{"total":26,"rows":[{"id":"2201.10142","title":"Almost Optimal Variance-Constrained Best Arm Identification","created":"2022-01-25","cited_by_count":16,"area":null},{"id":"2406.07451","title":"A Multi-Armed Bandit Approach to Online Selection and Evaluation of Generative Models","created":"2024-06-11","cited_by_count":13,"area":null},{"id":"2108.11345","title":"A Unifying Theory of Thompson Sampling for Continuous Risk-Averse Bandits","created":"2021-08-25","cited_by_count":9,"area":null},{"id":"2304.04341","title":"Regret Distribution in Stochastic Bandits: Optimal Trade-off between Expectation and Tail Risk","created":"2023-04-10","cited_by_count":9,"area":null},{"id":"2205.05843","title":"A Survey of Risk-Aware Multi-Armed Bandits","created":"2022-05-12","cited_by_count":8,"area":null},{"id":"2105.14586","title":"Kolmogorov-Smirnov Test-Based Actively-Adaptive Thompson Sampling for Non-Stationary Bandits","created":"2021-05-30","cited_by_count":4,"area":null},{"id":"2206.03019","title":"The Survival Bandit Problem","created":"2022-06-07","cited_by_count":4,"area":null},{"id":"2303.09033","title":"Only Pay for What Is Uncertain: Variance-Adaptive Thompson Sampling","created":"2023-03-16","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":"2210.13573","title":"Conditionally Risk-Averse Contextual Bandits","created":"2022-10-24","cited_by_count":2,"area":null},{"id":"2406.06552","title":"Optimizing Sharpe Ratio: Risk-Adjusted Decision-Making in Multi-Armed Bandits","created":"2024-05-28","cited_by_count":2,"area":null},{"id":"2603.23140","title":"DAK-UCB: Diversity-Aware Prompt Routing for LLMs and Generative Models","created":"2026-03-24","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":"2505.11985","title":"Variance-Optimal Arm Selection: Misallocation Minimization and Best Arm Identification","created":"2025-05-17","cited_by_count":1,"area":null},{"id":"2508.13749","title":"Order Optimal Regret Bounds for Sharpe Ratio Optimization under Thompson Sampling","created":"2025-08-19","cited_by_count":1,"area":null},{"id":"2508.15454","title":"Mini-Batch Robustness Verification of Deep Neural Networks","created":"2025-08-21","cited_by_count":1,"area":null},{"id":"2106.08187","title":"Thompson Sampling for Unimodal Bandits","created":"2021-06-15","cited_by_count":0,"area":null},{"id":"2303.03348","title":"Thompson Sampling for Linear Bandit Problems with Normal-Gamma Priors","created":"2023-03-06","cited_by_count":0,"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":"2506.14479","title":"Adaptive Data Augmentation for Thompson Sampling","created":"2025-06-17","cited_by_count":0,"area":null},{"id":"2602.15972","title":"Fast Online Learning with Gaussian Prior-Driven Hierarchical Unimodal Thompson Sampling","created":"2026-02-17","cited_by_count":0,"area":null},{"id":"2606.09191","title":"Asymptotic Optimality of Thompson Sampling for Risk-Averse Bandits with Sub-Gaussian Rewards","created":"2026-06-08","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}