{"total":37,"rows":[{"id":"2107.06196","title":"No Regrets for Learning the Prior in Bandits","created":"2021-07-13","cited_by_count":30,"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":"2303.17110","title":"Contextual Combinatorial Bandits with Probabilistically Triggered Arms","created":"2023-03-30","cited_by_count":18,"area":null},{"id":"2106.04819","title":"Contextual Recommendations and Low-Regret Cutting-Plane Algorithms","created":"2021-06-09","cited_by_count":15,"area":null},{"id":"2208.14837","title":"Batch-Size Independent Regret Bounds for Combinatorial Semi-Bandits with Probabilistically Triggered Arms or Independent Arms","created":"2022-08-31","cited_by_count":15,"area":null},{"id":"2203.12577","title":"Minimax Regret for Cascading Bandits","created":"2022-03-23","cited_by_count":10,"area":null},{"id":"2402.01845","title":"Multi-Armed Bandits with Interference","created":"2024-02-02","cited_by_count":10,"area":null},{"id":"2412.03727","title":"Online Experimental Design With Estimation-Regret Trade-off Under Network Interference","created":"2024-12-04","cited_by_count":9,"area":null},{"id":"2103.00368","title":"PairRank: Online Pairwise Learning to Rank by Divide-and-Conquer","created":"2021-02-28","cited_by_count":6,"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":"2305.17071","title":"Adversarial Attacks on Online Learning to Rank with Click Feedback","created":"2023-05-26","cited_by_count":6,"area":null},{"id":"2305.19218","title":"Adversarial Attacks on Online Learning to Rank with Stochastic Click Models","created":"2023-05-30","cited_by_count":6,"area":null},{"id":"2402.16312","title":"Federated Contextual Cascading Bandits with Asynchronous Communication and Heterogeneous Users","created":"2024-02-26","cited_by_count":6,"area":null},{"id":"2501.19300","title":"Offline Learning for Combinatorial Multi-armed Bandits","created":"2025-01-31","cited_by_count":5,"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":"2410.05856","title":"Stochastic Bandits for Egalitarian Assignment","created":"2024-10-08","cited_by_count":4,"area":null},{"id":"2105.10625","title":"Combinatorial Blocking Bandits with Stochastic Delays","created":"2021-05-22","cited_by_count":3,"area":null},{"id":"2305.16074","title":"Combinatorial Bandits for Maximum Value Reward Function under Max Value-Index Feedback","created":"2023-05-25","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":"2311.04528","title":"Bandit Learning to Rank with Position-Based Click Models: Personalized and Equal Treatments","created":"2023-11-08","cited_by_count":2,"area":null},{"id":"2105.11126","title":"Cascading Bandit under Differential Privacy","created":"2021-05-24","cited_by_count":1,"area":null},{"id":"2109.02519","title":"Online Learning of Independent Cascade Models with Node-level Feedback","created":"2021-09-06","cited_by_count":1,"area":null},{"id":"2201.06658","title":"Learning Neural Ranking Models Online from Implicit User Feedback","created":"2022-01-17","cited_by_count":1,"area":null},{"id":"2405.12439","title":"No-Regret M${}^{\\natural}$-Concave Function Maximization: Stochastic Bandit Algorithms and Hardness of Adversarial Full-Information Setting","created":"2024-05-21","cited_by_count":1,"area":null},{"id":"2510.07646","title":"Design-Based Bandits Under Network Interference: Trade-Off Between Regret and Statistical Inference","created":"2025-10-09","cited_by_count":1,"area":null},{"id":"2106.01624","title":"Sleeping Combinatorial Bandits","created":"2021-06-03","cited_by_count":0,"area":null},{"id":"2106.03546","title":"On Learning to Rank Long Sequences with Contextual Bandits","created":"2021-06-07","cited_by_count":0,"area":null},{"id":"2207.11545","title":"Learning to Sell a Focal-ancillary Combination","created":"2022-07-23","cited_by_count":0,"area":null},{"id":"2208.01515","title":"UniRank: Unimodal Bandit Algorithm for Online Ranking","created":"2022-08-02","cited_by_count":0,"area":null},{"id":"2305.01202","title":"Exploration of Unranked Items in Safe Online Learning to Re-Rank","created":"2023-05-02","cited_by_count":0,"area":null},{"id":"2502.13467","title":"On the Sublinear Regret of Continuous K-Max Bandits","created":"2025-02-19","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":"2509.22855","title":"Observation-Free Attacks on Online Learning to Rank","created":"2025-09-26","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":"2607.15440","title":"Stochastic Reset Pathfinding: Path-Level Regret for Cascading Bandits over Graph Paths","created":"2026-07-16","cited_by_count":0,"area":null},{"id":"2608.11873","title":"DCM Bandits: Multiplayer Information Asymmetric Cascading Bandits for Multiple Clicks","created":"2026-08-12","cited_by_count":0,"area":null}],"next_cursor":null}