Learning Theory

On the Sample Complexity of Representation Learning in Multi-Task Bandits with Global and Local Structure AAAI 2023 On the Sample Complexity of Vanilla Model-Based Offline Reinforcement Learning with Dependent Samples AAAI 2023 On the Saturation Effect of Kernel Ridge Regression ICLR 2023 On The Specialization of Neural Modules ICLR 2023 On the spectral bias of two-layer linear networks NeurIPS 2023 On the Stability and Generalization of Triplet Learning AAAI 2023 On the Stability-Plasticity Dilemma in Continual Meta-Learning: Theory and Algorithm NeurIPS 2023 On the Trade-off of Intra-/Inter-class Diversity for Supervised Pre-training NeurIPS 2023 On the Variance, Admissibility, and Stability of Empirical Risk Minimization NeurIPS 2023 Open problem: log(n) factor in "Local Glivenko-Cantelli" COLT 2023 Open Problem: The Sample Complexity of Multi-Distribution Learning for VC Classes COLT 2023 Optimal Activation Functions for the Random Features Regression Model ICLR 2023 Optimal Algorithms for Latent Bandits with Cluster Structure AISTATS 2023 Optimal Algorithms for the Inhomogeneous Spiked Wigner Model NeurIPS 2023 Optimal Approximation Rates for Deep ReLU Neural Networks on Sobolev and Besov Spaces JMLR 2023 Optimal Arms Identification with Knapsacks ICML 2023 Optimal Contextual Bandits with Knapsacks under Realizability via Regression Oracles AISTATS 2023 Optimal cross-learning for contextual bandits with unknown context distributions NeurIPS 2023 Optimal Excess Risk Bounds for Empirical Risk Minimization on p-Norm Linear Regression NeurIPS 2023 Optimal Horizon-Free Reward-Free Exploration for Linear Mixture MDPs ICML 2023 Optimality of Message-Passing Architectures for Sparse Graphs NeurIPS 2023 Optimal Learners for Realizable Regression: PAC Learning and Online Learning NeurIPS 2023 Optimal Nonlinearities Improve Generalization Performance of Random Features ACML 2023 Optimal Prediction Using Expert Advice and Randomized Littlestone Dimension COLT 2023 Optimal Rates and Efficient Algorithms for Online Bayesian Persuasion ICML 2023