{"total":20,"rows":[{"id":"2210.10768","title":"Anytime-valid off-policy inference for contextual bandits","created":"2022-10-19","cited_by_count":37,"area":null},{"id":"2302.07690","title":"Online Statistical Inference for Nonlinear Stochastic Approximation with Markovian Data","created":"2023-02-15","cited_by_count":20,"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":"2401.09346","title":"High Confidence Level Inference is Almost Free using Parallel Stochastic Optimization","created":"2024-01-17","cited_by_count":10,"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":"2302.12717","title":"Statistical Inference with Stochastic Gradient Methods under $\\phi$-mixing Data","created":"2023-02-24","cited_by_count":7,"area":null},{"id":"2308.01481","title":"Online covariance estimation for stochastic gradient descent under Markovian sampling","created":"2023-08-03","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":"2309.13278","title":"Distributional Shift-Aware Off-Policy Interval Estimation: A Unified Error Quantification Framework","created":"2023-09-23","cited_by_count":6,"area":null},{"id":"2406.13130","title":"Advancing Retail Data Science: Comprehensive Evaluation of Synthetic Data","created":"2024-06-19","cited_by_count":6,"area":null},{"id":"2110.15501","title":"Doubly Robust Interval Estimation for Optimal Policy Evaluation in Online Learning","created":"2021-10-29","cited_by_count":4,"area":null},{"id":"2310.02581","title":"Online Estimation and Inference for Robust Policy Evaluation in Reinforcement Learning","created":"2023-10-04","cited_by_count":4,"area":null},{"id":"2510.12375","title":"Improved Central Limit Theorem and Bootstrap Approximations for Linear Stochastic Approximation","created":"2025-10-14","cited_by_count":4,"area":null},{"id":"2211.03983","title":"Doubly Inhomogeneous Reinforcement Learning","created":"2022-11-08","cited_by_count":3,"area":null},{"id":"2506.12655","title":"Beyond Sin-Squared Error: Linear-Time Entrywise Uncertainty Quantification for Streaming PCA","created":"2025-06-14","cited_by_count":3,"area":null},{"id":"2505.11725","title":"CLT and Edgeworth Expansion for m-out-of-n Bootstrap Estimators of The Studentized Median","created":"2025-05-16","cited_by_count":2,"area":null},{"id":"2507.18118","title":"A Two-armed Bandit Framework for A/B Testing","created":"2025-07-24","cited_by_count":2,"area":null},{"id":"2406.04374","title":"Incentivized Exploration with Stochastic Covariates: A Two-Stage Mechanism Design for Recommender System","created":"2024-06-04","cited_by_count":1,"area":null},{"id":"2301.00927","title":"Deep Spectral Q-learning with Application to Mobile Health","created":"2023-01-03","cited_by_count":0,"area":null},{"id":"2310.19683","title":"An Online Bootstrap for Time Series","created":"2023-10-30","cited_by_count":0,"area":null}],"next_cursor":null}