{"total":39,"rows":[{"id":"2107.01509","title":"Bayesian decision-making under misspecified priors with applications to meta-learning","created":"2021-07-03","cited_by_count":44,"area":null},{"id":"2202.01454","title":"Deep Hierarchy in Bandits","created":"2022-02-03","cited_by_count":19,"area":null},{"id":"2302.01324","title":"Randomized Greedy Learning for Non-monotone Stochastic Submodular Maximization Under Full-bandit Feedback","created":"2023-02-02","cited_by_count":19,"area":null},{"id":"2106.05608","title":"Thompson Sampling with a Mixture Prior","created":"2021-06-10","cited_by_count":16,"area":null},{"id":"2205.15124","title":"Mixed-Effect Thompson Sampling","created":"2022-05-30","cited_by_count":14,"area":null},{"id":"2107.13078","title":"A Payload Optimization Method for Federated Recommender Systems","created":"2021-07-27","cited_by_count":10,"area":null},{"id":"2103.02729","title":"Linear Bandit Algorithms with Sublinear Time Complexity","created":"2021-03-03","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":"2111.02314","title":"Online Learning of Energy Consumption for Navigation of Electric Vehicles","created":"2021-11-03","cited_by_count":7,"area":null},{"id":"2202.12431","title":"Thompson Sampling with Unrestricted Delays","created":"2022-02-24","cited_by_count":6,"area":null},{"id":"2209.02211","title":"Multi-Armed Bandits with Self-Information Rewards","created":"2022-09-06","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":"2210.00340","title":"Speed Up the Cold-Start Learning in Two-Sided Bandits with Many Arms","created":"2022-10-01","cited_by_count":4,"area":null},{"id":"2305.03263","title":"Bayesian Reinforcement Learning with Limited Cognitive Load","created":"2023-05-05","cited_by_count":4,"area":null},{"id":"2407.14879","title":"Thompson Sampling Itself is Differentially Private","created":"2024-07-20","cited_by_count":4,"area":null},{"id":"2302.01543","title":"Multiplier Bootstrap-based Exploration","created":"2023-02-03","cited_by_count":3,"area":null},{"id":"2303.09033","title":"Only Pay for What Is Uncertain: Variance-Adaptive Thompson Sampling","created":"2023-03-16","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":"2311.02085","title":"Preference Elicitation with Soft Attributes in Interactive Recommendation","created":"2023-10-22","cited_by_count":3,"area":null},{"id":"2201.12955","title":"Optimal Regret Is Achievable with Bounded Approximate Inference Error: An Enhanced Bayesian Upper Confidence Bound Framework","created":"2022-01-31","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":"2104.05613","title":"An Efficient Algorithm for Deep Stochastic Contextual Bandits","created":"2021-04-12","cited_by_count":1,"area":null},{"id":"2203.08082","title":"Regenerative Particle Thompson Sampling","created":"2022-03-15","cited_by_count":1,"area":null},{"id":"2210.06302","title":"Maximum entropy exploration in contextual bandits with neural networks and energy based models","created":"2022-10-12","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":"2106.08187","title":"Thompson Sampling for Unimodal Bandits","created":"2021-06-15","cited_by_count":0,"area":null},{"id":"2207.06917","title":"Online Bayesian Meta-Learning for Cognitive Tracking Radar","created":"2022-07-07","cited_by_count":0,"area":null},{"id":"2209.08197","title":"Thompson Sampling with Virtual Helping Agents","created":"2022-09-16","cited_by_count":0,"area":null},{"id":"2210.02259","title":"Cost Aware Asynchronous Multi-Agent Active Search","created":"2022-10-05","cited_by_count":0,"area":null},{"id":"2210.05789","title":"Trading Off Resource Budgets for Improved Regret Bounds","created":"2022-10-11","cited_by_count":0,"area":null},{"id":"2306.17329","title":"Kernel $\\epsilon$-Greedy for Multi-Armed Bandits with Covariates","created":"2023-06-29","cited_by_count":0,"area":null},{"id":"2310.00642","title":"From Bandits Model to Deep Deterministic Policy Gradient, Reinforcement Learning with Contextual Information","created":"2023-10-01","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":"2501.03877","title":"Stochastically Constrained Best Arm Identification with Thompson Sampling","created":"2025-01-07","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":"2605.10018","title":"The Value of Mechanistic Priors in Sequential Decision Making","created":"2026-05-11","cited_by_count":0,"area":null},{"id":"2606.01655","title":"MINTS: Minimalist Thompson Sampling","created":"2026-06-01","cited_by_count":0,"area":null},{"id":"2607.16986","title":"Periodic Bootstrap Thompson Sampling For Periodically Non-Stationary Bandit Problems","created":"2026-07-18","cited_by_count":0,"area":null},{"id":"2608.16375","title":"Multinomial Subset Routing with Sum-Max Rewards and Operational Constraints","created":"2026-08-17","cited_by_count":0,"area":null}],"next_cursor":null}