{"total":20,"rows":[{"id":"2109.13595","title":"The Fragility of Optimized Bandit Algorithms","created":"2021-09-28","cited_by_count":17,"area":null},{"id":"2201.10142","title":"Almost Optimal Variance-Constrained Best Arm Identification","created":"2022-01-25","cited_by_count":16,"area":null},{"id":"2211.14768","title":"Constrained Pure Exploration Multi-Armed Bandits with a Fixed Budget","created":"2022-11-27","cited_by_count":9,"area":null},{"id":"2205.04134","title":"Federated Multi-Armed Bandits Under Byzantine Attacks","created":"2022-05-09","cited_by_count":6,"area":null},{"id":"2111.13415","title":"ESCADA: Efficient Safety and Context Aware Dose Allocation for Precision Medicine","created":"2021-11-26","cited_by_count":5,"area":null},{"id":"2206.03019","title":"The Survival Bandit Problem","created":"2022-06-07","cited_by_count":4,"area":null},{"id":"2503.08896","title":"Risk-sensitive Bandits: Arm Mixture Optimality and Regret-efficient Algorithms","created":"2025-03-11","cited_by_count":3,"area":null},{"id":"2102.12090","title":"Continuous Mean-Covariance Bandits","created":"2021-02-24","cited_by_count":2,"area":null},{"id":"2105.06960","title":"Thompson Sampling for Gaussian Entropic Risk Bandits","created":"2021-05-14","cited_by_count":2,"area":null},{"id":"2209.04356","title":"Risk-Averse Multi-Armed Bandits with Unobserved Confounders: A Case Study in Emotion Regulation in Mobile Health","created":"2022-09-09","cited_by_count":2,"area":null},{"id":"2210.13573","title":"Conditionally Risk-Averse Contextual Bandits","created":"2022-10-24","cited_by_count":2,"area":null},{"id":"2206.12463","title":"Risk-averse Contextual Multi-armed Bandit Problem with Linear Payoffs","created":"2022-06-24","cited_by_count":1,"area":null},{"id":"2208.02389","title":"Risk-Aware Linear Bandits: Theory and Applications in Smart Order Routing","created":"2022-08-04","cited_by_count":1,"area":null},{"id":"2301.13393","title":"Probably Anytime-Safe Stochastic Combinatorial Semi-Bandits","created":"2023-01-31","cited_by_count":1,"area":null},{"id":"2305.09626","title":"Balancing Risk and Reward: An Automated Phased Release Strategy","created":"2023-05-16","cited_by_count":0,"area":null},{"id":"2310.19821","title":"A Risk-Averse Framework for Non-Stationary Stochastic Multi-Armed Bandits","created":"2023-10-24","cited_by_count":0,"area":null},{"id":"2512.09850","title":"Conformal bandits: bringing statistical validity and reward efficiency under weak arm separability","created":"2025-12-10","cited_by_count":0,"area":null},{"id":"2602.20403","title":"Risk-Averse Wasserstein Distributionally Robust Online Learning","created":"2026-02-23","cited_by_count":0,"area":null},{"id":"2604.00241","title":"Softmax gradient policy for variance minimization and risk-averse multi armed bandits","created":"2026-03-31","cited_by_count":0,"area":null},{"id":"2608.01545","title":"Dominant Arm Identification with Mixing and Recycling Observed Samples","created":"2026-08-02","cited_by_count":0,"area":null}],"next_cursor":null}