{"total":31,"rows":[{"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":"2211.16275","title":"A survey on multi-player bandits","created":"2022-11-29","cited_by_count":19,"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":"2202.13227","title":"Towards Scalable and Robust Structured Bandits: A Meta-Learning Framework","created":"2022-02-26","cited_by_count":11,"area":null},{"id":"2204.12048","title":"Thompson Sampling for Bandit Learning in Matching Markets","created":"2022-04-26","cited_by_count":10,"area":null},{"id":"2401.11665","title":"Accelerating Approximate Thompson Sampling with Underdamped Langevin Monte Carlo","created":"2024-01-22","cited_by_count":10,"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":"2101.01086","title":"Be Greedy in Multi-Armed Bandits","created":"2021-01-04","cited_by_count":7,"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":"2302.11182","title":"When Combinatorial Thompson Sampling meets Approximation Regret","created":"2023-02-22","cited_by_count":6,"area":null},{"id":"2503.07555","title":"Graph-Dependent Regret Bounds in Multi-Armed Bandits with Interference","created":"2025-03-10","cited_by_count":5,"area":null},{"id":"2102.05502","title":"On the Suboptimality of Thompson Sampling in High Dimensions","created":"2021-02-10","cited_by_count":4,"area":null},{"id":"2104.05781","title":"Censored Semi-Bandits for Resource Allocation","created":"2021-04-12","cited_by_count":4,"area":null},{"id":"2108.00230","title":"Pure Exploration and Regret Minimization in Matching Bandits","created":"2021-07-31","cited_by_count":4,"area":null},{"id":"2206.09150","title":"Thompson Sampling for (Combinatorial) Pure Exploration","created":"2022-06-18","cited_by_count":4,"area":null},{"id":"2402.15171","title":"Towards Efficient and Optimal Covariance-Adaptive Algorithms for Combinatorial Semi-Bandits","created":"2024-02-23","cited_by_count":3,"area":null},{"id":"2405.17968","title":"Matroid Semi-Bandits in Sublinear Time","created":"2024-05-28","cited_by_count":3,"area":null},{"id":"2206.04091","title":"Uplifting Bandits","created":"2022-06-08","cited_by_count":2,"area":null},{"id":"2206.00466","title":"An $\\alpha$-No-Regret Algorithm For Graphical Bilinear Bandits","created":"2022-06-01","cited_by_count":1,"area":null},{"id":"2410.05441","title":"Thompson Sampling For Combinatorial Bandits: Polynomial Regret and Mismatched Sampling Paradox","created":"2024-10-07","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":"2208.01511","title":"Unimodal Mono-Partite Matching in a Bandit Setting","created":"2022-08-02","cited_by_count":0,"area":null},{"id":"2212.11603","title":"Sequential Decision Problems with Weak Feedback","created":"2022-12-22","cited_by_count":0,"area":null},{"id":"2305.19691","title":"Constant or logarithmic regret in asynchronous multiplayer bandits","created":"2023-05-31","cited_by_count":0,"area":null},{"id":"2410.08578","title":"Logarithmic Regret for Unconstrained Submodular Maximization Stochastic Bandit","created":"2024-10-11","cited_by_count":0,"area":null},{"id":"2410.10679","title":"Combinatorial Multi-armed Bandits: Arm Selection via Group Testing","created":"2024-10-14","cited_by_count":0,"area":null},{"id":"2509.09933","title":"Multi-Play Combinatorial Semi-Bandit Problem","created":"2025-09-12","cited_by_count":0,"area":null},{"id":"2604.14908","title":"Multi-User mmWave Beam and Rate Adaptation via Combinatorial Satisficing Bandits","created":"2026-04-16","cited_by_count":0,"area":null},{"id":"2604.19672","title":"Budgeted Online Influence Maximization","created":"2026-04-21","cited_by_count":0,"area":null},{"id":"2605.09277","title":"Worst-Case Regret Bounds for Combinatorial Thompson Sampling in Sleeping Semi-Bandits","created":"2026-05-10","cited_by_count":0,"area":null},{"id":"2610.20514","title":"Bayesian Learning to Select Fair Classifiers","created":"2026-10-14","cited_by_count":0,"area":null}],"next_cursor":null}