{"total":12,"rows":[{"id":"2110.08627","title":"Achieving the Pareto Frontier of Regret Minimization and Best Arm Identification in Multi-Armed Bandits","created":"2021-10-16","cited_by_count":13,"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":"2203.12577","title":"Minimax Regret for Cascading Bandits","created":"2022-03-23","cited_by_count":10,"area":null},{"id":"2302.01543","title":"Multiplier Bootstrap-based Exploration","created":"2023-02-03","cited_by_count":3,"area":null},{"id":"2301.10651","title":"Overcoming Prior Misspecification in Online Learning to Rank","created":"2023-01-25","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":"2308.08650","title":"AdaptEx: A Self-Service Contextual Bandit Platform","created":"2023-08-08","cited_by_count":1,"area":null},{"id":"2305.18333","title":"Ranking with Popularity Bias: User Welfare under Self-Amplification Dynamics","created":"2023-05-24","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":"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":"2511.10938","title":"Cascading Bandits With Feedback","created":"2025-11-14","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}