Learning Theory

Nonstochastic Contextual Combinatorial Bandits AISTATS 2023 No-Regret Learning in Two-Echelon Supply Chain with Unknown Demand Distribution AISTATS 2023 No-Regret Linear Bandits beyond Realizability UAI 2023 No-Regret Online Reinforcement Learning with Adversarial Losses and Transitions NeurIPS 2023 Norm-based Generalization Bounds for Sparse Neural Networks NeurIPS 2023 Not All Neuro-Symbolic Concepts Are Created Equal: Analysis and Mitigation of Reasoning Shortcuts NeurIPS 2023 Offline Reinforcement Learning with Differentiable Function Approximation is Provably Efficient ICLR 2023 Off-Policy Evaluation for Large Action Spaces via Conjunct Effect Modeling ICML 2023 Omnigrok: Grokking Beyond Algorithmic Data ICLR 2023 On Accelerated Perceptrons and Beyond ICLR 2023 On Balancing Bias and Variance in Unsupervised Multi-Source-Free Domain Adaptation ICML 2023 On Batch Teaching Without Collusion JMLR 2023 On Best-Arm Identification with a Fixed Budget in Non-Parametric Multi-Armed Bandits ALT 2023 On Certified Generalization in Structured Prediction NeurIPS 2023 On Computable Online Learning ALT 2023 On Discovering Interesting Combinatorial Integer Sequences IJCAI 2023 One Arrow, Two Kills: A Unified Framework for Achieving Optimal Regret Guarantees in Sleeping Bandits AISTATS 2023 On Enhancing Expressive Power via Compositions of Single Fixed-Size ReLU Network ICML 2023 On Excess Mass Behavior in Gaussian Mixture Models with Orlicz-Wasserstein Distances ICML 2023 On Generalization Bounds for Projective Clustering NeurIPS 2023 On Instance-Dependent Bounds for Offline Reinforcement Learning with Linear Function Approximation AAAI 2023 On Learning Latent Models with Multi-Instance Weak Supervision NeurIPS 2023 Online Constrained Meta-Learning: Provable Guarantees for Generalization NeurIPS 2023 Online Label Shift: Optimal Dynamic Regret meets Practical Algorithms NeurIPS 2023 Online Learning and Solving Infinite Games with an ERM Oracle COLT 2023