Showing 1–20 of 32 results
/ Date/ Name
Mar 3, 2021Combinatorial Bandits without Total Order for ArmsMar 3, 2021Linear Bandit Algorithms with Sublinear Time ComplexityNov 22, 2021A Free Lunch from the Noise: Provable and Practical Exploration for Representation LearningMay 16, 2022An Exponentially Increasing Step-size for Parameter Estimation in Statistical ModelsDec 17, 2022Latent Variable Representation for Reinforcement LearningApr 8, 2023Stochastic Nonlinear Control via Finite-dimensional Spectral Dynamic EmbeddingJul 14, 2022Making Linear MDPs Practical via Contrastive Representation LearningMar 13, 2022Policy Learning for Robust Markov Decision Process with a Mismatched Generative ModelOct 15, 2021Towards Statistical and Computational Complexities of Polyak Step Size Gradient DescentMar 25, 2021Nearly Horizon-Free Offline Reinforcement LearningNov 18, 2019Implicit Regularization and Convergence for Weight NormalizationAug 19, 2022Spectral Decomposition Representation for Reinforcement LearningNov 20, 2023Provable Representation with Efficient Planning for Partial Observable Reinforcement LearningJun 2, 2021Unsupervised Out-of-Domain Detection via Pre-trained TransformersJun 16, 2021Quasi-Bayesian Dual Instrumental Variable RegressionMay 27, 2022Efficient Forecasting of Large Scale Hierarchical Time Series via Multilevel ClusteringMar 8, 2024DeepSeek-VL: Towards Real-World Vision-Language UnderstandingJul 15, 2024Spectral Representation for Causal Estimation with Hidden ConfoundersFeb 21, 2020Stein Self-Repulsive Dynamics: Benefits From Past SamplesJan 27, 2019Reward Shaping via Meta-Learning