740-35762
Policy Gradient in Robust MDPs with Global Convergence Guarantee
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:35763-35797
Adaptive Smoothing Gradient Learning for Spiking Neural Networks
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:35798-35816
CircuitNet: A Generic Neural Network to Realize Universal Circuit Motif Modeling
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:35817-35835
Generalized Polyak Step Size for First Order Optimization with Momentum
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:35836-35863
Near-Minimax-Optimal Risk-Sensitive Reinforcement Learning with CVaR
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:35864-35907
FedHPO-Bench: A Benchmark Suite for Federated Hyperparameter Optimization
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:35908-35948
A/B Testing in Network Data with Covariate-Adaptive Randomization
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:35949-35969
Learning Belief Representations for Partially Observable Deep RL
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:35970-35988
Warm-Start Actor-Critic: From Approximation Error to Sub-optimality Gap
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:35989-36019
Slot-VAE: Object-Centric Scene Generation with Slot Attention
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:36020-36035
DIVISION: Memory Efficient Training via Dual Activation Precision
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:36036-36057
CocktailSGD: Fine-tuning Foundation Models over 500Mbps Networks
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:36058-36076
Magneto: A Foundation Transformer
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:36077-36092
Direct Parameterization of Lipschitz-Bounded Deep Networks
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:36093-36110
Tighter Information-Theoretic Generalization Bounds from Supersamples
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:36111-36137
NP-SemiSeg: When Neural Processes meet Semi-Supervised Semantic Segmentation
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:36138-36156
GC-Flow: A Graph-Based Flow Network for Effective Clustering
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:36157-36173
Curriculum Co-disentangled Representation Learning across Multiple Environments for Social Recommendation
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:36174-36192
Data Efficient Neural Scaling Law via Model Reusing
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:36193-36204
Deep Temporal Sets with Evidential Reinforced Attentions for Unique Behavioral Pattern Discovery
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:36205-36223
Active Learning based Structural Inference
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:36224-36245
Better Diffusion Models Further Improve Adversarial Training
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:36246-36263
Polarity Is All You Need to Learn and Transfer Faster
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:36264-36284
Projected Tensor Power Method for Hypergraph Community Recovery
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:36285-36307
Estimating Possible Causal Effects with Latent Variables via Adjustment
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:36308-36335
InfoDiffusion: Representation Learning Using Information Maximizing Diffusion Models
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:36336-36354
A Robust Test for the Stationarity Assumption in Sequential Decision Making
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:36355-36379
GEAR: A GPU-Centric Experience Replay System for Large Reinforcement Learning Models
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:36380-36390
Effective and Efficient Structural Inference with Reservoir Computing
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:36391-36410
Optimal Goal-Reaching Reinforcement Learning via Quasimetric Learning
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:36411-36430
Model-Free Robust Average-Reward Reinforcement Learning
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:36431-36469
Live in the Moment: Learning Dynamics Model Adapted to Evolving Policy
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:36470-36493
Learning to Bid in Repeated First-Price Auctions with Budgets
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:36494-36513
Network Effects in Performative Prediction Games
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:36514-36540
Robustly Learning a Single Neuron via Sharpness
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:36541-36577
DualHSIC: HSIC-Bottleneck and Alignment for Continual Learning
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:36578-36592
Enforcing Hard Constraints with Soft Barriers: Safe Reinforcement Learning in Unknown Stochastic Environments
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:36593-36604
LinSATNet: The Positive Linear Satisfiability Neural Networks
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:36605-36625
Offline Meta Reinforcement Learning with In-Distribution Online Adaptation
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:36626-36669
Reachability-Aware Laplacian Representation in Reinforcement Learning
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:36670-36693
PPG Reloaded: An Empirical Study on What Matters in Phasic Policy Gradient
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:36694-36713
On Heterogeneous Treatment Effects in Heterogeneous Causal Graphs
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:36714-36747
Nonparametric Extensions of Randomized Response for Private Confidence Sets
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:36748-36789
Global optimality for Euclidean CCCP under Riemannian convexity
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:36790-36803
A Universal Unbiased Method for Classification from Aggregate Observations
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:36804-36820
NTK-approximating MLP Fusion for Efficient Language Model Fine-tuning
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:36821-36838
Boosting Graph Contrastive Learning via Graph Contrastive Saliency
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:36839-36855
Set-membership Belief State-based Reinforcement Learning for POMDPs
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:36856-36867
Mitigating Memorization of Noisy Labels by Clipping the Model Prediction
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:36868-36886
Graphically Structured Diffusion Models
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:36887-36909
Expectation-Complete Graph Representations with Homomorphisms
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:36910-36925
A Conditional Normalizing Flow for Accelerated Multi-Coil MR Imaging
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:36926-36939
Optimizing Mode Connectivity for Class Incremental Learning
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:36940-36957
Towards Learning Geometric Eigen-Lengths Crucial for Fitting Tasks
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:36958-36977
Open-VCLIP: Transforming CLIP to an Open-vocabulary Video Model via Interpolated Weight Optimization
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:36978-36989
Fully-Adaptive Composition in Differential Privacy
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:36990-37007
Scalable Set Encoding with Universal Mini-Batch Consistency and Unbiased Full Set Gradient Approximation
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:37008-37041
Flexible Phase Dynamics for Bio-Plausible Contrastive Learning
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:37042-37065
Approximate Stein Classes for Truncated Density Estimation
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:37066-37090
Theoretical Behavior of XAI Methods in the Presence of Suppressor Variables
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:37091-37107
Marginalization is not Marginal: No Bad VAE Local Minima when Learning Optimal Sparse Representations
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:37108-37132
Uncertainty Estimation for Molecules: Desiderata and Methods
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:37133-37156
The Blessing of Heterogeneity in Federated Q-Learning: Linear Speedup and Beyond
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:37157-37216
Learning Deep Time-index Models for Time Series Forecasting
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:37217-37237
Sharper Bounds for $\ell_p$ Sensitivity Sampling
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:37238-37272
Two Losses Are Better Than One: Faster Optimization Using a Cheaper Proxy
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:37273-37292
SEGA: Structural Entropy Guided Anchor View for Graph Contrastive Learning
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:37293-37312
Causal Proxy Models for Concept-based Model Explanations
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:37313-37334
Effective Neural Topic Modeling with Embedding Clustering Regularization
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:37335-37357
Adaptive Compositional Continual Meta-Learning
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:37358-37378
Anchor Sampling for Federated Learning with Partial Client Participation
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:37379-37416
Solving High-Dimensional PDEs with Latent Spectral Models
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:37417-37438
A Law of Robustness beyond Isoperimetry
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:37439-37455
Uncovering Adversarial Risks of Test-Time Adaptation
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:37456-37495
Stable Estimation of Heterogeneous Treatment Effects
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:37496-37510
Rethinking Explaining Graph Neural Networks via Non-parametric Subgraph Matching
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:37511-37523
Understanding Int4 Quantization for Language Models: Latency Speedup, Composability, and Failure Cases
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:37524-37539
Towards Understanding Generalization of Macro-AUC in Multi-label Learning
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:37540-37570
Quantifying the Knowledge in GNNs for Reliable Distillation into MLPs
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:37571-37581
Delay-agnostic Asynchronous Coordinate Update Algorithm
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:37582-37606
Masked Trajectory Models for Prediction, Representation, and Control
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:37607-37623
Disentangled Multi-Fidelity Deep Bayesian Active Learning
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:37624-37634
Tight Data Access Bounds for Private Top-$k$ Selection
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:37635-37655
The Implicit Regularization of Dynamical Stability in Stochastic Gradient Descent
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:37656-37684
Distributional Offline Policy Evaluation with Predictive Error Guarantees
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:37685-37712
$\pi$-Tuning: Transferring Multimodal Foundation Models with Optimal Multi-task Interpolation
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:37713-37727
Learning Functional Distributions with Private Labels
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:37728-37744
QuantumDARTS: Differentiable Quantum Architecture Search for Variational Quantum Algorithms
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:37745-37764
Discover and Cure: Concept-aware Mitigation of Spurious Correlation
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:37765-37786
On the Training Instability of Shuffling SGD with Batch Normalization
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:37787-37845
dugMatting: Decomposed-Uncertainty-Guided Matting
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:37846-37859
Personalized Federated Learning under Mixture of Distributions
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:37860-37879
Differentially Private Episodic Reinforcement Learning with Heavy-tailed Rewards
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:37880-37918
Finite-Sample Analysis of Learning High-Dimensional Single ReLU Neuron
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:37919-37951
Understanding Backdoor Attacks through the Adaptability Hypothesis
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:37952-37976
Fair and Optimal Classification via Post-Processing
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:37977-38012
UMD: Unsupervised Model Detection for X2X Backdoor Attacks
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:38013-38038
Random Shuffle Transformer for Image Restoration
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:38039-38058
Communication-Efficient Federated Hypergradient Computation via Aggregated Iterative Differentiation
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:38059-38086
SmoothQuant: Accurate and Efficient Post-Training Quantization for Large Language Models
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:38087-38099
On the Forward Invariance of Neural ODEs
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:38100-38124
COMCAT: Towards Efficient Compression and Customization of Attention-Based Vision Models
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:38125-38136
Improving Bi-level Optimization Based Methods with Inspiration from Humans’ Classroom Study Techniques
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:38137-38186
Future-conditioned Unsupervised Pretraining for Decision Transformer
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:38187-38203
DeSRA: Detect and Delete the Artifacts of GAN-based Real-World Super-Resolution Models
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:38204-38226
Semiparametrically Efficient Off-Policy Evaluation in Linear Markov Decision Processes
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:38227-38257
A Critical View of Vision-Based Long-Term Dynamics Prediction Under Environment Misalignment
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:38258-38271
Controlling Type Confounding in Ad Hoc Teamwork with Instance-wise Teammate Feedback Rectification
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:38272-38285
Universal Morphology Control via Contextual Modulation
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:38286-38300
Relevant Walk Search for Explaining Graph Neural Networks
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:38301-38324
Why do Nearest Neighbor Language Models Work?
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:38325-38341
MixFlows: principled variational inference via mixed flows
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:38342-38376
Bit Allocation using Optimization
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:38377-38399
Regret Bounds for Markov Decision Processes with Recursive Optimized Certainty Equivalents
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:38400-38427
Probabilistic Categorical Adversarial Attack and Adversarial Training
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:38428-38442
Hierarchical Neural Coding for Controllable CAD Model Generation
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:38443-38461
Efficient Sequence Transduction by Jointly Predicting Tokens and Durations
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:38462-38484
Constrained Efficient Global Optimization of Expensive Black-box Functions
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:38485-38498
Pareto Regret Analyses in Multi-objective Multi-armed Bandit
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:38499-38517
Diverse and Faithful Knowledge-Grounded Dialogue Generation via Sequential Posterior Inference
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:38518-38534
Quantifying the Variability Collapse of Neural Networks
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:38535-38550
Progressive Purification for Instance-Dependent Partial Label Learning
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:38551-38565
PFGM++: Unlocking the Potential of Physics-Inspired Generative Models
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:38566-38591
Geometric Latent Diffusion Models for 3D Molecule Generation
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:38592-38610
The Power of Preconditioning in Overparameterized Low-Rank Matrix Sensing
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:38611-38654
Fascinating Supervisory Signals and Where to Find Them: Deep Anomaly Detection with Scale Learning
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:38655-38673
Competing for Shareable Arms in Multi-Player Multi-Armed Bandits
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:38674-38706
Sequential Predictive Conformal Inference for Time Series
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:38707-38727
mPLUG-2: A Modularized Multi-modal Foundation Model Across Text, Image and Video
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:38728-38748
ProtST: Multi-Modality Learning of Protein Sequences and Biomedical Texts
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:38749-38767
Bayesian Design Principles for Frequentist Sequential Learning
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:38768-38800
SLAMB: Accelerated Large Batch Training with Sparse Communication
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:38801-38825
Do Not Train It: A Linear Neural Architecture Search of Graph Neural Networks
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:38826-38847
An Instrumental Variable Approach to Confounded Off-Policy Evaluation
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:38848-38880
Near-Optimal Quantum Coreset Construction Algorithms for Clustering
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:38881-38912
A Study on Transformer Configuration and Training Objective
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:38913-38925
LazyGNN: Large-Scale Graph Neural Networks via Lazy Propagation
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:38926-38937
Which Features are Learnt by Contrastive Learning? On the Role of Simplicity Bias in Class Collapse and Feature Suppression
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:38938-38970
Adaptive Computation with Elastic Input Sequence
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:38971-38988
Q-learning Decision Transformer: Leveraging Dynamic Programming for Conditional Sequence Modelling in Offline RL
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:38989-39007
Quantum Ridgelet Transform: Winning Lottery Ticket of Neural Networks with Quantum Computation
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:39008-39034
Compressed Decentralized Proximal Stochastic Gradient Method for Nonconvex Composite Problems with Heterogeneous Data
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:39035-39061
Temporally Consistent Transformers for Video Generation
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:39062-39098
Distortion and Uncertainty Aware Loss for Panoramic Depth Completion
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:39099-39109
Self-Interpretable Time Series Prediction with Counterfactual Explanations
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:39110-39125
Quantum 3D Graph Learning with Applications to Molecule Embedding
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:39126-39137
Fast Rates in Time-Varying Strongly Monotone Games
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:39138-39164
Proper Scoring Rules for Survival Analysis
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:39165-39182
Behavior Contrastive Learning for Unsupervised Skill Discovery
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:39183-39204
Nested Elimination: A Simple Algorithm for Best-Item Identification From Choice-Based Feedback
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:39205-39233
Towards Better Graph Representation Learning with Parameterized Decomposition & Filtering
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:39234-39251
Weighted Flow Diffusion for Local Graph Clustering with Node Attributes: an Algorithm and Statistical Guarantees
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:39252-39276
Chemically Transferable Generative Backmapping of Coarse-Grained Proteins
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:39277-39298
Data Poisoning Attacks Against Multimodal Encoders
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:39299-39313
Towards Sustainable Learning: Coresets for Data-efficient Deep Learning
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:39314-39330
Improving Adversarial Robustness by Putting More Regularizations on Less Robust Samples
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:39331-39348
Improving Adversarial Robustness of Deep Equilibrium Models with Explicit Regulations Along the Neural Dynamics
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:39349-39364
Mitigating Spurious Correlations in Multi-modal Models during Fine-tuning
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:39365-39379
A theory of representation learning gives a deep generalisation of kernel methods
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:39380-39415
Efficient Algorithms for Exact Graph Matching on Correlated Stochastic Block Models with Constant Correlation
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:39416-39452
Are Neurons Actually Collapsed? On the Fine-Grained Structure in Neural Representations
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:39453-39487
Generative Adversarial Symmetry Discovery
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:39488-39508
Boosting Offline Reinforcement Learning with Action Preference Query
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:39509-39523
Towards Controlled Data Augmentations for Active Learning
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:39524-39542
What is Essential for Unseen Goal Generalization of Offline Goal-conditioned RL?
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:39543-39571
Neural Prediction Errors enable Analogical Visual Reasoning in Human Standard Intelligence Tests
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:39572-39583
Change is Hard: A Closer Look at Subpopulation Shift
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:39584-39622
Continual Task Allocation in Meta-Policy Network via Sparse Prompting
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:39623-39638
Hyperbolic Representation Learning: Revisiting and Advancing
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:39639-39659
Which is Better for Learning with Noisy Labels: The Semi-supervised Method or Modeling Label Noise?
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:39660-39673
How Bad is Top-$K$ Recommendation under Competing Content Creators?
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:39674-39701
MultiAdam: Parameter-wise Scale-invariant Optimizer for Multiscale Training of Physics-informed Neural Networks
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:39702-39721
Policy Mirror Ascent for Efficient and Independent Learning in Mean Field Games
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:39722-39754
Retrieval-Augmented Multimodal Language Modeling
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:39755-39769
On the Power of Pre-training for Generalization in RL: Provable Benefits and Hardness
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:39770-39800
Personalized Federated Learning with Inferred Collaboration Graphs
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:39801-39817
Compositional Exemplars for In-context Learning
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:39818-39833
Corruption-Robust Algorithms with Uncertainty Weighting for Nonlinear Contextual Bandits and Markov Decision Processes
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:39834-39863
GNN&GBDT-Guided Fast Optimizing Framework for Large-scale Integer Programming
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:39864-39878
FedDisco: Federated Learning with Discrepancy-Aware Collaboration
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:39879-39902
Towards Quantum Machine Learning for Constrained Combinatorial Optimization: a Quantum QAP Solver
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:39903-39912
Temporal Label Smoothing for Early Event Prediction
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:39913-39938
From Temporal to Contemporaneous Iterative Causal Discovery in the Presence of Latent Confounders
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:39939-39950
Doubly Adversarial Federated Bandits
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:39951-39967
Online Prototype Alignment for Few-shot Policy Transfer
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:39968-39983
MonoFlow: Rethinking Divergence GANs via the Perspective of Wasserstein Gradient Flows
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:39984-40000
SE(3) diffusion model with application to protein backbone generation
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:40001-40039
CoCo: A Coupled Contrastive Framework for Unsupervised Domain Adaptive Graph Classification
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:40040-40053
Adaptive Estimation of Graphical Models under Total Positivity
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:40054-40074
Improving Visual Prompt Tuning for Self-supervised Vision Transformers
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:40075-40092
End-to-End Multi-Object Detection with a Regularized Mixture Model
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:40093-40110
EM-Network: Oracle Guided Self-distillation for Sequence Learning
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:40111-40128
Continual Learners are Incremental Model Generalizers
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:40129-40146
An Investigation into Pre-Training Object-Centric Representations for Reinforcement Learning
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:40147-40174
Graph Generative Model for Benchmarking Graph Neural Networks
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:40175-40198
Analyzing Convergence in Quantum Neural Networks: Deviations from Neural Tangent Kernels
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:40199-40224
Entropy-driven Unsupervised Keypoint Representation Learning in Videos
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:40225-40253
The Benefits of Model-Based Generalization in Reinforcement Learning
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:40254-40276
COLA: Orchestrating Error Coding and Learning for Robust Neural Network Inference Against Hardware Defects
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:40277-40289
Delving into Noisy Label Detection with Clean Data
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:40290-40305
Bag of Tricks for Training Data Extraction from Language Models
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:40306-40320
Discover-Then-Rank Unlabeled Support Vectors in the Dual Space for Multi-Class Active Learning
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:40321-40338
Long-Term Rhythmic Video Soundtracker
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:40339-40353
Adversarial Parameter Attack on Deep Neural Networks
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:40354-40372
CodeIPPrompt: Intellectual Property Infringement Assessment of Code Language Models
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:40373-40389
SeedGNN: Graph Neural Network for Supervised Seeded Graph Matching
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:40390-40411
Efficient and Equivariant Graph Networks for Predicting Quantum Hamiltonian
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:40412-40424
On the Global Convergence of Risk-Averse Policy Gradient Methods with Expected Conditional Risk Measures
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:40425-40451
Actor-Critic Alignment for Offline-to-Online Reinforcement Learning
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:40452-40474
Master-ASR: Achieving Multilingual Scalability and Low-Resource Adaptation in ASR with Modular Learning
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:40475-40487
Coordinate Descent Methods for Fractional Minimization
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:40488-40518
On the Power of Foundation Models
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:40519-40530
Automatic Intrinsic Reward Shaping for Exploration in Deep Reinforcement Learning
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:40531-40554
Traversing Between Modes in Function Space for Fast Ensembling
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:40555-40577
Conformal Prediction with Missing Values
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:40578-40604
KDEformer: Accelerating Transformers via Kernel Density Estimation
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:40605-40623
Bayesian Estimation of Differential Privacy
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:40624-40636
When is Realizability Sufficient for Off-Policy Reinforcement Learning?
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:40637-40668
On Distribution Dependent Sub-Logarithmic Query Time of Learned Indexing
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:40669-40680
Sequential Counterfactual Risk Minimization
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:40681-40706
LookupFFN: Making Transformers Compute-lite for CPU inference
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:40707-40718
Attribute-Efficient PAC Learning of Low-Degree Polynomial Threshold Functions with Nasty Noise
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:40719-40748
Generative Graph Dictionary Learning
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:40749-40769
Stabilizing Transformer Training by Preventing Attention Entropy Collapse
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:40770-40803
Offline Learning in Markov Games with General Function Approximation
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:40804-40829
Learning useful representations for shifting tasks and distributions
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:40830-40850
Nonparametric Iterative Machine Teaching
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:40851-40870
Matrix Estimation for Individual Fairness
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:40871-40887
Graph Contrastive Backdoor Attacks
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:40888-40910
Effective Minkowski Dimension of Deep Nonparametric Regression: Function Approximation and Statistical Theories
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:40911-40931
Tractable Control for Autoregressive Language Generation
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:40932-40945
CataBEEM: Integrating Latent Interaction Categories in Node-wise Community Detection Models for Network Data
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:40946-40975
Rethink DARTS Search Space and Renovate a New Benchmark
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:40976-40995
Team Belief DAG: Generalizing the Sequence Form to Team Games for Fast Computation of Correlated Team Max-Min Equilibria via Regret Minimization
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:40996-41018
A Complete Expressiveness Hierarchy for Subgraph GNNs via Subgraph Weisfeiler-Lehman Tests
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:41019-41077
Crafting Training Degradation Distribution for the Accuracy-Generalization Trade-off in Real-World Super-Resolution
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:41078-41091
Prompting Large Language Model for Machine Translation: A Case Study
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:41092-41110
On the Interplay Between Misspecification and Sub-optimality Gap in Linear Contextual Bandits
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:41111-41132
When Sparsity Meets Contrastive Models: Less Graph Data Can Bring Better Class-Balanced Representations
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:41133-41150
Spatial-Temporal Graph Learning with Adversarial Contrastive Adaptation
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:41151-41163
Towards Coherent Image Inpainting Using Denoising Diffusion Implicit Models
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:41164-41193
CAB: Comprehensive Attention Benchmarking on Long Sequence Modeling
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:41194-41218
Adaptive Barrier Smoothing for First-Order Policy Gradient with Contact Dynamics
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:41219-41243
One-Step Estimator for Permuted Sparse Recovery
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:41244-41267
Quantum Lower Bounds for Finding Stationary Points of Nonconvex Functions
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:41268-41299
Improving Medical Predictions by Irregular Multimodal Electronic Health Records Modeling
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:41300-41313
FedCR: Personalized Federated Learning Based on Across-Client Common Representation with Conditional Mutual Information Regularization
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:41314-41330
On the Optimality of Misspecified Kernel Ridge Regression
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:41331-41353
Fed-CBS: A Heterogeneity-Aware Client Sampling Mechanism for Federated Learning via Class-Imbalance Reduction
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:41354-41381
Learning Subpocket Prototypes for Generalizable Structure-based Drug Design
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:41382-41398
No One Idles: Efficient Heterogeneous Federated Learning with Parallel Edge and Server Computation
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:41399-41413
The Wisdom of Hindsight Makes Language Models Better Instruction Followers
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:41414-41428
Detecting Adversarial Data by Probing Multiple Perturbations Using Expected Perturbation Score
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:41429-41451
On Enhancing Expressive Power via Compositions of Single Fixed-Size ReLU Network
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:41452-41487
Bi-directional Masks for Efficient N:M Sparse Training
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:41488-41497
Towards Unbiased Training in Federated Open-world Semi-supervised Learning
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:41498-41509
Interactive Object Placement with Reinforcement Learning
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:41510-41522
Optimal Shrinkage for Distributed Second-Order Optimization
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:41523-41549
"Why did the Model Fail?": Attributing Model Performance Changes to Distribution Shifts
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:41550-41578
Learning Regions of Interest for Bayesian Optimization with Adaptive Level-Set Estimation
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:41579-41595
A Category-theoretical Meta-analysis of Definitions of Disentanglement
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:41596-41612
On the Convergence of SARSA with Linear Function Approximation
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:41613-41646
AdaNPC: Exploring Non-Parametric Classifier for Test-Time Adaptation
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:41647-41676
On the Generalization of Multi-modal Contrastive Learning
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:41677-41693
ConCerNet: A Contrastive Learning Based Framework for Automated Conservation Law Discovery and Trustworthy Dynamical System Prediction
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:41694-41714
Towards Trustworthy Explanation: On Causal Rationalization
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:41715-41736
Demystifying Uneven Vulnerability of Link Stealing Attacks against Graph Neural Networks
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:41737-41752
Provable Dynamic Fusion for Low-Quality Multimodal Data
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:41753-41769
ReDi: Efficient Learning-Free Diffusion Inference via Trajectory Retrieval
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:41770-41785
Nearly Optimal Competitive Ratio for Online Allocation Problems with Two-sided Resource Constraints and Finite Requests
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:41786-41818
Do You Remember? Overcoming Catastrophic Forgetting for Fake Audio Detection
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:41819-41831
Coder Reviewer Reranking for Code Generation
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:41832-41846
DP-Fast MH: Private, Fast, and Accurate Metropolis-Hastings for Large-Scale Bayesian Inference
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:41847-41860
Nearly-tight Bounds for Deep Kernel Learning
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:41861-41879
OpenFE: Automated Feature Generation with Expert-level Performance
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:41880-41901
Optimal Horizon-Free Reward-Free Exploration for Linear Mixture MDPs
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:41902-41930
Unlocking Slot Attention by Changing Optimal Transport Costs
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:41931-41951
Towards a Persistence Diagram that is Robust to Noise and Varied Densities
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:41952-41972
Robust Situational Reinforcement Learning in Face of Context Disturbances
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:41973-41989
Patch-level Contrastive Learning via Positional Query for Visual Pre-training
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:41990-41999
Men Also Do Laundry: Multi-Attribute Bias Amplification
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:42000-42017
Rockmate: an Efficient, Fast, Automatic and Generic Tool for Re-materialization in PyTorch
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:42018-42045
Revisiting Structured Variational Autoencoders
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:42046-42057
On Pitfalls of Test-Time Adaptation
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:42058-42080
Addressing Budget Allocation and Revenue Allocation in Data Market Environments Using an Adaptive Sampling Algorithm
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:42081-42097
X-Paste: Revisiting Scalable Copy-Paste for Instance Segmentation using CLIP and StableDiffusion
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:42098-42109
Revisiting Simple Regret: Fast Rates for Returning a Good Arm
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:42110-42158
Transformed Distribution Matching for Missing Value Imputation
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:42159-42186
Protecting Language Generation Models via Invisible Watermarking
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:42187-42199
Local Optimization Achieves Global Optimality in Multi-Agent Reinforcement Learning
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:42200-42226
Simplified Temporal Consistency Reinforcement Learning
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:42227-42246
RLEG: Vision-Language Representation Learning with Diffusion-based Embedding Generation
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:42247-42258
Optimal Online Generalized Linear Regression with Stochastic Noise and Its Application to Heteroscedastic Bandits
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:42259-42279
Does Continual Learning Equally Forget All Parameters?
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:42280-42303
Online Learning in Stackelberg Games with an Omniscient Follower
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:42304-42316
Structure-informed Language Models Are Protein Designers
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:42317-42338
Semi-Supervised Offline Reinforcement Learning with Action-Free Trajectories
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:42339-42362
Improved Techniques for Maximum Likelihood Estimation for Diffusion ODEs
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:42363-42389
Fast Sampling of Diffusion Models via Operator Learning
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:42390-42402
Outline, Then Details: Syntactically Guided Coarse-To-Fine Code Generation
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:42403-42419
Revisiting Discriminative vs. Generative Classifiers: Theory and Implications
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:42420-42477
Evidential Interactive Learning for Medical Image Captioning
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:42478-42491
Finding the Missing-half: Graph Complementary Learning for Homophily-prone and Heterophily-prone Graphs
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:42492-42505
Multi-agent Online Scheduling: MMS Allocations for Indivisible Items
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:42506-42516
Eliminating Adversarial Noise via Information Discard and Robust Representation Restoration
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:42517-42530
Brainformers: Trading Simplicity for Efficiency
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:42531-42542
Implicit Regularization Leads to Benign Overfitting for Sparse Linear Regression
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:42543-42573
ODS: Test-Time Adaptation in the Presence of Open-World Data Shift
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:42574-42588
Fourmer: An Efficient Global Modeling Paradigm for Image Restoration
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:42589-42601
Controlled Text Generation with Natural Language Instructions
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:42602-42613
NNSplitter: An Active Defense Solution for DNN Model via Automated Weight Obfuscation
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:42614-42624
Deep Latent State Space Models for Time-Series Generation
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:42625-42643
SlotGAT: Slot-based Message Passing for Heterogeneous Graphs
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:42644-42657
Fast Online Node Labeling for Very Large Graphs
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:42658-42697
Horizon-Free and Variance-Dependent Reinforcement Learning for Latent Markov Decision Processes
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:42698-42723
Phase-aware Adversarial Defense for Improving Adversarial Robustness
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:42724-42741
From Relational Pooling to Subgraph GNNs: A Universal Framework for More Expressive Graph Neural Networks
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:42742-42768
Towards Omni-generalizable Neural Methods for Vehicle Routing Problems
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:42769-42789
A Three-regime Model of Network Pruning
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:42790-42809
Learning to Decouple Complex Systems
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:42810-42828
ESC: Exploration with Soft Commonsense Constraints for Zero-shot Object Navigation
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:42829-42842
On Strengthening and Defending Graph Reconstruction Attack with Markov Chain Approximation
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:42843-42877
Sharp Variance-Dependent Bounds in Reinforcement Learning: Best of Both Worlds in Stochastic and Deterministic Environments
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:42878-42914
Learning Unforeseen Robustness from Out-of-distribution Data Using Equivariant Domain Translator
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:42915-42937
Markovian Gaussian Process Variational Autoencoders
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:42938-42961
Mixture Proportion Estimation Beyond Irreducibility
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:42962-42982
Exploring Model Dynamics for Accumulative Poisoning Discovery
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:42983-43004
Decentralized SGD and Average-direction SAM are Asymptotically Equivalent
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:43005-43036
Principled Reinforcement Learning with Human Feedback from Pairwise or K-wise Comparisons
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:43037-43067
Unleashing Mask: Explore the Intrinsic Out-of-Distribution Detection Capability
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:43068-43104
Benign Overfitting in Deep Neural Networks under Lazy Training
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:43105-43128
Interpolation for Robust Learning: Data Augmentation on Wasserstein Geodesics
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:43129-43157
LeadFL: Client Self-Defense against Model Poisoning in Federated Learning
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:43158-43180
XTab: Cross-table Pretraining for Tabular Transformers
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:43181-43204
Provable Multi-instance Deep AUC Maximization with Stochastic Pooling
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:43205-43227
Surrogate Model Extension (SME): A Fast and Accurate Weight Update Attack on Federated Learning
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:43228-43257
Weak Proxies are Sufficient and Preferable for Fairness with Missing Sensitive Attributes
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:43258-43288
Label Distributionally Robust Losses for Multi-class Classification: Consistency, Robustness and Adaptivity
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:43289-43325
Likelihood Adjusted Semidefinite Programs for Clustering Heterogeneous Data
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:43326-43346
Are Random Decompositions all we need in High Dimensional Bayesian Optimisation?
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:43347-43368
Revisiting Bellman Errors for Offline Model Selection
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:43369-43406
spred: Solving L1 Penalty with SGD
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:43407-43422
The Benefits of Mixup for Feature Learning
; Proceedings of the 40th International Conference on Machine Learning, PMLR 202:43423-43479
subscribe via RSS