International Conference on Machine Learning (ICML) - 2022

Conference Proceedings:

Key: PC - Pseudocode, OSC - Open Source Code, OSD - Open Datasets, DS - Dataset Splits, HS - Hardware Specification, SD - Software Dependencies, ES - Experiment Setup

$p$-Laplacian Based Graph Neural Networks 4
(Non-)Convergence Results for Predictive Coding Networks 0
3D Infomax improves GNNs for Molecular Property Prediction 5
3DLinker: An E(3) Equivariant Variational Autoencoder for Molecular Linker Design 4
3PC: Three Point Compressors for Communication-Efficient Distributed Training and a Better Theory for Lazy Aggregation 6
A Branch and Bound Framework for Stronger Adversarial Attacks of ReLU Networks 4
A Closer Look at Smoothness in Domain Adversarial Training 6
A Completely Tuning-Free and Robust Approach to Sparse Precision Matrix Estimation 4
A Consistent and Efficient Evaluation Strategy for Attribution Methods 4
A Context-Integrated Transformer-Based Neural Network for Auction Design 3
A Convergence Theory for SVGD in the Population Limit under Talagrand’s Inequality T1 1
A Convergent and Dimension-Independent Min-Max Optimization Algorithm 4
A Deep Learning Approach for the Segmentation of Electroencephalography Data in Eye Tracking Applications 5
A Difference Standardization Method for Mutual Transfer Learning 5
A Differential Entropy Estimator for Training Neural Networks 6
A Dynamical System Perspective for Lipschitz Neural Networks 4
A Framework for Learning to Request Rich and Contextually Useful Information from Humans 4
A Functional Information Perspective on Model Interpretation 3
A General Recipe for Likelihood-free Bayesian Optimization 3
A Hierarchical Bayesian Approach to Inverse Reinforcement Learning with Symbolic Reward Machines 3
A Hierarchical Transitive-Aligned Graph Kernel for Un-attributed Graphs 3
A Joint Exponential Mechanism For Differentially Private Top-$k$ 4
A Langevin-like Sampler for Discrete Distributions 5
A Marriage between Adversarial Team Games and 2-player Games: Enabling Abstractions, No-regret Learning, and Subgame Solving 4
A Minimax Learning Approach to Off-Policy Evaluation in Confounded Partially Observable Markov Decision Processes 3
A Model-Agnostic Randomized Learning Framework based on Random Hypothesis Subspace Sampling 4
A Modern Self-Referential Weight Matrix That Learns to Modify Itself 5
A Multi-objective / Multi-task Learning Framework Induced by Pareto Stationarity 2
A Natural Actor-Critic Framework for Zero-Sum Markov Games 3
A Neural Tangent Kernel Perspective of GANs 5
A New Perspective on the Effects of Spectrum in Graph Neural Networks 4
A Parametric Class of Approximate Gradient Updates for Policy Optimization 2
A Psychological Theory of Explainability 3
A Random Matrix Analysis of Data Stream Clustering: Coping With Limited Memory Resources 3
A Reduction from Linear Contextual Bandits Lower Bounds to Estimations Lower Bounds 0
A Regret Minimization Approach to Multi-Agent Control 2
A Resilient Distributed Boosting Algorithm 1
A Rigorous Study of Integrated Gradients Method and Extensions to Internal Neuron Attributions 2
A Self-Play Posterior Sampling Algorithm for Zero-Sum Markov Games 1
A Simple Guard for Learned Optimizers 6
A Simple Reward-free Approach to Constrained Reinforcement Learning 1
A Simple Unified Framework for High Dimensional Bandit Problems 1
A Simple yet Universal Strategy for Online Convex Optimization 2
A Single-Loop Gradient Descent and Perturbed Ascent Algorithm for Nonconvex Functional Constrained Optimization 4
A State-Distribution Matching Approach to Non-Episodic Reinforcement Learning 3
A Statistical Manifold Framework for Point Cloud Data 4
A Stochastic Multi-Rate Control Framework For Modeling Distributed Optimization Algorithms 1
A Study of Face Obfuscation in ImageNet 5
A Study on the Ramanujan Graph Property of Winning Lottery Tickets 3
A Temporal-Difference Approach to Policy Gradient Estimation 4
A Theoretical Analysis on Independence-driven Importance Weighting for Covariate-shift Generalization 3
A Theoretical Comparison of Graph Neural Network Extensions 0
A Tighter Analysis of Spectral Clustering, and Beyond 3
A Tree-based Model Averaging Approach for Personalized Treatment Effect Estimation from Heterogeneous Data Sources 6
A Unified View on PAC-Bayes Bounds for Meta-Learning 2
A Unified Weight Initialization Paradigm for Tensorial Convolutional Neural Networks 5
A data-driven approach for learning to control computers 2
A deep convolutional neural network that is invariant to time rescaling 2
A new similarity measure for covariate shift with applications to nonparametric regression 0
A query-optimal algorithm for finding counterfactuals 1
A$^3$T: Alignment-Aware Acoustic and Text Pretraining for Speech Synthesis and Editing 4
AGNAS: Attention-Guided Micro and Macro-Architecture Search 6
ASAP.SGD: Instance-based Adaptiveness to Staleness in Asynchronous SGD 5
Accelerated Federated Learning with Decoupled Adaptive Optimization 4
Accelerated Gradient Methods for Geodesically Convex Optimization: Tractable Algorithms and Convergence Analysis 3
Accelerated, Optimal and Parallel: Some results on model-based stochastic optimization 1
Accelerating Bayesian Optimization for Biological Sequence Design with Denoising Autoencoders 6
Accelerating Shapley Explanation via Contributive Cooperator Selection 6
Accurate Quantization of Measures via Interacting Particle-based Optimization 3
Achieving Fairness at No Utility Cost via Data Reweighing with Influence 6
Achieving Minimax Rates in Pool-Based Batch Active Learning 1
Action-Sufficient State Representation Learning for Control with Structural Constraints 3
Active Learning on a Budget: Opposite Strategies Suit High and Low Budgets 4
Active Multi-Task Representation Learning 2
Active Nearest Neighbor Regression Through Delaunay Refinement 5
Active Sampling for Min-Max Fairness 5
Active fairness auditing 2
ActiveHedge: Hedge meets Active Learning 2
Actor-Critic based Improper Reinforcement Learning 2
AdAUC: End-to-end Adversarial AUC Optimization Against Long-tail Problems 3
AdaGrad Avoids Saddle Points 0
Adapting k-means Algorithms for Outliers 3
Adapting the Linearised Laplace Model Evidence for Modern Deep Learning 4
Adapting to Mixing Time in Stochastic Optimization with Markovian Data 2
Adaptive Accelerated (Extra-)Gradient Methods with Variance Reduction 3
Adaptive Best-of-Both-Worlds Algorithm for Heavy-Tailed Multi-Armed Bandits 1
Adaptive Conformal Predictions for Time Series 4
Adaptive Data Analysis with Correlated Observations 1
Adaptive Gaussian Process Change Point Detection 5
Adaptive Inertia: Disentangling the Effects of Adaptive Learning Rate and Momentum 5
Adaptive Model Design for Markov Decision Process 2
Adaptive Random Walk Gradient Descent for Decentralized Optimization 3
Adaptive Second Order Coresets for Data-efficient Machine Learning 5
Additive Gaussian Processes Revisited 5
Addressing Optimism Bias in Sequence Modeling for Reinforcement Learning 4
Adversarial Attack and Defense for Non-Parametric Two-Sample Tests 6
Adversarial Attacks on Gaussian Process Bandits 4
Adversarial Masking for Self-Supervised Learning 2
Adversarial Robustness against Multiple and Single $l_p$-Threat Models via Quick Fine-Tuning of Robust Classifiers 4
Adversarial Vulnerability of Randomized Ensembles 5
Adversarially Robust Models may not Transfer Better: Sufficient Conditions for Domain Transferability from the View of Regularization 2
Adversarially Trained Actor Critic for Offline Reinforcement Learning 4
Adversarially trained neural representations are already as robust as biological neural representations 2
Agnostic Learnability of Halfspaces via Logistic Loss 0
Algorithms for the Communication of Samples 2
Align-RUDDER: Learning From Few Demonstrations by Reward Redistribution 5
An Analytical Update Rule for General Policy Optimization 0
An Asymptotic Test for Conditional Independence using Analytic Kernel Embeddings 2
An Equivalence Between Data Poisoning and Byzantine Gradient Attacks 3
An Exact Symbolic Reduction of Linear Smart Predict+Optimize to Mixed Integer Linear Programming 4
An Initial Alignment between Neural Network and Target is Needed for Gradient Descent to Learn 2
An Intriguing Property of Geophysics Inversion 4
An iterative clustering algorithm for the Contextual Stochastic Block Model with optimality guarantees 4
Analysis of Stochastic Processes through Replay Buffers 1
Analyzing and Mitigating Interference in Neural Architecture Search 4
Anarchic Federated Learning 3
Antibody-Antigen Docking and Design via Hierarchical Structure Refinement 3
Anticorrelated Noise Injection for Improved Generalization 2
AnyMorph: Learning Transferable Polices By Inferring Agent Morphology 5
Anytime Information Cascade Popularity Prediction via Self-Exciting Processes 5
Approximate Bayesian Computation with Domain Expert in the Loop 3
Approximate Frank-Wolfe Algorithms over Graph-structured Support Sets 5
Approximately Equivariant Networks for Imperfectly Symmetric Dynamics 3
Architecture Agnostic Federated Learning for Neural Networks 4
Asking for Knowledge (AFK): Training RL Agents to Query External Knowledge Using Language 5
Asymptotically-Optimal Gaussian Bandits with Side Observations 1
Attentional Meta-learners for Few-shot Polythetic Classification 5
Augment with Care: Contrastive Learning for Combinatorial Problems 4
AutoIP: A United Framework to Integrate Physics into Gaussian Processes 3
AutoSNN: Towards Energy-Efficient Spiking Neural Networks 6
Auxiliary Learning with Joint Task and Data Scheduling 5
BAMDT: Bayesian Additive Semi-Multivariate Decision Trees for Nonparametric Regression 5
BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generation 4
BabelTower: Learning to Auto-parallelized Program Translation 4
Balancing Discriminability and Transferability for Source-Free Domain Adaptation 3
Balancing Sample Efficiency and Suboptimality in Inverse Reinforcement Learning 2
Batch Greenkhorn Algorithm for Entropic-Regularized Multimarginal Optimal Transport: Linear Rate of Convergence and Iteration Complexity 5
Batched Dueling Bandits 4
Bayesian Continuous-Time Tucker Decomposition 4
Bayesian Deep Embedding Topic Meta-Learner 4
Bayesian Imitation Learning for End-to-End Mobile Manipulation 1
Bayesian Learning with Information Gain Provably Bounds Risk for a Robust Adversarial Defense 3
Bayesian Model Selection, the Marginal Likelihood, and Generalization 3
Bayesian Nonparametric Learning for Point Processes with Spatial Homogeneity: A Spatial Analysis of NBA Shot Locations 4
Bayesian Nonparametrics for Offline Skill Discovery 4
Bayesian Optimization for Distributionally Robust Chance-constrained Problem 2
Bayesian Optimization under Stochastic Delayed Feedback 5
Be Like Water: Adaptive Floating Point for Machine Learning 2
Being Properly Improper 5
Benchmarking and Analyzing Point Cloud Classification under Corruptions 3
Benefits of Overparameterized Convolutional Residual Networks: Function Approximation under Smoothness Constraint 2
Beyond Images: Label Noise Transition Matrix Estimation for Tasks with Lower-Quality Features 3
Beyond Worst-Case Analysis in Stochastic Approximation: Moment Estimation Improves Instance Complexity 2
Biased Gradient Estimate with Drastic Variance Reduction for Meta Reinforcement Learning 2
Biological Sequence Design with GFlowNets 5
Bisimulation Makes Analogies in Goal-Conditioned Reinforcement Learning 2
Bit Prioritization in Variational Autoencoders via Progressive Coding 2
Bitwidth Heterogeneous Federated Learning with Progressive Weight Dequantization 3
Black-Box Tuning for Language-Model-as-a-Service 5
Blocks Assemble! Learning to Assemble with Large-Scale Structured Reinforcement Learning 3
Blurs Behave Like Ensembles: Spatial Smoothings to Improve Accuracy, Uncertainty, and Robustness 5
Boosting Graph Structure Learning with Dummy Nodes 7
Born-Infeld (BI) for AI: Energy-Conserving Descent (ECD) for Optimization 4
Bounding Training Data Reconstruction in Private (Deep) Learning 4
Bounding the Width of Neural Networks via Coupled Initialization A Worst Case Analysis 0
Branchformer: Parallel MLP-Attention Architectures to Capture Local and Global Context for Speech Recognition and Understanding 5
Branching Reinforcement Learning 2
Breaking Down Out-of-Distribution Detection: Many Methods Based on OOD Training Data Estimate a Combination of the Same Core Quantities 5
Breaking the $\sqrtT$ Barrier: Instance-Independent Logarithmic Regret in Stochastic Contextual Linear Bandits 1
Bregman Neural Networks 4
Bregman Power k-Means for Clustering Exponential Family Data 4
Bregman Proximal Langevin Monte Carlo via Bregman-Moreau Envelopes 4
Building Robust Ensembles via Margin Boosting 5
Burst-Dependent Plasticity and Dendritic Amplification Support Target-Based Learning and Hierarchical Imitation Learning 2
ButterflyFlow: Building Invertible Layers with Butterfly Matrices 3
Byzantine Machine Learning Made Easy By Resilient Averaging of Momentums 4
C*-algebra Net: A New Approach Generalizing Neural Network Parameters to C*-algebra 3
C-MinHash: Improving Minwise Hashing with Circulant Permutation 3
CITRIS: Causal Identifiability from Temporal Intervened Sequences 4
COAT: Measuring Object Compositionality in Emergent Representations 2
COLA: Consistent Learning with Opponent-Learning Awareness 1
Calibrated Learning to Defer with One-vs-All Classifiers 4
Calibrated and Sharp Uncertainties in Deep Learning via Density Estimation 4
Cascaded Gaps: Towards Logarithmic Regret for Risk-Sensitive Reinforcement Learning 1
Causal Conceptions of Fairness and their Consequences 3
Causal Dynamics Learning for Task-Independent State Abstraction 2
Causal Imitation Learning under Temporally Correlated Noise 4
Causal Inference Through the Structural Causal Marginal Problem 3
Causal Transformer for Estimating Counterfactual Outcomes 6
Causal structure-based root cause analysis of outliers 3
Centroid Approximation for Bootstrap: Improving Particle Quality at Inference 5
CerDEQ: Certifiable Deep Equilibrium Model 3
Certified Adversarial Robustness Under the Bounded Support Set 4
Certified Neural Network Watermarks with Randomized Smoothing 3
Certified Robustness Against Natural Language Attacks by Causal Intervention 5
Certifying Out-of-Domain Generalization for Blackbox Functions 2
Channel Importance Matters in Few-Shot Image Classification 3
Characterizing and Overcoming the Greedy Nature of Learning in Multi-modal Deep Neural Networks 5
Choosing Answers in Epsilon-Best-Answer Identification for Linear Bandits 4
Class-Imbalanced Semi-Supervised Learning with Adaptive Thresholding 5
Cliff Diving: Exploring Reward Surfaces in Reinforcement Learning Environments 3
Closed-Form Diffeomorphic Transformations for Time Series Alignment 5
Co-training Improves Prompt-based Learning for Large Language Models 6
Coarsening the Granularity: Towards Structurally Sparse Lottery Tickets 7
Coin Flipping Neural Networks 3
Collaboration of Experts: Achieving 80% Top-1 Accuracy on ImageNet with 100M FLOPs 5
Combining Diverse Feature Priors 6
Communicating via Markov Decision Processes 5
Communication-Efficient Adaptive Federated Learning 3
Communication-efficient Distributed Learning for Large Batch Optimization 4
Composing Partial Differential Equations with Physics-Aware Neural Networks 4
Comprehensive Analysis of Negative Sampling in Knowledge Graph Representation Learning 4
Compressed-VFL: Communication-Efficient Learning with Vertically Partitioned Data 5
Conditional GANs with Auxiliary Discriminative Classifier 3
Confidence Score for Source-Free Unsupervised Domain Adaptation 4
Conformal Prediction Sets with Limited False Positives 5
Congested Bandits: Optimal Routing via Short-term Resets 2
Connect, Not Collapse: Explaining Contrastive Learning for Unsupervised Domain Adaptation 2
Consensus Multiplicative Weights Update: Learning to Learn using Projector-based Game Signatures 2
Consistent Polyhedral Surrogates for Top-k Classification and Variants 1
Constants Matter: The Performance Gains of Active Learning 2
Constrained Discrete Black-Box Optimization using Mixed-Integer Programming 6
Constrained Gradient Descent: A Powerful and Principled Evasion Attack Against Neural Networks 4
Constrained Offline Policy Optimization 1
Constrained Optimization with Dynamic Bound-scaling for Effective NLP Backdoor Defense 5
Constrained Variational Policy Optimization for Safe Reinforcement Learning 4
Constraint-based graph network simulator 4
Content Addressable Memory Without Catastrophic Forgetting by Heteroassociation with a Fixed Scaffold 3
ContentVec: An Improved Self-Supervised Speech Representation by Disentangling Speakers 4
Context-Aware Drift Detection 5
Contextual Bandits with Large Action Spaces: Made Practical 4
Contextual Bandits with Smooth Regret: Efficient Learning in Continuous Action Spaces 3
Contextual Information-Directed Sampling 1
Continual Learning via Sequential Function-Space Variational Inference 4
Continual Learning with Guarantees via Weight Interval Constraints 5
Continual Repeated Annealed Flow Transport Monte Carlo 6
Continuous Control with Action Quantization from Demonstrations 3
Continuous-Time Analysis of Accelerated Gradient Methods via Conservation Laws in Dilated Coordinate Systems 0
Continuous-Time Modeling of Counterfactual Outcomes Using Neural Controlled Differential Equations 5
Contrastive Learning with Boosted Memorization 5
Contrastive Mixture of Posteriors for Counterfactual Inference, Data Integration and Fairness 6
Contrastive UCB: Provably Efficient Contrastive Self-Supervised Learning in Online Reinforcement Learning 4
Controlling Conditional Language Models without Catastrophic Forgetting 5
Convergence Rates of Non-Convex Stochastic Gradient Descent Under a Generic Lojasiewicz Condition and Local Smoothness 3
Convergence and Recovery Guarantees of the K-Subspaces Method for Subspace Clustering 5
Convergence of Invariant Graph Networks 1
Convergence of Policy Gradient for Entropy Regularized MDPs with Neural Network Approximation in the Mean-Field Regime 0
Convergence of Uncertainty Sampling for Active Learning 2
Convolutional and Residual Networks Provably Contain Lottery Tickets 5
Cooperative Online Learning in Stochastic and Adversarial MDPs 1
Coordinated Attacks against Contextual Bandits: Fundamental Limits and Defense Mechanisms 2
Coordinated Double Machine Learning 5
Correct-N-Contrast: a Contrastive Approach for Improving Robustness to Spurious Correlations 6
Correlated Quantization for Distributed Mean Estimation and Optimization 4
Correlation Clustering via Strong Triadic Closure Labeling: Fast Approximation Algorithms and Practical Lower Bounds 5
Counterfactual Prediction for Outcome-Oriented Treatments 3
Counterfactual Transportability: A Formal Approach 1
Cross-Space Active Learning on Graph Convolutional Networks 1
CtrlFormer: Learning Transferable State Representation for Visual Control via Transformer 5
Curriculum Reinforcement Learning via Constrained Optimal Transport 5
Cycle Representation Learning for Inductive Relation Prediction 5
DAVINZ: Data Valuation using Deep Neural Networks at Initialization 5
DAdaQuant: Doubly-adaptive quantization for communication-efficient Federated Learning 4
DNA: Domain Generalization with Diversified Neural Averaging 7
DNNR: Differential Nearest Neighbors Regression 6
DNS: Determinantal Point Process Based Neural Network Sampler for Ensemble Reinforcement Learning 5
DRAGONN: Distributed Randomized Approximate Gradients of Neural Networks 5
DRIBO: Robust Deep Reinforcement Learning via Multi-View Information Bottleneck 7
DSTAGNN: Dynamic Spatial-Temporal Aware Graph Neural Network for Traffic Flow Forecasting 5
Data Augmentation as Feature Manipulation 2
Data Determines Distributional Robustness in Contrastive Language Image Pre-training (CLIP) 2
Data Scaling Laws in NMT: The Effect of Noise and Architecture 3
Data-Efficient Double-Win Lottery Tickets from Robust Pre-training 3
Data-SUITE: Data-centric identification of in-distribution incongruous examples 6
Datamodels: Understanding Predictions with Data and Data with Predictions 4
Dataset Condensation via Efficient Synthetic-Data Parameterization 5
Dataset Condensation with Contrastive Signals 4
De novo mass spectrometry peptide sequencing with a transformer model 5
Debiaser Beware: Pitfalls of Centering Regularized Transport Maps 4
Decentralized Online Convex Optimization in Networked Systems 1
Deciphering Lasso-based Classification Through a Large Dimensional Analysis of the Iterative Soft-Thresholding Algorithm 5
Decision-Focused Learning: Through the Lens of Learning to Rank 5
Decomposing Temporal High-Order Interactions via Latent ODEs 3
Deconfounded Value Decomposition for Multi-Agent Reinforcement Learning 3
Deduplicating Training Data Mitigates Privacy Risks in Language Models 2
Deep Causal Metric Learning 5
Deep Hierarchy in Bandits 3
Deep Network Approximation in Terms of Intrinsic Parameters 2
Deep Networks on Toroids: Removing Symmetries Reveals the Structure of Flat Regions in the Landscape Geometry 5
Deep Neural Network Fusion via Graph Matching with Applications to Model Ensemble and Federated Learning 5
Deep Probability Estimation 4
Deep Reference Priors: What is the best way to pretrain a model? 4
Deep Safe Incomplete Multi-view Clustering: Theorem and Algorithm 3
Deep Squared Euclidean Approximation to the Levenshtein Distance for DNA Storage 2
Deep Variational Graph Convolutional Recurrent Network for Multivariate Time Series Anomaly Detection 6
Deep and Flexible Graph Neural Architecture Search 7
Deep equilibrium networks are sensitive to initialization statistics 3
Deep symbolic regression for recurrence prediction 4
DeepSpeed-MoE: Advancing Mixture-of-Experts Inference and Training to Power Next-Generation AI Scale 5
Delay-Adaptive Step-sizes for Asynchronous Learning 3
Delayed Reinforcement Learning by Imitation 4
Deletion Robust Submodular Maximization over Matroids 3
Demystifying the Adversarial Robustness of Random Transformation Defenses 6
Denoised MDPs: Learning World Models Better Than the World Itself 6
Deploying Convolutional Networks on Untrusted Platforms Using 2D Holographic Reduced Representations 5
DepthShrinker: A New Compression Paradigm Towards Boosting Real-Hardware Efficiency of Compact Neural Networks 4
Describing Differences between Text Distributions with Natural Language 3
Design-Bench: Benchmarks for Data-Driven Offline Model-Based Optimization 5
Detached Error Feedback for Distributed SGD with Random Sparsification 5
Detecting Adversarial Examples Is (Nearly) As Hard As Classifying Them 1
Detecting Corrupted Labels Without Training a Model to Predict 4
Dialog Inpainting: Turning Documents into Dialogs 4
Difference Advantage Estimation for Multi-Agent Policy Gradients 3
Differentiable Top-k Classification Learning 3
Differentially Private Approximate Quantiles 5
Differentially Private Community Detection for Stochastic Block Models 4
Differentially Private Coordinate Descent for Composite Empirical Risk Minimization 5
Differentially Private Maximal Information Coefficients 3
Diffusion Models for Adversarial Purification 4
Diffusion bridges vector quantized variational autoencoders 4
Dimension-free Complexity Bounds for High-order Nonconvex Finite-sum Optimization 1
Direct Behavior Specification via Constrained Reinforcement Learning 3
Directed Acyclic Transformer for Non-Autoregressive Machine Translation 6
DisPFL: Towards Communication-Efficient Personalized Federated Learning via Decentralized Sparse Training 4
Discovering Generalizable Spatial Goal Representations via Graph-based Active Reward Learning 3
Discrete Probabilistic Inverse Optimal Transport 4
Discrete Tree Flows via Tree-Structured Permutations 5
Discriminator-Weighted Offline Imitation Learning from Suboptimal Demonstrations 6
Disentangled Federated Learning for Tackling Attributes Skew via Invariant Aggregation and Diversity Transferring 3
Disentangling Disease-related Representation from Obscure for Disease Prediction 3
Disentangling Sources of Risk for Distributional Multi-Agent Reinforcement Learning 5
Distinguishing rule and exemplar-based generalization in learning systems 4
Distribution Regression with Sliced Wasserstein Kernels 5
Distributional Hamilton-Jacobi-Bellman Equations for Continuous-Time Reinforcement Learning 3
Distributionally Robust $Q$-Learning 2
Distributionally-Aware Kernelized Bandit Problems for Risk Aversion 5
Divergence-Regularized Multi-Agent Actor-Critic 4
Diversified Adversarial Attacks based on Conjugate Gradient Method 6
Do Differentiable Simulators Give Better Policy Gradients? 1
Do More Negative Samples Necessarily Hurt In Contrastive Learning? 2
Does the Data Induce Capacity Control in Deep Learning? 4
Domain Adaptation for Time Series Forecasting via Attention Sharing 4
Double Sampling Randomized Smoothing 4
Doubly Robust Distributionally Robust Off-Policy Evaluation and Learning 4
DreamerPro: Reconstruction-Free Model-Based Reinforcement Learning with Prototypical Representations 4
Dual Decomposition of Convex Optimization Layers for Consistent Attention in Medical Images 5
Dual Perspective of Label-Specific Feature Learning for Multi-Label Classification 4
DynaMixer: A Vision MLP Architecture with Dynamic Mixing 6
Dynamic Regret of Online Markov Decision Processes 1
Dynamic Topic Models for Temporal Document Networks 5
EAT-C: Environment-Adversarial sub-Task Curriculum for Efficient Reinforcement Learning 3
EDEN: Communication-Efficient and Robust Distributed Mean Estimation for Federated Learning 5
Easy Variational Inference for Categorical Models via an Independent Binary Approximation 4
Efficient Approximate Inference for Stationary Kernel on Frequency Domain 7
Efficient Computation of Higher-Order Subgraph Attribution via Message Passing 5
Efficient Distributionally Robust Bayesian Optimization with Worst-case Sensitivity 4
Efficient Learning for AlphaZero via Path Consistency 5
Efficient Learning of CNNs using Patch Based Features 4
Efficient Low Rank Convex Bounds for Pairwise Discrete Graphical Models 5
Efficient Model-based Multi-agent Reinforcement Learning via Optimistic Equilibrium Computation 2
Efficient Online ML API Selection for Multi-Label Classification Tasks 6
Efficient PAC Learning from the Crowd with Pairwise Comparisons 1
Efficient Reinforcement Learning in Block MDPs: A Model-free Representation Learning approach 3
Efficient Representation Learning via Adaptive Context Pooling 4
Efficient Test-Time Model Adaptation without Forgetting 6
Efficient Variance Reduction for Meta-learning 3
Efficiently Learning the Topology and Behavior of a Networked Dynamical System Via Active Queries 5
End-to-End Balancing for Causal Continuous Treatment-Effect Estimation 5
Entropic Causal Inference: Graph Identifiability 3
Entropic Gromov-Wasserstein between Gaussian Distributions 2
EqR: Equivariant Representations for Data-Efficient Reinforcement Learning 4
EquiBind: Geometric Deep Learning for Drug Binding Structure Prediction 5
Equivalence Analysis between Counterfactual Regret Minimization and Online Mirror Descent 3
Equivariance versus Augmentation for Spherical Images 5
Equivariant Diffusion for Molecule Generation in 3D 5
Equivariant Priors for compressed sensing with unknown orientation 4
Equivariant Quantum Graph Circuits 1
Error-driven Input Modulation: Solving the Credit Assignment Problem without a Backward Pass 5
Estimating Instance-dependent Bayes-label Transition Matrix using a Deep Neural Network 6
Estimating and Penalizing Induced Preference Shifts in Recommender Systems 5
Estimating the Optimal Covariance with Imperfect Mean in Diffusion Probabilistic Models 5
Estimation in Rotationally Invariant Generalized Linear Models via Approximate Message Passing 1
Evaluating the Adversarial Robustness of Adaptive Test-time Defenses 4
Evolving Curricula with Regret-Based Environment Design 6
Exact Learning of Preference Structure: Single-peaked Preferences and Beyond 1
Exact Optimal Accelerated Complexity for Fixed-Point Iterations 1
Examining Scaling and Transfer of Language Model Architectures for Machine Translation 3
Exploiting Independent Instruments: Identification and Distribution Generalization 4
Exploiting Redundancy: Separable Group Convolutional Networks on Lie Groups 5
Exploring and Exploiting Hubness Priors for High-Quality GAN Latent Sampling 5
Exploring the Gap between Collapsed & Whitened Features in Self-Supervised Learning 4
Expression might be enough: representing pressure and demand for reinforcement learning based traffic signal control 4
Extended Unconstrained Features Model for Exploring Deep Neural Collapse 2
Extracting Latent State Representations with Linear Dynamics from Rich Observations 2
FEDformer: Frequency Enhanced Decomposed Transformer for Long-term Series Forecasting 6
FITNESS: (Fine Tune on New and Similar Samples) to detect anomalies in streams with drift and outliers 3
FOCUS: Familiar Objects in Common and Uncommon Settings 3
Failure and success of the spectral bias prediction for Laplace Kernel Ridge Regression: the case of low-dimensional data 2
Fair Generalized Linear Models with a Convex Penalty 4
Fair Representation Learning through Implicit Path Alignment 4
Fair and Fast k-Center Clustering for Data Summarization 5
Fairness Interventions as (Dis)Incentives for Strategic Manipulation 2
Fairness with Adaptive Weights 3
Fast Aquatic Swimmer Optimization with Differentiable Projective Dynamics and Neural Network Hydrodynamic Models 1
Fast Composite Optimization and Statistical Recovery in Federated Learning 3
Fast Convex Optimization for Two-Layer ReLU Networks: Equivalent Model Classes and Cone Decompositions 7
Fast Finite Width Neural Tangent Kernel 5
Fast Lossless Neural Compression with Integer-Only Discrete Flows 6
Fast Population-Based Reinforcement Learning on a Single Machine 5
Fast Provably Robust Decision Trees and Boosting 5
Fast Relative Entropy Coding with A* coding 4
Fast and Provable Nonconvex Tensor RPCA 5
Fast and Reliable Evaluation of Adversarial Robustness with Minimum-Margin Attack 6
Fast rates for noisy interpolation require rethinking the effect of inductive bias 3
Fast-Rate PAC-Bayesian Generalization Bounds for Meta-Learning 3
Faster Algorithms for Learning Convex Functions 7
Faster Fundamental Graph Algorithms via Learned Predictions 3
Faster Privacy Accounting via Evolving Discretization 2
Fat–Tailed Variational Inference with Anisotropic Tail Adaptive Flows 5
Feature Learning and Signal Propagation in Deep Neural Networks 4
Feature Space Particle Inference for Neural Network Ensembles 5
Feature and Parameter Selection in Stochastic Linear Bandits 3
Feature selection using e-values 6
FedNL: Making Newton-Type Methods Applicable to Federated Learning 3
FedNest: Federated Bilevel, Minimax, and Compositional Optimization 5
FedNew: A Communication-Efficient and Privacy-Preserving Newton-Type Method for Federated Learning 4
FedScale: Benchmarking Model and System Performance of Federated Learning at Scale 7
Federated Learning with Label Distribution Skew via Logits Calibration 4
Federated Learning with Partial Model Personalization 5
Federated Learning with Positive and Unlabeled Data 3
Federated Minimax Optimization: Improved Convergence Analyses and Algorithms 5
Federated Reinforcement Learning: Linear Speedup Under Markovian Sampling 1
Fenrir: Physics-Enhanced Regression for Initial Value Problems 3
Fictitious Play and Best-Response Dynamics in Identical Interest and Zero-Sum Stochastic Games 1
Fighting Fire with Fire: Avoiding DNN Shortcuts through Priming 3
Finding Global Homophily in Graph Neural Networks When Meeting Heterophily 6
Finding the Task-Optimal Low-Bit Sub-Distribution in Deep Neural Networks 7
Finite-Sum Coupled Compositional Stochastic Optimization: Theory and Applications 5
First-Order Regret in Reinforcement Learning with Linear Function Approximation: A Robust Estimation Approach 1
Fisher SAM: Information Geometry and Sharpness Aware Minimisation 4
Fishing for User Data in Large-Batch Federated Learning via Gradient Magnification 6
Fishr: Invariant Gradient Variances for Out-of-Distribution Generalization 6
Flashlight: Enabling Innovation in Tools for Machine Learning 7
Flow-Guided Sparse Transformer for Video Deblurring 4
Flow-based Recurrent Belief State Learning for POMDPs 3
Flowformer: Linearizing Transformers with Conservation Flows 5
Fluctuations, Bias, Variance & Ensemble of Learners: Exact Asymptotics for Convex Losses in High-Dimension 1
For Learning in Symmetric Teams, Local Optima are Global Nash Equilibria 4
Forget-free Continual Learning with Winning Subnetworks 6
Forward Operator Estimation in Generative Models with Kernel Transfer Operators 5
Fourier Learning with Cyclical Data 4
Framework for Evaluating Faithfulness of Local Explanations 4
FriendlyCore: Practical Differentially Private Aggregation 4
From Dirichlet to Rubin: Optimistic Exploration in RL without Bonuses 3
From Noisy Prediction to True Label: Noisy Prediction Calibration via Generative Model 5
From block-Toeplitz matrices to differential equations on graphs: towards a general theory for scalable masked Transformers 6
From data to functa: Your data point is a function and you can treat it like one 3
Frustratingly Easy Transferability Estimation 5
Fully-Connected Network on Noncompact Symmetric Space and Ridgelet Transform based on Helgason-Fourier Analysis 0
Function-space Inference with Sparse Implicit Processes 5
Functional Generalized Empirical Likelihood Estimation for Conditional Moment Restrictions 4
Functional Output Regression with Infimal Convolution: Exploring the Huber and $ε$-insensitive Losses 4
G$^2$CN: Graph Gaussian Convolution Networks with Concentrated Graph Filters 4
G-Mixup: Graph Data Augmentation for Graph Classification 5
GACT: Activation Compressed Training for Generic Network Architectures 5
GALAXY: Graph-based Active Learning at the Extreme 4
GLIDE: Towards Photorealistic Image Generation and Editing with Text-Guided Diffusion Models 5
GLaM: Efficient Scaling of Language Models with Mixture-of-Experts 4
GNNRank: Learning Global Rankings from Pairwise Comparisons via Directed Graph Neural Networks 6
GSmooth: Certified Robustness against Semantic Transformations via Generalized Randomized Smoothing 3
Gating Dropout: Communication-efficient Regularization for Sparsely Activated Transformers 5
Gaussian Mixture Variational Autoencoder with Contrastive Learning for Multi-Label Classification 5
Gaussian Process Uniform Error Bounds with Unknown Hyperparameters for Safety-Critical Applications 4
GenLabel: Mixup Relabeling using Generative Models 6
General-purpose, long-context autoregressive modeling with Perceiver AR 5
Generalised Policy Improvement with Geometric Policy Composition 2
Generalization Bounds using Lower Tail Exponents in Stochastic Optimizers 4
Generalization Guarantee of Training Graph Convolutional Networks with Graph Topology Sampling 2
Generalization and Robustness Implications in Object-Centric Learning 5
Generalized Beliefs for Cooperative AI 4
Generalized Data Distribution Iteration 4
Generalized Federated Learning via Sharpness Aware Minimization 5
Generalized Leverage Scores: Geometric Interpretation and Applications 3
Generalized Results for the Existence and Consistency of the MLE in the Bradley-Terry-Luce Model 2
Generalized Strategic Classification and the Case of Aligned Incentives 4
Generalizing Gaussian Smoothing for Random Search 3
Generalizing to Evolving Domains with Latent Structure-Aware Sequential Autoencoder 4
Generalizing to New Physical Systems via Context-Informed Dynamics Model 6
Generating 3D Molecules for Target Protein Binding 2
Generating Distributional Adversarial Examples to Evade Statistical Detectors 2
Generative Coarse-Graining of Molecular Conformations 4
Generative Cooperative Networks for Natural Language Generation 4
Generative Flow Networks for Discrete Probabilistic Modeling 5
Generative Modeling for Multi-task Visual Learning 5
Generative Trees: Adversarial and Copycat 6
Generic Coreset for Scalable Learning of Monotonic Kernels: Logistic Regression, Sigmoid and more 4
Geometric Multimodal Contrastive Representation Learning 3
Global Optimization Networks 4
Global Optimization of K-Center Clustering 5
Goal Misgeneralization in Deep Reinforcement Learning 4
Going Deeper into Permutation-Sensitive Graph Neural Networks 6
Gradient Based Clustering 2
Gradient Descent on Neurons and its Link to Approximate Second-order Optimization 4
Gradient-Free Method for Heavily Constrained Nonconvex Optimization 4
Graph Neural Architecture Search Under Distribution Shifts 5
Graph-Coupled Oscillator Networks 5
GraphFM: Improving Large-Scale GNN Training via Feature Momentum 6
Greedy based Value Representation for Optimal Coordination in Multi-agent Reinforcement Learning 3
Greedy when Sure and Conservative when Uncertain about the Opponents 4
Guarantees for Epsilon-Greedy Reinforcement Learning with Function Approximation 1
Guided-TTS: A Diffusion Model for Text-to-Speech via Classifier Guidance 5
H-Consistency Bounds for Surrogate Loss Minimizers 0
Hardness and Algorithms for Robust and Sparse Optimization 1
Head2Toe: Utilizing Intermediate Representations for Better Transfer Learning 4
Hermite Polynomial Features for Private Data Generation 5
Hessian-Free High-Resolution Nesterov Acceleration For Sampling 3
Hierarchical Shrinkage: Improving the accuracy and interpretability of tree-based models. 4
High Probability Guarantees for Nonconvex Stochastic Gradient Descent with Heavy Tails 1
Hindering Adversarial Attacks with Implicit Neural Representations 3
History Compression via Language Models in Reinforcement Learning 5
HousE: Knowledge Graph Embedding with Householder Parameterization 5
How Faithful is your Synthetic Data? Sample-level Metrics for Evaluating and Auditing Generative Models 4
How Powerful are Spectral Graph Neural Networks 4
How Tempering Fixes Data Augmentation in Bayesian Neural Networks 3
How to Fill the Optimum Set? Population Gradient Descent with Harmless Diversity 4
How to Leverage Unlabeled Data in Offline Reinforcement Learning 3
How to Stay Curious while avoiding Noisy TVs using Aleatoric Uncertainty Estimation 4
How to Steer Your Adversary: Targeted and Efficient Model Stealing Defenses with Gradient Redirection 5
How to Train Your Wide Neural Network Without Backprop: An Input-Weight Alignment Perspective 6
Human-in-the-loop: Provably Efficient Preference-based Reinforcement Learning with General Function Approximation 1
HyperImpute: Generalized Iterative Imputation with Automatic Model Selection 5
HyperPrompt: Prompt-based Task-Conditioning of Transformers 3
HyperTransformer: Model Generation for Supervised and Semi-Supervised Few-Shot Learning 3
IDYNO: Learning Nonparametric DAGs from Interventional Dynamic Data 4
IGLUE: A Benchmark for Transfer Learning across Modalities, Tasks, and Languages 5
Identifiability Conditions for Domain Adaptation 4
Identification of Linear Non-Gaussian Latent Hierarchical Structure 3
Identity-Disentangled Adversarial Augmentation for Self-supervised Learning 6
Image-to-Image Regression with Distribution-Free Uncertainty Quantification and Applications in Imaging 5
Imitation Learning by Estimating Expertise of Demonstrators 4
Implicit Bias of Linear Equivariant Networks 3
Implicit Bias of the Step Size in Linear Diagonal Neural Networks 1
Implicit Regularization in Hierarchical Tensor Factorization and Deep Convolutional Neural Networks 5
Implicit Regularization with Polynomial Growth in Deep Tensor Factorization 3
Importance Weighted Kernel Bayes’ Rule 4
Improve Single-Point Zeroth-Order Optimization Using High-Pass and Low-Pass Filters 1
Improved Certified Defenses against Data Poisoning with (Deterministic) Finite Aggregation 2
Improved Convergence Rates for Sparse Approximation Methods in Kernel-Based Learning 1
Improved No-Regret Algorithms for Stochastic Shortest Path with Linear MDP 1
Improved Rates for Differentially Private Stochastic Convex Optimization with Heavy-Tailed Data 1
Improved Regret for Differentially Private Exploration in Linear MDP 1
Improved StyleGAN-v2 based Inversion for Out-of-Distribution Images 4
Improving Adversarial Robustness via Mutual Information Estimation 5
Improving Ensemble Distillation With Weight Averaging and Diversifying Perturbation 7
Improving Language Models by Retrieving from Trillions of Tokens 4
Improving Mini-batch Optimal Transport via Partial Transportation 6
Improving Out-of-Distribution Robustness via Selective Augmentation 5
Improving Policy Optimization with Generalist-Specialist Learning 3
Improving Robustness against Real-World and Worst-Case Distribution Shifts through Decision Region Quantification 3
Improving Screening Processes via Calibrated Subset Selection 4
Improving Task-free Continual Learning by Distributionally Robust Memory Evolution 4
Improving Transformers with Probabilistic Attention Keys 5
In defense of dual-encoders for neural ranking 3
Independent Policy Gradient for Large-Scale Markov Potential Games: Sharper Rates, Function Approximation, and Game-Agnostic Convergence 3
Individual Preference Stability for Clustering 4
Individual Reward Assisted Multi-Agent Reinforcement Learning 3
Inducing Causal Structure for Interpretable Neural Networks 6
Inductive Biases and Variable Creation in Self-Attention Mechanisms 3
Inductive Matrix Completion: No Bad Local Minima and a Fast Algorithm 4
Inferring Cause and Effect in the Presence of Heteroscedastic Noise 5
Influence-Augmented Local Simulators: a Scalable Solution for Fast Deep RL in Large Networked Systems 2
Information Discrepancy in Strategic Learning 4
Informed Learning by Wide Neural Networks: Convergence, Generalization and Sampling Complexity 3
Injecting Logical Constraints into Neural Networks via Straight-Through Estimators 4
Input Dependent Sparse Gaussian Processes 6
Input-agnostic Certified Group Fairness via Gaussian Parameter Smoothing 4
Instance Dependent Regret Analysis of Kernelized Bandits 1
Instrumental Variable Regression with Confounder Balancing 7
Interactive Correlation Clustering with Existential Cluster Constraints 5
Interactive Inverse Reinforcement Learning for Cooperative Games 5
Interactively Learning Preference Constraints in Linear Bandits 4
Interpretable Neural Networks with Frank-Wolfe: Sparse Relevance Maps and Relevance Orderings 6
Interpretable Off-Policy Learning via Hyperbox Search 7
Interpretable and Generalizable Graph Learning via Stochastic Attention Mechanism 5
Interventional Contrastive Learning with Meta Semantic Regularizer 4
Intriguing Properties of Input-Dependent Randomized Smoothing 3
Invariant Ancestry Search 4
Inverse Contextual Bandits: Learning How Behavior Evolves over Time 4
Investigating Generalization by Controlling Normalized Margin 4
Investigating Why Contrastive Learning Benefits Robustness against Label Noise 3
Iterative Double Sketching for Faster Least-Squares Optimization 3
Iterative Hard Thresholding with Adaptive Regularization: Sparser Solutions Without Sacrificing Runtime 6
It’s Raw! Audio Generation with State-Space Models 4
Kernel Methods for Radial Transformed Compositional Data with Many Zeros 2
Kernelized Multiplicative Weights for 0/1-Polyhedral Games: Bridging the Gap Between Learning in Extensive-Form and Normal-Form Games 3
Kill a Bird with Two Stones: Closing the Convergence Gaps in Non-Strongly Convex Optimization by Directly Accelerated SVRG with Double Compensation and Snapshots 4
Knowledge Base Question Answering by Case-based Reasoning over Subgraphs 4
Knowledge-Grounded Self-Rationalization via Extractive and Natural Language Explanations 5
Koopman Q-learning: Offline Reinforcement Learning via Symmetries of Dynamics 5
LCANets: Lateral Competition Improves Robustness Against Corruption and Attack 5
LIDL: Local Intrinsic Dimension Estimation Using Approximate Likelihood 4
LIMO: Latent Inceptionism for Targeted Molecule Generation 7
LSB: Local Self-Balancing MCMC in Discrete Spaces 4
Label Ranking through Nonparametric Regression 4
Label-Descriptive Patterns and Their Application to Characterizing Classification Errors 7
Label-Free Explainability for Unsupervised Models 7
Lagrangian Method for Q-Function Learning (with Applications to Machine Translation) 5
Langevin Monte Carlo for Contextual Bandits 5
Language Models as Zero-Shot Planners: Extracting Actionable Knowledge for Embodied Agents 4
Large Batch Experience Replay 5
Large-Scale Graph Neural Architecture Search 7
Large-scale Stochastic Optimization of NDCG Surrogates for Deep Learning with Provable Convergence 6
Last Iterate Risk Bounds of SGD with Decaying Stepsize for Overparameterized Linear Regression 2
Latent Diffusion Energy-Based Model for Interpretable Text Modelling 4
Latent Outlier Exposure for Anomaly Detection with Contaminated Data 5
Lazy Estimation of Variable Importance for Large Neural Networks 5
LeNSE: Learning To Navigate Subgraph Embeddings for Large-Scale Combinatorial Optimisation 4
Learning Augmented Binary Search Trees 2
Learning Bellman Complete Representations for Offline Policy Evaluation 4
Learning Domain Adaptive Object Detection with Probabilistic Teacher 5
Learning Dynamics and Generalization in Deep Reinforcement Learning 2
Learning Efficient and Robust Ordinary Differential Equations via Invertible Neural Networks 5
Learning General Halfspaces with Adversarial Label Noise via Online Gradient Descent 1
Learning Infinite-horizon Average-reward Markov Decision Process with Constraints 2
Learning Iterative Reasoning through Energy Minimization 4
Learning Markov Games with Adversarial Opponents: Efficient Algorithms and Fundamental Limits 1
Learning Mixtures of Linear Dynamical Systems 3
Learning Multiscale Transformer Models for Sequence Generation 4
Learning Pseudometric-based Action Representations for Offline Reinforcement Learning 2
Learning Stable Classifiers by Transferring Unstable Features 5
Learning Stochastic Shortest Path with Linear Function Approximation 2
Learning Symmetric Embeddings for Equivariant World Models 4
Learning fair representation with a parametric integral probability metric 5
Learning from Counterfactual Links for Link Prediction 7
Learning from Demonstration: Provably Efficient Adversarial Policy Imitation with Linear Function Approximation 3
Learning from a Learning User for Optimal Recommendations 2
Learning inverse folding from millions of predicted structures 5
Learning of Cluster-based Feature Importance for Electronic Health Record Time-series 5
Learning to Cut by Looking Ahead: Cutting Plane Selection via Imitation Learning 5
Learning to Estimate and Refine Fluid Motion with Physical Dynamics 4
Learning to Hash Robustly, Guaranteed 5
Learning to Incorporate Texture Saliency Adaptive Attention to Image Cartoonization 2
Learning to Infer Structures of Network Games 4
Learning to Predict Graphs with Fused Gromov-Wasserstein Barycenters 5
Learning to Separate Voices by Spatial Regions 5
Learning to Solve PDE-constrained Inverse Problems with Graph Networks 3
Learning-based Optimisation of Particle Accelerators Under Partial Observability Without Real-World Training 2
Least Squares Estimation using Sketched Data with Heteroskedastic Errors 3
Let Invariant Rationale Discovery Inspire Graph Contrastive Learning 5
Leverage Score Sampling for Tensor Product Matrices in Input Sparsity Time 3
Leveraging Approximate Symbolic Models for Reinforcement Learning via Skill Diversity 3
Lie Point Symmetry Data Augmentation for Neural PDE Solvers 3
Lightweight Projective Derivative Codes for Compressed Asynchronous Gradient Descent 2
Linear Adversarial Concept Erasure 5
Linear Bandit Algorithms with Sublinear Time Complexity 3
Linear Complexity Randomized Self-attention Mechanism 4
Linear-Time Gromov Wasserstein Distances using Low Rank Couplings and Costs 5
Linearity Grafting: Relaxed Neuron Pruning Helps Certifiable Robustness 3
Local Augmentation for Graph Neural Networks 7
Local Linear Convergence of Douglas-Rachford for Linear Programming: a Probabilistic Analysis 2
Locally Sparse Neural Networks for Tabular Biomedical Data 5
Log-Euclidean Signatures for Intrinsic Distances Between Unaligned Datasets 5
Loss Function Learning for Domain Generalization by Implicit Gradient 5
Low-Complexity Deep Convolutional Neural Networks on Fully Homomorphic Encryption Using Multiplexed Parallel Convolutions 6
Low-Precision Stochastic Gradient Langevin Dynamics 3
LyaNet: A Lyapunov Framework for Training Neural ODEs 6
Lyapunov Density Models: Constraining Distribution Shift in Learning-Based Control 3
MAE-DET: Revisiting Maximum Entropy Principle in Zero-Shot NAS for Efficient Object Detection 6
MAML and ANIL Provably Learn Representations 1
MASER: Multi-Agent Reinforcement Learning with Subgoals Generated from Experience Replay Buffer 4
ME-GAN: Learning Panoptic Electrocardio Representations for Multi-view ECG Synthesis Conditioned on Heart Diseases 4
Making Linear MDPs Practical via Contrastive Representation Learning 3
Marginal Distribution Adaptation for Discrete Sets via Module-Oriented Divergence Minimization 4
Marginal Tail-Adaptive Normalizing Flows 5
Markov Chain Monte Carlo for Continuous-Time Switching Dynamical Systems 3
Maslow’s Hammer in Catastrophic Forgetting: Node Re-Use vs. Node Activation 3
Massively Parallel $k$-Means Clustering for Perturbation Resilient Instances 4
Matching Learned Causal Effects of Neural Networks with Domain Priors 6
Matching Normalizing Flows and Probability Paths on Manifolds 2
Matching Structure for Dual Learning 4
Maximum Likelihood Training for Score-based Diffusion ODEs by High Order Denoising Score Matching 5
Meaningfully debugging model mistakes using conceptual counterfactual explanations 5
Measure Estimation in the Barycentric Coding Model 5
Measuring Representational Robustness of Neural Networks Through Shared Invariances 4
Measuring dissimilarity with diffeomorphism invariance 4
Measuring the Effect of Training Data on Deep Learning Predictions via Randomized Experiments 6
MemSR: Training Memory-efficient Lightweight Model for Image Super-Resolution 6
Memory-Based Model Editing at Scale 3
MetAug: Contrastive Learning via Meta Feature Augmentation 3
Meta-Learning Hypothesis Spaces for Sequential Decision-making 3
Metric-Fair Active Learning 2
Metric-Fair Classifier Derandomization 0
Minimax Classification under Concept Drift with Multidimensional Adaptation and Performance Guarantees 5
Minimax M-estimation under Adversarial Contamination 2
Minimizing Control for Credit Assignment with Strong Feedback 5
Minimum Cost Intervention Design for Causal Effect Identification 4
Mirror Learning: A Unifying Framework of Policy Optimisation 1
Mitigating Gender Bias in Face Recognition using the von Mises-Fisher Mixture Model 4
Mitigating Modality Collapse in Multimodal VAEs via Impartial Optimization 4
Mitigating Neural Network Overconfidence with Logit Normalization 5
ModLaNets: Learning Generalisable Dynamics via Modularity and Physical Inductive Bias 3
Modality Competition: What Makes Joint Training of Multi-modal Network Fail in Deep Learning? (Provably) 4
Model Agnostic Sample Reweighting for Out-of-Distribution Learning 5
Model Selection in Batch Policy Optimization 2
Model soups: averaging weights of multiple fine-tuned models improves accuracy without increasing inference time 5
Model-Free Opponent Shaping 3
Model-Value Inconsistency as a Signal for Epistemic Uncertainty 3
Model-based Meta Reinforcement Learning using Graph Structured Surrogate Models and Amortized Policy Search 6
Modeling Adversarial Noise for Adversarial Training 5
Modeling Irregular Time Series with Continuous Recurrent Units 6
Modeling Strong and Human-Like Gameplay with KL-Regularized Search 4
Modeling Structure with Undirected Neural Networks 4
Modular Conformal Calibration 4
Molecular Representation Learning via Heterogeneous Motif Graph Neural Networks 5
Monarch: Expressive Structured Matrices for Efficient and Accurate Training 6
More Efficient Sampling for Tensor Decomposition With Worst-Case Guarantees 7
More Than a Toy: Random Matrix Models Predict How Real-World Neural Representations Generalize 4
Multi Resolution Analysis (MRA) for Approximate Self-Attention 5
Multi-Grained Vision Language Pre-Training: Aligning Texts with Visual Concepts 5
Multi-Level Branched Regularization for Federated Learning 4
Multi-Task Learning as a Bargaining Game 5
Multi-scale Feature Learning Dynamics: Insights for Double Descent 3
Multi-slots Online Matching with High Entropy 2
Multiclass learning with margin: exponential rates with no bias-variance trade-off 0
Multicoated Supermasks Enhance Hidden Networks 4
Multiple-Play Stochastic Bandits with Shareable Finite-Capacity Arms 2
Multirate Training of Neural Networks 6
N-Penetrate: Active Learning of Neural Collision Handler for Complex 3D Mesh Deformations 5
NAFS: A Simple yet Tough-to-beat Baseline for Graph Representation Learning 7
NISPA: Neuro-Inspired Stability-Plasticity Adaptation for Continual Learning in Sparse Networks 5
NLP From Scratch Without Large-Scale Pretraining: A Simple and Efficient Framework 4
NOMU: Neural Optimization-based Model Uncertainty 5
NP-Match: When Neural Processes meet Semi-Supervised Learning 5
Near-Exact Recovery for Tomographic Inverse Problems via Deep Learning 4
Near-Optimal Algorithms for Autonomous Exploration and Multi-Goal Stochastic Shortest Path 1
Near-Optimal Learning of Extensive-Form Games with Imperfect Information 1
Near-optimal rate of consistency for linear models with missing values 3
Nearly Minimax Optimal Reinforcement Learning with Linear Function Approximation 1
Nearly Optimal Catoni’s M-estimator for Infinite Variance 2
Nearly Optimal Policy Optimization with Stable at Any Time Guarantee 1
Nested Bandits 4
Nesterov Accelerated Shuffling Gradient Method for Convex Optimization 6
Neural Fisher Discriminant Analysis: Optimal Neural Network Embeddings in Polynomial Time 3
Neural Implicit Dictionary Learning via Mixture-of-Expert Training 3
Neural Inverse Kinematic 1
Neural Inverse Transform Sampler 5
Neural Language Models are not Born Equal to Fit Brain Data, but Training Helps 4
Neural Laplace: Learning diverse classes of differential equations in the Laplace domain 5
Neural Network Poisson Models for Behavioural and Neural Spike Train Data 3
Neural Network Pruning Denoises the Features and Makes Local Connectivity Emerge in Visual Tasks 5
Neural Network Weights Do Not Converge to Stationary Points: An Invariant Measure Perspective 3
Neural Tangent Kernel Analysis of Deep Narrow Neural Networks 3
Neural Tangent Kernel Beyond the Infinite-Width Limit: Effects of Depth and Initialization 3
Neural Tangent Kernel Empowered Federated Learning 3
Neural-Symbolic Models for Logical Queries on Knowledge Graphs 6
NeuralEF: Deconstructing Kernels by Deep Neural Networks 4
Neuro-Symbolic Hierarchical Rule Induction 4
Neuro-Symbolic Language Modeling with Automaton-augmented Retrieval 5
NeuroFluid: Fluid Dynamics Grounding with Particle-Driven Neural Radiance Fields 2
Neurocoder: General-Purpose Computation Using Stored Neural Programs 3
Neuron Dependency Graphs: A Causal Abstraction of Neural Networks 5
Neurotoxin: Durable Backdoors in Federated Learning 4
No-Regret Learning in Partially-Informed Auctions 1
No-Regret Learning in Time-Varying Zero-Sum Games 2
Non-Vacuous Generalisation Bounds for Shallow Neural Networks 4
Nonlinear Feature Diffusion on Hypergraphs 5
Nonparametric Embeddings of Sparse High-Order Interaction Events 2
Nonparametric Factor Trajectory Learning for Dynamic Tensor Decomposition 3
Nonparametric Involutive Markov Chain Monte Carlo 3
Nonparametric Sparse Tensor Factorization with Hierarchical Gamma Processes 3
Not All Poisons are Created Equal: Robust Training against Data Poisoning 5
NysADMM: faster composite convex optimization via low-rank approximation 4
Nyström Kernel Mean Embeddings 2
OFA: Unifying Architectures, Tasks, and Modalities Through a Simple Sequence-to-Sequence Learning Framework 4
Object Permanence Emerges in a Random Walk along Memory 5
Off-Policy Evaluation for Large Action Spaces via Embeddings 4
Off-Policy Fitted Q-Evaluation with Differentiable Function Approximators: Z-Estimation and Inference Theory 1
Off-Policy Reinforcement Learning with Delayed Rewards 4
Offline Meta-Reinforcement Learning with Online Self-Supervision 3
Offline RL Policies Should Be Trained to be Adaptive 3
Omni-Granular Ego-Semantic Propagation for Self-Supervised Graph Representation Learning 4
On Collective Robustness of Bagging Against Data Poisoning 7
On Convergence of Gradient Descent Ascent: A Tight Local Analysis 2
On Distribution Shift in Learning-based Bug Detectors 5
On Finite-Sample Identifiability of Contrastive Learning-Based Nonlinear Independent Component Analysis 2
On Implicit Bias in Overparameterized Bilevel Optimization 5
On Improving Model-Free Algorithms for Decentralized Multi-Agent Reinforcement Learning 3
On Last-Iterate Convergence Beyond Zero-Sum Games 2
On Learning Mixture of Linear Regressions in the Non-Realizable Setting 4
On Measuring Causal Contributions via do-interventions 4
On Non-local Convergence Analysis of Deep Linear Networks 1
On Numerical Integration in Neural Ordinary Differential Equations 2
On Transportation of Mini-batches: A Hierarchical Approach 5
On Well-posedness and Minimax Optimal Rates of Nonparametric Q-function Estimation in Off-policy Evaluation 0
On the Adversarial Robustness of Causal Algorithmic Recourse 4
On the Convergence of Inexact Predictor-Corrector Methods for Linear Programming 2
On the Convergence of Local Stochastic Compositional Gradient Descent with Momentum 5
On the Convergence of the Shapley Value in Parametric Bayesian Learning Games 3
On the Difficulty of Defending Self-Supervised Learning against Model Extraction 4
On the Effects of Artificial Data Modification 4
On the Equivalence Between Temporal and Static Equivariant Graph Representations 5
On the Finite-Time Complexity and Practical Computation of Approximate Stationarity Concepts of Lipschitz Functions 1
On the Finite-Time Performance of the Knowledge Gradient Algorithm 2
On the Generalization Analysis of Adversarial Learning 0
On the Hidden Biases of Policy Mirror Ascent in Continuous Action Spaces 2
On the Impossibility of Learning to Cooperate with Adaptive Partner Strategies in Repeated Games 0
On the Learning of Non-Autoregressive Transformers 3
On the Optimization Landscape of Neural Collapse under MSE Loss: Global Optimality with Unconstrained Features 4
On the Practicality of Deterministic Epistemic Uncertainty 5
On the Robustness of CountSketch to Adaptive Inputs 3
On the Role of Discount Factor in Offline Reinforcement Learning 3
On the Sample Complexity of Learning Infinite-horizon Discounted Linear Kernel MDPs 1
On the Statistical Benefits of Curriculum Learning 2
On the Surrogate Gap between Contrastive and Supervised Losses 6
One-Pass Algorithms for MAP Inference of Nonsymmetric Determinantal Point Processes 4
One-Pass Diversified Sampling with Application to Terabyte-Scale Genomic Sequence Streams 5
Online Active Regression 4
Online Algorithms with Multiple Predictions 1
Online Balanced Experimental Design 3
Online Continual Learning through Mutual Information Maximization 4
Online Decision Transformer 3
Online Learning and Pricing with Reusable Resources: Linear Bandits with Sub-Exponential Rewards 2
Online Learning for Min Sum Set Cover and Pandora’s Box 1
Online Learning with Knapsacks: the Best of Both Worlds 1
Online Nonsubmodular Minimization with Delayed Costs: From Full Information to Bandit Feedback 3
Online and Consistent Correlation Clustering 5
Only tails matter: Average-Case Universality and Robustness in the Convex Regime 3
Open-Sampling: Exploring Out-of-Distribution data for Re-balancing Long-tailed datasets 6
Optimal Algorithms for Mean Estimation under Local Differential Privacy 1
Optimal Algorithms for Stochastic Multi-Level Compositional Optimization 3
Optimal Clipping and Magnitude-aware Differentiation for Improved Quantization-aware Training 3
Optimal Clustering with Noisy Queries via Multi-Armed Bandit 1
Optimal Estimation of Policy Gradient via Double Fitted Iteration 1
Optimal and Efficient Dynamic Regret Algorithms for Non-Stationary Dueling Bandits 2
Optimally Controllable Perceptual Lossy Compression 3
Optimistic Linear Support and Successor Features as a Basis for Optimal Policy Transfer 4
Optimization-Derived Learning with Essential Convergence Analysis of Training and Hyper-training 4
Optimization-Induced Graph Implicit Nonlinear Diffusion 4
Optimizing Sequential Experimental Design with Deep Reinforcement Learning 3
Optimizing Tensor Network Contraction Using Reinforcement Learning 4
Orchestra: Unsupervised Federated Learning via Globally Consistent Clustering 6
Order Constraints in Optimal Transport 6
Out-of-Distribution Detection with Deep Nearest Neighbors 5
Overcoming Oscillations in Quantization-Aware Training 5
PAC-Bayesian Bounds on Rate-Efficient Classifiers 4
PAC-Net: A Model Pruning Approach to Inductive Transfer Learning 3
PACE: A Parallelizable Computation Encoder for Directed Acyclic Graphs 6
PAGE-PG: A Simple and Loopless Variance-Reduced Policy Gradient Method with Probabilistic Gradient Estimation 4
PDE-Based Optimal Strategy for Unconstrained Online Learning 4
PDO-s3DCNNs: Partial Differential Operator Based Steerable 3D CNNs 4
PINs: Progressive Implicit Networks for Multi-Scale Neural Representations 3
PLATINUM: Semi-Supervised Model Agnostic Meta-Learning using Submodular Mutual Information 6
PLATON: Pruning Large Transformer Models with Upper Confidence Bound of Weight Importance 6
PMIC: Improving Multi-Agent Reinforcement Learning with Progressive Mutual Information Collaboration 4
POEM: Out-of-Distribution Detection with Posterior Sampling 6
POET: Training Neural Networks on Tiny Devices with Integrated Rematerialization and Paging 5
Pairwise Conditional Gradients without Swap Steps and Sparser Kernel Herding 4
Parametric Visual Program Induction with Function Modularization 3
Parsimonious Learning-Augmented Caching 3
Partial Counterfactual Identification from Observational and Experimental Data 3
Partial Label Learning via Label Influence Function 4
Partial and Asymmetric Contrastive Learning for Out-of-Distribution Detection in Long-Tailed Recognition 5
Partial disentanglement for domain adaptation 3
Particle Transformer for Jet Tagging 4
Path-Aware and Structure-Preserving Generation of Synthetically Accessible Molecules 3
Path-Gradient Estimators for Continuous Normalizing Flows 5
Penalizing Gradient Norm for Efficiently Improving Generalization in Deep Learning 5
Perfectly Balanced: Improving Transfer and Robustness of Supervised Contrastive Learning 4
Permutation Search of Tensor Network Structures via Local Sampling 4
Personalization Improves Privacy-Accuracy Tradeoffs in Federated Learning 4
Personalized Federated Learning through Local Memorization 5
Personalized Federated Learning via Variational Bayesian Inference 5
Pessimism meets VCG: Learning Dynamic Mechanism Design via Offline Reinforcement Learning 1
Pessimistic Minimax Value Iteration: Provably Efficient Equilibrium Learning from Offline Datasets 1
Pessimistic Q-Learning for Offline Reinforcement Learning: Towards Optimal Sample Complexity 1
Phasic Self-Imitative Reduction for Sparse-Reward Goal-Conditioned Reinforcement Learning 5
Plan Better Amid Conservatism: Offline Multi-Agent Reinforcement Learning with Actor Rectification 4
Plan Your Target and Learn Your Skills: Transferable State-Only Imitation Learning via Decoupled Policy Optimization 5
Planning with Diffusion for Flexible Behavior Synthesis 5
Plug & Play Attacks: Towards Robust and Flexible Model Inversion Attacks 5
Plug-In Inversion: Model-Agnostic Inversion for Vision with Data Augmentations 4
PoF: Post-Training of Feature Extractor for Improving Generalization 5
Pocket2Mol: Efficient Molecular Sampling Based on 3D Protein Pockets 6
Policy Diagnosis via Measuring Role Diversity in Cooperative Multi-agent RL 2
Policy Gradient Method For Robust Reinforcement Learning 3
Popular decision tree algorithms are provably noise tolerant 1
Position Prediction as an Effective Pretraining Strategy 5
Power-Law Escape Rate of SGD 2
Practical Almost-Linear-Time Approximation Algorithms for Hybrid and Overlapping Graph Clustering 6
Preconditioning for Scalable Gaussian Process Hyperparameter Optimization 6
Predicting Out-of-Distribution Error with the Projection Norm 5
Principal Component Flows 5
Principled Knowledge Extrapolation with GANs 4
Prioritized Training on Points that are Learnable, Worth Learning, and not yet Learnt 5
Privacy for Free: How does Dataset Condensation Help Privacy? 3
Private Adaptive Optimization with Side information 5
Private Streaming SCO in $\ell_p$ geometry with Applications in High Dimensional Online Decision Making 3
Private frequency estimation via projective geometry 4
Private optimization in the interpolation regime: faster rates and hardness results 1
ProGCL: Rethinking Hard Negative Mining in Graph Contrastive Learning 6
Probabilistic Bilevel Coreset Selection 4
Probabilistic ODE Solutions in Millions of Dimensions 3
Probabilistically Robust Learning: Balancing Average and Worst-case Performance 6
ProgFed: Effective, Communication, and Computation Efficient Federated Learning by Progressive Training 4
Prompting Decision Transformer for Few-Shot Policy Generalization 3
Prototype Based Classification from Hierarchy to Fairness 3
Prototype-Anchored Learning for Learning with Imperfect Annotations 4
Provable Acceleration of Heavy Ball beyond Quadratics for a Class of Polyak-Lojasiewicz Functions when the Non-Convexity is Averaged-Out 2
Provable Domain Generalization via Invariant-Feature Subspace Recovery 5
Provable Reinforcement Learning with a Short-Term Memory 1
Provable Stochastic Optimization for Global Contrastive Learning: Small Batch Does Not Harm Performance 6
Provably Adversarially Robust Nearest Prototype Classifiers 3
Provably Efficient Offline Reinforcement Learning for Partially Observable Markov Decision Processes 1
Proving Theorems using Incremental Learning and Hindsight Experience Replay 5
ProxSkip: Yes! Local Gradient Steps Provably Lead to Communication Acceleration! Finally! 5
Proximal Denoiser for Convergent Plug-and-Play Optimization with Nonconvex Regularization 4
Proximal Exploration for Model-guided Protein Sequence Design 4
Proximal and Federated Random Reshuffling 4
Public Data-Assisted Mirror Descent for Private Model Training 5
Pure Noise to the Rescue of Insufficient Data: Improving Imbalanced Classification by Training on Random Noise Images 5
QSFL: A Two-Level Uplink Communication Optimization Framework for Federated Learning 5
Quant-BnB: A Scalable Branch-and-Bound Method for Optimal Decision Trees with Continuous Features 7
Quantification and Analysis of Layer-wise and Pixel-wise Information Discarding 3
Quantifying and Learning Linear Symmetry-Based Disentanglement 5
Quantum-Inspired Algorithms from Randomized Numerical Linear Algebra 4
Query-Efficient and Scalable Black-Box Adversarial Attacks on Discrete Sequential Data via Bayesian Optimization 4
RECAPP: Crafting a More Efficient Catalyst for Convex Optimization 4
REvolveR: Continuous Evolutionary Models for Robot-to-robot Policy Transfer 4
ROCK: Causal Inference Principles for Reasoning about Commonsense Causality 4
RUMs from Head-to-Head Contests 5
Random Forest Density Estimation 4
Random Gegenbauer Features for Scalable Kernel Methods 3
RankSim: Ranking Similarity Regularization for Deep Imbalanced Regression 5
Re-evaluating Word Mover’s Distance 5
Reachability Constrained Reinforcement Learning 3
Reconstructing Nonlinear Dynamical Systems from Multi-Modal Time Series 5
Recurrent Model-Free RL Can Be a Strong Baseline for Many POMDPs 4
Reducing Variance in Temporal-Difference Value Estimation via Ensemble of Deep Networks 4
Refined Convergence Rates for Maximum Likelihood Estimation under Finite Mixture Models 4
Region-Based Semantic Factorization in GANs 4
Regret Bounds for Stochastic Shortest Path Problems with Linear Function Approximation 1
Regret Minimization with Performative Feedback 1
Regularizing a Model-based Policy Stationary Distribution to Stabilize Offline Reinforcement Learning 4
Reinforcement Learning from Partial Observation: Linear Function Approximation with Provable Sample Efficiency 1
Reinforcement Learning with Action-Free Pre-Training from Videos 4
Removing Batch Normalization Boosts Adversarial Training 5
Representation Topology Divergence: A Method for Comparing Neural Network Representations. 4
Residual-Based Sampling for Online Outlier-Robust PCA 2
Resilient and Communication Efficient Learning for Heterogeneous Federated Systems 3
Restarted Nonconvex Accelerated Gradient Descent: No More Polylogarithmic Factor in the $O(ε^-7/4)$ Complexity 3
Rethinking Attention-Model Explainability through Faithfulness Violation Test 2
Rethinking Fano’s Inequality in Ensemble Learning 6
Rethinking Graph Neural Networks for Anomaly Detection 5
Rethinking Image-Scaling Attacks: The Interplay Between Vulnerabilities in Machine Learning Systems 5
Retrieval-Augmented Reinforcement Learning 3
RetrievalGuard: Provably Robust 1-Nearest Neighbor Image Retrieval 4
Retroformer: Pushing the Limits of End-to-end Retrosynthesis Transformer 6
Reverse Engineering $\ell_p$ attacks: A block-sparse optimization approach with recovery guarantees 3
Reverse Engineering the Neural Tangent Kernel 4
Revisiting Consistency Regularization for Deep Partial Label Learning 4
Revisiting Contrastive Learning through the Lens of Neighborhood Component Analysis: an Integrated Framework 3
Revisiting End-to-End Speech-to-Text Translation From Scratch 4
Revisiting Label Smoothing and Knowledge Distillation Compatibility: What was Missing? 6
Revisiting Online Submodular Minimization: Gap-Dependent Regret Bounds, Best of Both Worlds and Adversarial Robustness 1
Revisiting Some Common Practices in Cooperative Multi-Agent Reinforcement Learning 2
Revisiting and Advancing Fast Adversarial Training Through The Lens of Bi-Level Optimization 6
Revisiting the Effects of Stochasticity for Hamiltonian Samplers 3
Reward-Free RL is No Harder Than Reward-Aware RL in Linear Markov Decision Processes 1
Rich Feature Construction for the Optimization-Generalization Dilemma 5
RieszNet and ForestRiesz: Automatic Debiased Machine Learning with Neural Nets and Random Forests 3
Ripple Attention for Visual Perception with Sub-quadratic Complexity 5
Risk-Averse No-Regret Learning in Online Convex Games 2
Robin Hood and Matthew Effects: Differential Privacy Has Disparate Impact on Synthetic Data 4
Robust Counterfactual Explanations for Tree-Based Ensembles 3
Robust Deep Reinforcement Learning through Bootstrapped Opportunistic Curriculum 5
Robust Fine-Tuning of Deep Neural Networks with Hessian-based Generalization Guarantees 4
Robust Group Synchronization via Quadratic Programming 4
Robust Imitation Learning against Variations in Environment Dynamics 5
Robust Kernel Density Estimation with Median-of-Means principle 3
Robust Meta-learning with Sampling Noise and Label Noise via Eigen-Reptile 6
Robust Models Are More Interpretable Because Attributions Look Normal 5
Robust Multi-Objective Bayesian Optimization Under Input Noise 5
Robust Policy Learning over Multiple Uncertainty Sets 4
Robust SDE-Based Variational Formulations for Solving Linear PDEs via Deep Learning 3
Robust Task Representations for Offline Meta-Reinforcement Learning via Contrastive Learning 4
Robust Training of Neural Networks Using Scale Invariant Architectures 3
Robust Training under Label Noise by Over-parameterization 7
Robust alignment of cross-session recordings of neural population activity by behaviour via unsupervised domain adaptation 3
Robustness Implies Generalization via Data-Dependent Generalization Bounds 3
Robustness Verification for Contrastive Learning 5
Robustness and Accuracy Could Be Reconcilable by (Proper) Definition 4
Robustness in Multi-Objective Submodular Optimization: a Quantile Approach 2
Role-based Multiplex Network Embedding 3
Rotting Infinitely Many-Armed Bandits 3
SCHA-VAE: Hierarchical Context Aggregation for Few-Shot Generation 5
SDQ: Stochastic Differentiable Quantization with Mixed Precision 5
SE(3) Equivariant Graph Neural Networks with Complete Local Frames 5
SPDY: Accurate Pruning with Speedup Guarantees 7
SPECTRE: Spectral Conditioning Helps to Overcome the Expressivity Limits of One-shot Graph Generators 5
SQ-VAE: Variational Bayes on Discrete Representation with Self-annealed Stochastic Quantization 5
Safe Exploration for Efficient Policy Evaluation and Comparison 3
Safe Learning in Tree-Form Sequential Decision Making: Handling Hard and Soft Constraints 3
Sample Efficient Learning of Predictors that Complement Humans 5
Sample and Communication-Efficient Decentralized Actor-Critic Algorithms with Finite-Time Analysis 2
Sample-Efficient Reinforcement Learning with loglog(T) Switching Cost 1
Sanity Simulations for Saliency Methods 5
Saute RL: Almost Surely Safe Reinforcement Learning Using State Augmentation 5
Scalable Computation of Causal Bounds 1
Scalable Deep Gaussian Markov Random Fields for General Graphs 4
Scalable Deep Reinforcement Learning Algorithms for Mean Field Games 3
Scalable First-Order Bayesian Optimization via Structured Automatic Differentiation 4
Scalable MCMC Sampling for Nonsymmetric Determinantal Point Processes 5
Scalable Spike-and-Slab 6
Scaling Gaussian Process Optimization by Evaluating a Few Unique Candidates Multiple Times 3
Scaling Out-of-Distribution Detection for Real-World Settings 4
Scaling Structured Inference with Randomization 5
Scaling-up Diverse Orthogonal Convolutional Networks by a Paraunitary Framework 5
Score Matching Enables Causal Discovery of Nonlinear Additive Noise Models 4
Score-Guided Intermediate Level Optimization: Fast Langevin Mixing for Inverse Problems 5
Score-based Generative Modeling of Graphs via the System of Stochastic Differential Equations 7
Searching for BurgerFormer with Micro-Meso-Macro Space Design 5
Secure Distributed Training at Scale 5
Secure Quantized Training for Deep Learning 6
Selective Network Linearization for Efficient Private Inference 5
Selective Regression under Fairness Criteria 4
Self-Organized Polynomial-Time Coordination Graphs 5
Self-Supervised Models of Audio Effectively Explain Human Cortical Responses to Speech 4
Self-Supervised Representation Learning via Latent Graph Prediction 7
Self-conditioning Pre-Trained Language Models 5
Self-supervised Models are Good Teaching Assistants for Vision Transformers 4
Self-supervised learning with random-projection quantizer for speech recognition 2
Selling Data To a Machine Learner: Pricing via Costly Signaling 1
Sequential Covariate Shift Detection Using Classifier Two-Sample Tests 4
Sequential and Parallel Constrained Max-value Entropy Search via Information Lower Bound 3
Set Based Stochastic Subsampling 3
Set Norm and Equivariant Skip Connections: Putting the Deep in Deep Sets 4
Sharp-MAML: Sharpness-Aware Model-Agnostic Meta Learning 4
Sharpened Quasi-Newton Methods: Faster Superlinear Rate and Larger Local Convergence Neighborhood 2
ShiftAddNAS: Hardware-Inspired Search for More Accurate and Efficient Neural Networks 5
Short-Term Plasticity Neurons Learning to Learn and Forget 5
Showing Your Offline Reinforcement Learning Work: Online Evaluation Budget Matters 5
Shuffle Private Linear Contextual Bandits 3
Simple and near-optimal algorithms for hidden stratification and multi-group learning 1
Simplex Neural Population Learning: Any-Mixture Bayes-Optimality in Symmetric Zero-sum Games 4
Simultaneous Graph Signal Clustering and Graph Learning 4
Simultaneously Learning Stochastic and Adversarial Bandits with General Graph Feedback 1
Sketching Algorithms and Lower Bounds for Ridge Regression 2
SkexGen: Autoregressive Generation of CAD Construction Sequences with Disentangled Codebooks 5
Skin Deep Unlearning: Artefact and Instrument Debiasing in the Context of Melanoma Classification 5
Smoothed Adaptive Weighting for Imbalanced Semi-Supervised Learning: Improve Reliability Against Unknown Distribution Data 6
Smoothed Adversarial Linear Contextual Bandits with Knapsacks 1
SoQal: Selective Oracle Questioning for Consistency Based Active Learning of Cardiac Signals 5
Soft Truncation: A Universal Training Technique of Score-based Diffusion Model for High Precision Score Estimation 4
Solving Stackelberg Prediction Game with Least Squares Loss via Spherically Constrained Least Squares Reformulation 5
SpaceMAP: Visualizing High-Dimensional Data by Space Expansion 5
Sparse Double Descent: Where Network Pruning Aggravates Overfitting 3
Sparse Invariant Risk Minimization 3
Sparse Mixed Linear Regression with Guarantees: Taming an Intractable Problem with Invex Relaxation 1
Sparsity in Partially Controllable Linear Systems 2
Spatial-Channel Token Distillation for Vision MLPs 3
Spectral Representation of Robustness Measures for Optimization Under Input Uncertainty 4
SpeqNets: Sparsity-aware permutation-equivariant graph networks 7
Stability Based Generalization Bounds for Exponential Family Langevin Dynamics 3
Stabilizing Off-Policy Deep Reinforcement Learning from Pixels 4
Stabilizing Q-learning with Linear Architectures for Provable Efficient Learning 1
Stable Conformal Prediction Sets 4
Staged Training for Transformer Language Models 4
State Transition of Dendritic Spines Improves Learning of Sparse Spiking Neural Networks 4
Statistical inference with implicit SGD: proximal Robbins-Monro vs. Polyak-Ruppert 1
Steerable 3D Spherical Neurons 4
Stochastic Contextual Dueling Bandits under Linear Stochastic Transitivity Models 3
Stochastic Continuous Submodular Maximization: Boosting via Non-oblivious Function 3
Stochastic Deep Networks with Linear Competing Units for Model-Agnostic Meta-Learning 4
Stochastic Reweighted Gradient Descent 3
Stochastic Rising Bandits 4
Stochastic smoothing of the top-K calibrated hinge loss for deep imbalanced classification 4
Strategic Instrumental Variable Regression: Recovering Causal Relationships From Strategic Responses 3
Strategic Representation 1
Strategies for Safe Multi-Armed Bandits with Logarithmic Regret and Risk 3
Streaming Algorithm for Monotone k-Submodular Maximization with Cardinality Constraints 3
Streaming Algorithms for High-Dimensional Robust Statistics 1
Streaming Algorithms for Support-Aware Histograms 3
Streaming Inference for Infinite Feature Models 1
StreamingQA: A Benchmark for Adaptation to New Knowledge over Time in Question Answering Models 4
Structural Entropy Guided Graph Hierarchical Pooling 5
Structure Preserving Neural Networks: A Case Study in the Entropy Closure of the Boltzmann Equation 6
Structure-Aware Transformer for Graph Representation Learning 5
Structure-preserving GANs 4
Structured Stochastic Gradient MCMC 5
Style Equalization: Unsupervised Learning of Controllable Generative Sequence Models 5
Sublinear-Time Clustering Oracle for Signed Graphs 5
Subspace Learning for Effective Meta-Learning 4
Supervised Learning with General Risk Functionals 3
Supervised Off-Policy Ranking 6
Surrogate Likelihoods for Variational Annealed Importance Sampling 4
Symmetric Machine Theory of Mind 4
Synergy and Symmetry in Deep Learning: Interactions between the Data, Model, and Inference Algorithm 3
TACTiS: Transformer-Attentional Copulas for Time Series 5
TAM: Topology-Aware Margin Loss for Class-Imbalanced Node Classification 4
TPC: Transformation-Specific Smoothing for Point Cloud Models 2
TSPipe: Learn from Teacher Faster with Pipelines 4
TURF: Two-Factor, Universal, Robust, Fast Distribution Learning Algorithm 2
Tackling Data Heterogeneity: A New Unified Framework for Decentralized SGD with Sample-induced Topology 4
Tackling covariate shift with node-based Bayesian neural networks 4
Task-aware Privacy Preservation for Multi-dimensional Data 5
Tell me why! Explanations support learning relational and causal structure 3
Temporal Difference Learning for Model Predictive Control 5
Test-Time Training Can Close the Natural Distribution Shift Performance Gap in Deep Learning Based Compressed Sensing 4
The Algebraic Path Problem for Graph Metrics 0
The CLRS Algorithmic Reasoning Benchmark 6
The Combinatorial Brain Surgeon: Pruning Weights That Cancel One Another in Neural Networks 4
The Complexity of k-Means Clustering when Little is Known 0
The Dual Form of Neural Networks Revisited: Connecting Test Time Predictions to Training Patterns via Spotlights of Attention 4
The Fundamental Price of Secure Aggregation in Differentially Private Federated Learning 5
The Geometry of Robust Value Functions 0
The Importance of Non-Markovianity in Maximum State Entropy Exploration 2
The Infinite Contextual Graph Markov Model 5
The Multivariate Community Hawkes Model for Dependent Relational Events in Continuous-time Networks 4
The Neural Race Reduction: Dynamics of Abstraction in Gated Networks 4
The Poisson Binomial Mechanism for Unbiased Federated Learning with Secure Aggregation 2
The Power of Exploiter: Provable Multi-Agent RL in Large State Spaces 1
The Primacy Bias in Deep Reinforcement Learning 3
The Role of Deconfounding in Meta-learning 4
The State of Sparse Training in Deep Reinforcement Learning 3
The Teaching Dimension of Regularized Kernel Learners 3
The Unsurprising Effectiveness of Pre-Trained Vision Models for Control 4
The dynamics of representation learning in shallow, non-linear autoencoders 3
The power of first-order smooth optimization for black-box non-smooth problems 5
Thompson Sampling for (Combinatorial) Pure Exploration 2
Thompson Sampling for Robust Transfer in Multi-Task Bandits 3
Three-stage Evolution and Fast Equilibrium for SGD with Non-degerate Critical Points 2
Thresholded Lasso Bandit 4
Tight and Robust Private Mean Estimation with Few Users 1
Time Is MattEr: Temporal Self-supervision for Video Transformers 4
To Smooth or Not? When Label Smoothing Meets Noisy Labels 3
Topology-Aware Network Pruning using Multi-stage Graph Embedding and Reinforcement Learning 6
Topology-aware Generalization of Decentralized SGD 5
Toward Compositional Generalization in Object-Oriented World Modeling 3
Towards Coherent and Consistent Use of Entities in Narrative Generation 4
Towards Evaluating Adaptivity of Model-Based Reinforcement Learning Methods 5
Towards Noise-adaptive, Problem-adaptive (Accelerated) Stochastic Gradient Descent 3
Towards Scaling Difference Target Propagation by Learning Backprop Targets 4
Towards Theoretical Analysis of Transformation Complexity of ReLU DNNs 5
Towards Understanding Sharpness-Aware Minimization 4
Towards Uniformly Superhuman Autonomy via Subdominance Minimization 1
Towards understanding how momentum improves generalization in deep learning 2
Tractable Dendritic RNNs for Reconstructing Nonlinear Dynamical Systems 3
Tractable Uncertainty for Structure Learning 2
Training Characteristic Functions with Reinforcement Learning: XAI-methods play Connect Four 2
Training Discrete Deep Generative Models via Gapped Straight-Through Estimator 6
Training OOD Detectors in their Natural Habitats 6
Training Your Sparse Neural Network Better with Any Mask 3
Tranception: Protein Fitness Prediction with Autoregressive Transformers and Inference-time Retrieval 4
Transfer Learning In Differential Privacy’s Hybrid-Model 2
Transfer and Marginalize: Explaining Away Label Noise with Privileged Information 3
Transformer Neural Processes: Uncertainty-Aware Meta Learning Via Sequence Modeling 4
Transformer Quality in Linear Time 4
Transformers are Meta-Reinforcement Learners 4
Translating Robot Skills: Learning Unsupervised Skill Correspondences Across Robots 3
Translatotron 2: High-quality direct speech-to-speech translation with voice preservation 4
UAST: Uncertainty-Aware Siamese Tracking 6
UNIREX: A Unified Learning Framework for Language Model Rationale Extraction 3
Unaligned Supervision for Automatic Music Transcription in The Wild 6
Uncertainty Modeling in Generative Compressed Sensing 5
UnderGrad: A Universal Black-Box Optimization Method with Almost Dimension-Free Convergence Rate Guarantees 3
Understanding Clipping for Federated Learning: Convergence and Client-Level Differential Privacy 4
Understanding Contrastive Learning Requires Incorporating Inductive Biases 3
Understanding Dataset Difficulty with $\mathcal{V}$-Usable Information 4
Understanding Doubly Stochastic Clustering 1
Understanding Gradient Descent on the Edge of Stability in Deep Learning 3
Understanding Gradual Domain Adaptation: Improved Analysis, Optimal Path and Beyond 4
Understanding Instance-Level Impact of Fairness Constraints 4
Understanding Policy Gradient Algorithms: A Sensitivity-Based Approach 1
Understanding Robust Generalization in Learning Regular Languages 2
Understanding Robust Overfitting of Adversarial Training and Beyond 4
Understanding The Robustness in Vision Transformers 4
Understanding and Improving Knowledge Graph Embedding for Entity Alignment 5
Understanding the unstable convergence of gradient descent 2
UniRank: Unimodal Bandit Algorithms for Online Ranking 2
Unified Fourier-based Kernel and Nonlinearity Design for Equivariant Networks on Homogeneous Spaces 2
Unified Scaling Laws for Routed Language Models 4
Universal Hopfield Networks: A General Framework for Single-Shot Associative Memory Models 3
Universal Joint Approximation of Manifolds and Densities by Simple Injective Flows 0
Universal and data-adaptive algorithms for model selection in linear contextual bandits 1
Universality of Winning Tickets: A Renormalization Group Perspective 2
Unraveling Attention via Convex Duality: Analysis and Interpretations of Vision Transformers 3
Unsupervised Detection of Contextualized Embedding Bias with Application to Ideology 5
Unsupervised Flow-Aligned Sequence-to-Sequence Learning for Video Restoration 6
Unsupervised Ground Metric Learning Using Wasserstein Singular Vectors 4
Unsupervised Image Representation Learning with Deep Latent Particles 5
Unsupervised Time-Series Representation Learning with Iterative Bilinear Temporal-Spectral Fusion 5
Utility Theory for Sequential Decision Making 0
Utilizing Expert Features for Contrastive Learning of Time-Series Representations 4
VLMixer: Unpaired Vision-Language Pre-training via Cross-Modal CutMix 5
VLUE: A Multi-Task Multi-Dimension Benchmark for Evaluating Vision-Language Pre-training 5
Validating Causal Inference Methods 2
Value Function based Difference-of-Convex Algorithm for Bilevel Hyperparameter Selection Problems 6
VarScene: A Deep Generative Model for Realistic Scene Graph Synthesis 5
VariGrow: Variational Architecture Growing for Task-Agnostic Continual Learning based on Bayesian Novelty 3
Variational Feature Pyramid Networks 4
Variational Inference for Infinitely Deep Neural Networks 6
Variational Inference with Locally Enhanced Bounds for Hierarchical Models 2
Variational Mixtures of ODEs for Inferring Cellular Gene Expression Dynamics 4
Variational On-the-Fly Personalization 5
Variational Sparse Coding with Learned Thresholding 7
Variational Wasserstein gradient flow 5
Variational nearest neighbor Gaussian process 5
Versatile Dueling Bandits: Best-of-both World Analyses for Learning from Relative Preferences 3
Versatile Offline Imitation from Observations and Examples via Regularized State-Occupancy Matching 4
ViT-NeT: Interpretable Vision Transformers with Neural Tree Decoder 5
Virtual Homogeneity Learning: Defending against Data Heterogeneity in Federated Learning 4
Visual Attention Emerges from Recurrent Sparse Reconstruction 3
Volatility Based Kernels and Moving Average Means for Accurate Forecasting with Gaussian Processes 4
Weisfeiler-Lehman Meets Gromov-Wasserstein 4
Welfare Maximization in Competitive Equilibrium: Reinforcement Learning for Markov Exchange Economy 3
What Can Linear Interpolation of Neural Network Loss Landscapes Tell Us? 3
What Dense Graph Do You Need for Self-Attention? 5
What Language Model Architecture and Pretraining Objective Works Best for Zero-Shot Generalization? 4
When AUC meets DRO: Optimizing Partial AUC for Deep Learning with Non-Convex Convergence Guarantee 5
When Are Linear Stochastic Bandits Attackable? 2
When and How Mixup Improves Calibration 4
Why Should I Trust You, Bellman? The Bellman Error is a Poor Replacement for Value Error 2
Why the Rich Get Richer? On the Balancedness of Random Partition Models 4
Wide Bayesian neural networks have a simple weight posterior: theory and accelerated sampling 3
Wide Neural Networks Forget Less Catastrophically 3
Winning the Lottery Ahead of Time: Efficient Early Network Pruning 5
XAI for Transformers: Better Explanations through Conservative Propagation 3
You Only Cut Once: Boosting Data Augmentation with a Single Cut 3
YourTTS: Towards Zero-Shot Multi-Speaker TTS and Zero-Shot Voice Conversion for Everyone 5
Zero-Shot Reward Specification via Grounded Natural Language 1
Zero-shot AutoML with Pretrained Models 5
data2vec: A General Framework for Self-supervised Learning in Speech, Vision and Language 4
pathGCN: Learning General Graph Spatial Operators from Paths 4