{"total":17,"rows":[{"id":"2302.04452","title":"An Information-Theoretic Analysis of Nonstationary Bandit Learning","created":"2023-02-09","cited_by_count":11,"area":null},{"id":"2302.12202","title":"A Definition of Non-Stationary Bandits","created":"2023-02-23","cited_by_count":9,"area":null},{"id":"2402.15411","title":"Optimistic Information Directed Sampling","created":"2024-02-23","cited_by_count":7,"area":null},{"id":"2502.07064","title":"Contextual Thompson Sampling via Generation of Missing Data","created":"2025-02-10","cited_by_count":6,"area":null},{"id":"2304.13593","title":"Thompson Sampling Regret Bounds for Contextual Bandits with sub-Gaussian rewards","created":"2023-04-26","cited_by_count":5,"area":null},{"id":"2306.01990","title":"Incentivizing Exploration with Linear Contexts and Combinatorial Actions","created":"2023-06-03","cited_by_count":5,"area":null},{"id":"2405.16581","title":"On Bits and Bandits: Quantifying the Regret-Information Trade-off","created":"2024-05-26","cited_by_count":3,"area":null},{"id":"2401.11565","title":"Thompson Sampling for Stochastic Bandits with Noisy Contexts: An Information-Theoretic Regret Analysis","created":"2024-01-21","cited_by_count":2,"area":null},{"id":"2510.01620","title":"Learning to Decide with Just Enough: Information-Theoretic Context Summarization for CMDPs","created":"2025-10-02","cited_by_count":2,"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":"2412.02861","title":"An Information-Theoretic Analysis of Thompson Sampling for Logistic Bandits","created":"2024-12-03","cited_by_count":1,"area":null},{"id":"2510.24234","title":"Sparse Optimistic Information Directed Sampling","created":"2025-10-28","cited_by_count":1,"area":null},{"id":"2602.07767","title":"BFTS: Thompson Sampling with Bayesian Additive Regression Trees","created":"2026-02-08","cited_by_count":1,"area":null},{"id":"2403.03361","title":"Chained Information-Theoretic bounds and Tight Regret Rate for Linear Bandit Problems","created":"2024-03-05","cited_by_count":0,"area":null},{"id":"2502.02140","title":"An Information-Theoretic Analysis of Thompson Sampling with Infinite Action Spaces","created":"2025-02-04","cited_by_count":0,"area":null},{"id":"2503.16382","title":"Sparse Nonparametric Contextual Bandits","created":"2025-03-20","cited_by_count":0,"area":null},{"id":"2508.13411","title":"Decentralized Contextual Bandits with Network Adaptivity","created":"2025-08-19","cited_by_count":0,"area":null}],"next_cursor":null}