{"total":19,"rows":[{"id":"2310.00968","title":"Variance-Aware Regret Bounds for Stochastic Contextual Dueling Bandits","created":"2023-10-02","cited_by_count":22,"area":null},{"id":"2203.04510","title":"ReVar: Strengthening Policy Evaluation via Reduced Variance Sampling","created":"2022-03-09","cited_by_count":16,"area":null},{"id":"2105.03962","title":"Stochastic Multi-Armed Bandits with Control Variates","created":"2021-05-09","cited_by_count":7,"area":null},{"id":"2505.21372","title":"Improving LLM-based Global Optimization with Search Space Partitioning","created":"2025-05-27","cited_by_count":6,"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":"2301.12357","title":"SPEED: Experimental Design for Policy Evaluation in Linear Heteroscedastic Bandits","created":"2023-01-29","cited_by_count":3,"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":"2205.13689","title":"Safety Aware Changepoint Detection for Piecewise i.i.d. Bandits","created":"2022-05-27","cited_by_count":2,"area":null},{"id":"2304.14989","title":"Kullback-Leibler Maillard Sampling for Multi-armed Bandits with Bounded Rewards","created":"2023-04-28","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":"2412.07216","title":"Learnable Sparse Customization in Heterogeneous Edge Computing","created":"2024-12-10","cited_by_count":2,"area":null},{"id":"2511.02123","title":"Variance-Aware Feel-Good Thompson Sampling for Contextual Bandits","created":"2025-11-03","cited_by_count":2,"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":"2510.27001","title":"A Framework for Fair Evaluation of Variance-Aware Bandit Algorithms","created":"2025-10-30","cited_by_count":1,"area":null},{"id":"2604.13738","title":"Covariance-adapting algorithm for semi-bandits with application to sparse rewards","created":"2026-04-15","cited_by_count":1,"area":null},{"id":"2503.05662","title":"On Mitigating Affinity Bias through Bandits with Evolving Biased Feedback","created":"2025-03-07","cited_by_count":0,"area":null},{"id":"2508.06247","title":"Near-Optimal Regret for Efficient Stochastic Combinatorial Semi-Bandits","created":"2025-08-08","cited_by_count":0,"area":null},{"id":"2511.04590","title":"Complexity as Advantage: A Regret-Based Perspective on Emergent Structure","created":"2025-11-06","cited_by_count":0,"area":null},{"id":"2603.02100","title":"Stochastic Multi-Armed Bandits with Limited Control Variates","created":"2026-03-02","cited_by_count":0,"area":null}],"next_cursor":null}