{"total":29,"rows":[{"id":"2108.03706","title":"Online Bootstrap Inference For Policy Evaluation in Reinforcement Learning","created":"2021-08-08","cited_by_count":26,"area":null},{"id":"2405.16644","title":"Gaussian Approximation and Multiplier Bootstrap for Polyak-Ruppert Averaged Linear Stochastic Approximation with Applications to TD Learning","created":"2024-05-26","cited_by_count":19,"area":null},{"id":"2412.06126","title":"UCB algorithms for multi-armed bandits: Precise regret and adaptive inference","created":"2024-12-09","cited_by_count":19,"area":null},{"id":"2106.15358","title":"Towards Sample-Optimal Compressive Phase Retrieval with Sparse and Generative Priors","created":"2021-06-29","cited_by_count":14,"area":null},{"id":"2201.07306","title":"Bregman Deviations of Generic Exponential Families","created":"2022-01-18","cited_by_count":13,"area":null},{"id":"2310.00692","title":"A Theoretical Analysis of Noise Geometry in Stochastic Gradient Descent","created":"2023-10-01","cited_by_count":9,"area":null},{"id":"2102.02450","title":"Sharper Sub-Weibull Concentrations","created":"2021-02-04","cited_by_count":8,"area":null},{"id":"2202.11474","title":"Residual Bootstrap Exploration for Stochastic Linear Bandit","created":"2022-02-23","cited_by_count":8,"area":null},{"id":"2212.14883","title":"Online Statistical Inference for Contextual Bandits via Stochastic Gradient Descent","created":"2022-12-30","cited_by_count":8,"area":null},{"id":"2210.05571","title":"Misspecified Phase Retrieval with Generative Priors","created":"2022-10-11","cited_by_count":7,"area":null},{"id":"2304.05365","title":"Did we personalize? Assessing personalization by an online reinforcement learning algorithm using resampling","created":"2023-04-11","cited_by_count":6,"area":null},{"id":"2106.03790","title":"Multi-armed Bandit Requiring Monotone Arm Sequences","created":"2021-06-07","cited_by_count":5,"area":null},{"id":"2509.20648","title":"Wonder Wins Ways: Curiosity-Driven Exploration through Multi-Agent Contextual Calibration","created":"2025-09-25","cited_by_count":4,"area":null},{"id":"2108.00236","title":"Debiasing Samples from Online Learning Using Bootstrap","created":"2021-07-31","cited_by_count":3,"area":null},{"id":"2211.03827","title":"Lower Bounds for the Convergence of Tensor Power Iteration on Random Overcomplete Models","created":"2022-11-07","cited_by_count":3,"area":null},{"id":"2302.01543","title":"Multiplier Bootstrap-based Exploration","created":"2023-02-03","cited_by_count":3,"area":null},{"id":"2201.12955","title":"Optimal Regret Is Achievable with Bounded Approximate Inference Error: An Enhanced Bayesian Upper Confidence Bound Framework","created":"2022-01-31","cited_by_count":2,"area":null},{"id":"2211.14426","title":"A Critical Review of Traffic Signal Control and A Novel Unified View of Reinforcement Learning and Model Predictive Control Approaches for Adaptive Traffic Signal Control","created":"2022-11-26","cited_by_count":2,"area":null},{"id":"2309.16109","title":"Feature Normalization Prevents Collapse of Non-contrastive Learning Dynamics","created":"2023-09-28","cited_by_count":2,"area":null},{"id":"2303.07287","title":"Tight Non-asymptotic Inference via Sub-Gaussian Intrinsic Moment Norm","created":"2023-03-13","cited_by_count":1,"area":null},{"id":"2505.12250","title":"Not All Documents Are What You Need for Extracting Instruction Tuning Data","created":"2025-05-18","cited_by_count":1,"area":null},{"id":"2512.12572","title":"On the Accuracy of Newton Step and Influence Function Data Attributions","created":"2025-12-14","cited_by_count":1,"area":null},{"id":"2106.08477","title":"Fundamental Limits of Reinforcement Learning in Environment with Endogeneous and Exogeneous Uncertainty","created":"2021-06-15","cited_by_count":0,"area":null},{"id":"2107.08383","title":"GuideBoot: Guided Bootstrap for Deep Contextual Bandits","created":"2021-07-18","cited_by_count":0,"area":null},{"id":"2110.08720","title":"Centroid Approximation for Bootstrap: Improving Particle Quality at Inference","created":"2021-10-17","cited_by_count":0,"area":null},{"id":"2202.10008","title":"Double Thompson Sampling in Finite stochastic Games","created":"2022-02-21","cited_by_count":0,"area":null},{"id":"2208.09819","title":"Robust Tests in Online Decision-Making","created":"2022-08-21","cited_by_count":0,"area":null},{"id":"2312.15595","title":"Zero-Inflated Bandits","created":"2023-12-25","cited_by_count":0,"area":null},{"id":"2603.07437","title":"Cost-Driven Representation Learning for Linear Quadratic Gaussian Control: Part II","created":"2026-03-08","cited_by_count":0,"area":null}],"next_cursor":null}