{"total":30,"rows":[{"id":"2107.06196","title":"No Regrets for Learning the Prior in Bandits","created":"2021-07-13","cited_by_count":30,"area":null},{"id":"2101.08534","title":"Efficient Pure Exploration for Combinatorial Bandits with Semi-Bandit Feedback","created":"2021-01-21","cited_by_count":21,"area":null},{"id":"2110.14622","title":"Heterogeneous Multi-player Multi-armed Bandits: Closing the Gap and Generalization","created":"2021-10-27","cited_by_count":18,"area":null},{"id":"2101.07957","title":"Near-Optimal Regret Bounds for Contextual Combinatorial Semi-Bandits with Linear Payoff Functions","created":"2021-01-20","cited_by_count":9,"area":null},{"id":"2206.00494","title":"Incentivizing Combinatorial Bandit Exploration","created":"2022-06-01","cited_by_count":9,"area":null},{"id":"2312.15427","title":"Semi-Bandit Learning for Monotone Stochastic Optimization","created":"2023-12-24","cited_by_count":8,"area":null},{"id":"2408.11202","title":"Effective Off-Policy Evaluation and Learning in Contextual Combinatorial Bandits","created":"2024-08-20","cited_by_count":8,"area":null},{"id":"2111.04295","title":"The Hardness Analysis of Thompson Sampling for Combinatorial Semi-bandits with Greedy Oracle","created":"2021-11-08","cited_by_count":7,"area":null},{"id":"2206.08776","title":"Multiple-Play Stochastic Bandits with Shareable Finite-Capacity Arms","created":"2022-06-17","cited_by_count":6,"area":null},{"id":"2410.05856","title":"Stochastic Bandits for Egalitarian Assignment","created":"2024-10-08","cited_by_count":4,"area":null},{"id":"2405.17968","title":"Matroid Semi-Bandits in Sublinear Time","created":"2024-05-28","cited_by_count":3,"area":null},{"id":"2102.00321","title":"Recurrent Submodular Welfare and Matroid Blocking Bandits","created":"2021-01-30","cited_by_count":2,"area":null},{"id":"2110.02248","title":"Contextual Combinatorial Bandits with Changing Action Sets via Gaussian Processes","created":"2021-10-05","cited_by_count":2,"area":null},{"id":"2310.05308","title":"Adversarial Attacks on Combinatorial Multi-Armed Bandits","created":"2023-10-08","cited_by_count":2,"area":null},{"id":"2402.13338","title":"Incentivized Exploration via Filtered Posterior Sampling","created":"2024-02-20","cited_by_count":2,"area":null},{"id":"2504.07307","title":"Follow-the-Perturbed-Leader Approaches Best-of-Both-Worlds for the m-Set Semi-Bandit Problems","created":"2025-04-09","cited_by_count":2,"area":null},{"id":"2207.03091","title":"Online SuBmodular + SuPermodular (BP) Maximization with Bandit Feedback","created":"2022-07-07","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":"2506.12490","title":"Note on Follow-the-Perturbed-Leader in Combinatorial Semi-Bandit Problems","created":"2025-06-14","cited_by_count":1,"area":null},{"id":"2401.06135","title":"A Distributed Neural Linear Thompson Sampling Framework to Achieve URLLC in Industrial IoT","created":"2023-11-21","cited_by_count":0,"area":null},{"id":"2405.00080","title":"Recommenadation aided Caching using Combinatorial Multi-armed Bandits","created":"2024-04-30","cited_by_count":0,"area":null},{"id":"2410.13109","title":"Latency-Aware Contextual Bandit: Application to Cryo-EM Data Collection","created":"2024-10-17","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":"2511.03074","title":"Online Learning to Rank under Corruption: A Robust Cascading Bandits Approach","created":"2025-11-04","cited_by_count":0,"area":null},{"id":"2512.00605","title":"Efficient Matroid Bandit Linear Optimization Leveraging Unimodality","created":"2025-11-29","cited_by_count":0,"area":null},{"id":"2512.21626","title":"Multiple-play Stochastic Bandits with Prioritized Arm Capacity Sharing","created":"2025-12-25","cited_by_count":0,"area":null},{"id":"2602.02087","title":"Efficient Swap Regret Minimization in Combinatorial Bandits","created":"2026-02-02","cited_by_count":0,"area":null},{"id":"2602.24231","title":"Adaptive Combinatorial Experimental Design: Pareto Optimality for Decision-Making and Inference","created":"2026-02-27","cited_by_count":0,"area":null},{"id":"2605.03493","title":"Bandits on graphs and structures","created":"2026-05-05","cited_by_count":0,"area":null},{"id":"2606.18438","title":"Sequential Hiring of Contingent Workers Through Learning-Based Optimization","created":"2026-06-16","cited_by_count":0,"area":null}],"next_cursor":null}