Learning Theory

Modality-Agnostic Self-Supervised Learning with Meta-Learned Masked Auto-Encoder NeurIPS 2023 Model-agnostic Measure of Generalization Difficulty ICML 2023 Model-based Causal Bayesian Optimization ICLR 2023 Model-Free Reinforcement Learning with the Decision-Estimation Coefficient NeurIPS 2023 Monarch Mixer: A Simple Sub-Quadratic GEMM-Based Architecture NeurIPS 2023 Most Neural Networks Are Almost Learnable NeurIPS 2023 MTR: A Dataset Fusing Inductive, Deductive, and Defeasible Reasoning ACL 2023 Multicalibration as Boosting for Regression ICML 2023 Multiclass Boosting: Simple and Intuitive Weak Learning Criteria NeurIPS 2023 Multiclass Online Learning and Uniform Convergence COLT 2023 Multiplier Bootstrap-based Exploration ICML 2023 Multitask Learning via Shared Features: Algorithms and Hardness COLT 2023 Nash Regret Guarantees for Linear Bandits NeurIPS 2023 Nearest Neighbour with Bandit Feedback NeurIPS 2023 Nearly Minimax Optimal Offline Reinforcement Learning with Linear Function Approximation: Single-Agent MDP and Markov Game ICLR 2023 Nearly Minimax Optimal Regret for Learning Linear Mixture Stochastic Shortest Path ICML 2023 Nearly Minimax Optimal Reinforcement Learning for Linear Markov Decision Processes ICML 2023 Nearly Optimal Algorithms with Sublinear Computational Complexity for Online Kernel Regression ICML 2023 Nearly Optimal Bounds for Cyclic Forgetting NeurIPS 2023 Nearly Optimal VC-Dimension and Pseudo-Dimension Bounds for Deep Neural Network Derivatives NeurIPS 2023 Nearly-tight Bounds for Deep Kernel Learning ICML 2023 Near-Minimax-Optimal Risk-Sensitive Reinforcement Learning with CVaR ICML 2023 Near-Optimal $Φ$-Regret Learning in Extensive-Form Games ICML 2023 Near-Optimal Adversarial Reinforcement Learning with Switching Costs ICLR 2023 Near-Optimal Algorithms for Private Online Optimization in the Realizable Regime ICML 2023