Learning Theory

Nonstochastic Bandits with Composite Anonymous Feedback JMLR 2022 Non-Vacuous Generalisation Bounds for Shallow Neural Networks ICML 2022 No-Regret Learning in Partially-Informed Auctions ICML 2022 Nuances in Margin Conditions Determine Gains in Active Learning AISTATS 2022 Offline Reinforcement Learning: Fundamental Barriers for Value Function Approximation COLT 2022 Offline reinforcement learning under value and density-ratio realizability: The power of gaps UAI 2022 Offline Reinforcement Learning with Realizability and Single-policy Concentrability COLT 2022 Offline stochastic shortest path: Learning, evaluation and towards optimality UAI 2022 Off-Policy Fitted Q-Evaluation with Differentiable Function Approximators: Z-Estimation and Inference Theory ICML 2022 On Batch Teaching with Sample Complexity Bounded by VCD NeurIPS 2022 On characterizations of learnability with computable learners COLT 2022 On Deep Generative Models for Approximation and Estimation of Distributions on Manifolds NeurIPS 2022 On-Demand Sampling: Learning Optimally from Multiple Distributions NeurIPS 2022 On Finite-Sample Identifiability of Contrastive Learning-Based Nonlinear Independent Component Analysis ICML 2022 On Gap-dependent Bounds for Offline Reinforcement Learning NeurIPS 2022 On global convergence of ResNets: From finite to infinite width using linear parameterization NeurIPS 2022 On Implicit Bias in Overparameterized Bilevel Optimization ICML 2022 On Learning and Refutation in Noninteractive Local Differential Privacy NeurIPS 2022 On Leave-One-Out Conditional Mutual Information For Generalization NeurIPS 2022 Online Allocation and Learning in the Presence of Strategic Agents NeurIPS 2022 Online Bipartite Matching with Advice: Tight Robustness-Consistency Tradeoffs for the Two-Stage Model NeurIPS 2022 Online Decision Mediation NeurIPS 2022 Online Learning for Unknown Partially Observable MDPs AISTATS 2022 Online PAC-Bayes Learning NeurIPS 2022 Online Search with Best-Price and Query-Based Predictions AAAI 2022