{"total":21,"rows":[{"id":"2210.10768","title":"Anytime-valid off-policy inference for contextual bandits","created":"2022-10-19","cited_by_count":37,"area":null},{"id":"2201.04805","title":"Non-Stationary Representation Learning in Sequential Linear Bandits","created":"2022-01-13","cited_by_count":13,"area":null},{"id":"2311.05794","title":"An Experimental Design for Anytime-Valid Causal Inference on Multi-Armed Bandits","created":"2023-11-09","cited_by_count":9,"area":null},{"id":"2412.03727","title":"Online Experimental Design With Estimation-Regret Trade-off Under Network Interference","created":"2024-12-04","cited_by_count":9,"area":null},{"id":"2203.02605","title":"Reinforcement Learning in Modern Biostatistics: Constructing Optimal Adaptive Interventions","created":"2022-03-04","cited_by_count":6,"area":null},{"id":"2307.07320","title":"Adaptive Linear Estimating Equations","created":"2023-07-14","cited_by_count":6,"area":null},{"id":"2410.05552","title":"Optimal Adaptive Experimental Design for Estimating Treatment Effect","created":"2024-10-07","cited_by_count":5,"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":"2201.04469","title":"Optimal Best Arm Identification in Two-Armed Bandits with a Fixed Budget under a Small Gap","created":"2022-01-12","cited_by_count":4,"area":null},{"id":"2412.08843","title":"Allocation Stability and Wald Inference under Variance-Aware UCB","created":"2024-12-12","cited_by_count":4,"area":null},{"id":"2605.10405","title":"Valid Best-Model Identification for LLM Evaluation via Low-Rank Factorization","created":"2026-05-11","cited_by_count":4,"area":null},{"id":"2209.07330","title":"Best Arm Identification with Contextual Information under a Small Gap","created":"2022-09-15","cited_by_count":3,"area":null},{"id":"2503.04855","title":"A characterization of sample adaptivity in UCB data","created":"2025-03-06","cited_by_count":2,"area":null},{"id":"2602.06014","title":"Optimism Stabilizes Thompson Sampling for Adaptive Inference","created":"2026-02-05","cited_by_count":2,"area":null},{"id":"2205.03820","title":"Some performance considerations when using multi-armed bandit algorithms in the presence of missing data","created":"2022-05-08","cited_by_count":1,"area":null},{"id":"2208.11747","title":"Entropy Regularization for Population Estimation","created":"2022-08-24","cited_by_count":1,"area":null},{"id":"2510.07646","title":"Design-Based Bandits Under Network Interference: Trade-Off Between Regret and Statistical Inference","created":"2025-10-09","cited_by_count":1,"area":null},{"id":"2310.19683","title":"An Online Bootstrap for Time Series","created":"2023-10-30","cited_by_count":0,"area":null},{"id":"2404.08671","title":"Navigating the Evaluation Funnel to Optimize Iteration Speed for Recommender Systems","created":"2024-04-03","cited_by_count":0,"area":null},{"id":"2501.03999","title":"Adaptive Experiments Under Data Sparse Settings: Applications for Educational Platforms","created":"2025-01-07","cited_by_count":0,"area":null},{"id":"2610.06213","title":"Sampling Allocation of LinUCB: Optimal Design Limits in the Small-Gap Regime","created":"2026-10-05","cited_by_count":0,"area":null}],"next_cursor":null}