Sample Complexity

On characterizations of learnability with computable learners COLT 2022 On Gap-dependent Bounds for Offline Reinforcement Learning NeurIPS 2022 Online Target Q-learning with Reverse Experience Replay: Efficiently finding the Optimal Policy for Linear MDPs ICLR 2022 On the Efficient Implementation of High Accuracy Optimality of Profile Maximum Likelihood NeurIPS 2022 On The Memory Complexity of Uniformity Testing COLT 2022 Open Problem: Properly learning decision trees in polynomial time? COLT 2022 Optimal Mean Estimation without a Variance COLT 2022 Optimal SQ Lower Bounds for Learning Halfspaces with Massart Noise COLT 2022 PER-ETD: A Polynomially Efficient Emphatic Temporal Difference Learning Method ICLR 2022 Sample-Efficient Reinforcement Learning in the Presence of Exogenous Information COLT 2022 Strong Memory Lower Bounds for Learning Natural Models COLT 2022 The Price of Tolerance in Distribution Testing COLT 2022 The Sample Complexity of One-Hidden-Layer Neural Networks NeurIPS 2022 Towards Bridging Sample Complexity and Model Capacity AAAI 2022 Towards Deployment-Efficient Reinforcement Learning: Lower Bound and Optimality ICLR 2022 Agnostic Reinforcement Learning with Low-Rank MDPs and Rich Observations NeurIPS 2021 A Mathematical Framework for Quantifying Transferability in Multi-source Transfer Learning NeurIPS 2021 Bellman Eluder Dimension: New Rich Classes of RL Problems, and Sample-Efficient Algorithms NeurIPS 2021 Bounded Memory Active Learning through Enriched Queries COLT 2021 Breaking The Dimension Dependence in Sparse Distribution Estimation under Communication Constraints COLT 2021 Efficient Coreset Constructions via Sensitivity Sampling ACML 2021 Empirical or Invariant Risk Minimization? A Sample Complexity Perspective ICLR 2021 From Local Pseudorandom Generators to Hardness of Learning COLT 2021 Generalizing Complex Hypotheses on Product Distributions: Auctions, Prophet Inequalities, and Pandora’s Problem COLT 2021 Identification of the Generalized Condorcet Winner in Multi-dueling Bandits NeurIPS 2021