{"total":21,"rows":[{"id":"2110.14177","title":"Federated Linear Contextual Bandits","created":"2021-10-27","cited_by_count":61,"area":null},{"id":"2106.02029","title":"Off-Policy Evaluation via Adaptive Weighting with Data from Contextual Bandits","created":"2021-06-03","cited_by_count":40,"area":null},{"id":"2106.00418","title":"Post-Contextual-Bandit Inference","created":"2021-06-01","cited_by_count":32,"area":null},{"id":"2102.13202","title":"Online Multi-Armed Bandits with Adaptive Inference","created":"2021-02-25","cited_by_count":22,"area":null},{"id":"2105.02344","title":"Policy Learning with Adaptively Collected Data","created":"2021-05-05","cited_by_count":21,"area":null},{"id":"2106.01723","title":"Risk Minimization from Adaptively Collected Data: Guarantees for Supervised and Policy Learning","created":"2021-06-03","cited_by_count":10,"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":"2204.11910","title":"Integrating Reward Maximization and Population Estimation: Sequential Decision-Making for Internal Revenue Service Audit Selection","created":"2022-04-25","cited_by_count":5,"area":null},{"id":"2108.00236","title":"Debiasing Samples from Online Learning Using Bootstrap","created":"2021-07-31","cited_by_count":3,"area":null},{"id":"2202.06657","title":"The Impact of Batch Learning in Stochastic Linear Bandits","created":"2022-02-14","cited_by_count":3,"area":null},{"id":"2202.13448","title":"Federated Online Sparse Decision Making","created":"2022-02-27","cited_by_count":3,"area":null},{"id":"2111.02071","title":"The Impact of Batch Learning in Stochastic Bandits","created":"2021-11-03","cited_by_count":1,"area":null},{"id":"2209.06128","title":"A Scalable Recommendation Engine for New Users and Items","created":"2022-09-06","cited_by_count":1,"area":null},{"id":"2308.09248","title":"Active and Passive Causal Inference Learning","created":"2023-08-18","cited_by_count":1,"area":null},{"id":"2308.15107","title":"Stochastic Graph Bandit Learning with Side-Observations","created":"2023-08-29","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":"2205.04528","title":"Selectively Contextual Bandits","created":"2022-05-09","cited_by_count":0,"area":null},{"id":"2209.03224","title":"Dual Instrumental Method for Confounded Kernelized Bandits","created":"2022-09-07","cited_by_count":0,"area":null},{"id":"2301.12571","title":"Bounded (O(1)) Regret Recommendation Learning via Synthetic Controls Oracle","created":"2023-01-29","cited_by_count":0,"area":null},{"id":"2508.13411","title":"Decentralized Contextual Bandits with Network Adaptivity","created":"2025-08-19","cited_by_count":0,"area":null},{"id":"2606.22639","title":"Statistical Inference for Misspecified Contextual Bandits","created":"2026-06-21","cited_by_count":0,"area":null}],"next_cursor":null}