{"total":31,"rows":[{"id":"2206.03611","title":"FedPop: A Bayesian Approach for Personalised Federated Learning","created":"2022-06-07","cited_by_count":35,"area":null},{"id":"2202.01454","title":"Deep Hierarchy in Bandits","created":"2022-02-03","cited_by_count":19,"area":null},{"id":"2205.15124","title":"Mixed-Effect Thompson Sampling","created":"2022-05-30","cited_by_count":14,"area":null},{"id":"2211.08572","title":"Bayesian Fixed-Budget Best-Arm Identification","created":"2022-11-15","cited_by_count":13,"area":null},{"id":"2310.02717","title":"Online Clustering of Bandits with Misspecified User Models","created":"2023-10-04","cited_by_count":12,"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":"2202.12888","title":"Meta-Learning for Simple Regret Minimization","created":"2022-02-25","cited_by_count":10,"area":null},{"id":"2209.06129","title":"Hierarchical Conversational Preference Elicitation with Bandit Feedback","created":"2022-09-06","cited_by_count":10,"area":null},{"id":"2212.04720","title":"Multi-Task Off-Policy Learning from Bandit Feedback","created":"2022-12-09","cited_by_count":9,"area":null},{"id":"2210.12262","title":"Group Distributionally Robust Reinforcement Learning with Hierarchical Latent Variables","created":"2022-10-21","cited_by_count":7,"area":null},{"id":"2408.05586","title":"Meta Clustering of Neural Bandits","created":"2024-08-10","cited_by_count":7,"area":null},{"id":"2505.13355","title":"Survey: Multi-Armed Bandits Meet Large Language Models","created":"2025-05-19","cited_by_count":7,"area":null},{"id":"2402.17739","title":"reBandit: Random Effects based Online RL algorithm for Reducing Cannabis Use","created":"2024-02-27","cited_by_count":6,"area":null},{"id":"2310.07518","title":"Exploiting Causal Graph Priors with Posterior Sampling for Reinforcement Learning","created":"2023-10-11","cited_by_count":5,"area":null},{"id":"2205.06326","title":"Multi-Environment Meta-Learning in Stochastic Linear Bandits","created":"2022-05-12","cited_by_count":4,"area":null},{"id":"2210.14483","title":"Robust Contextual Linear Bandits","created":"2022-10-26","cited_by_count":4,"area":null},{"id":"2210.15513","title":"Lifelong Bandit Optimization: No Prior and No Regret","created":"2022-10-27","cited_by_count":4,"area":null},{"id":"2402.05878","title":"Prior-Dependent Allocations for Bayesian Fixed-Budget Best-Arm Identification in Structured Bandits","created":"2024-02-08","cited_by_count":4,"area":null},{"id":"2403.00116","title":"Federated Linear Contextual Bandits with Heterogeneous Clients","created":"2024-02-29","cited_by_count":4,"area":null},{"id":"2206.08556","title":"Thompson Sampling for Robust Transfer in Multi-Task Bandits","created":"2022-06-17","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":"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":"2502.01226","title":"Adaptive Prior Selection in Gaussian Process Bandits with Thompson Sampling","created":"2025-02-03","cited_by_count":2,"area":null},{"id":"2504.04505","title":"A Classification View on Meta Learning Bandits","created":"2025-04-06","cited_by_count":1,"area":null},{"id":"2510.26284","title":"Empirical Bayesian Multi-Bandit Learning","created":"2025-10-30","cited_by_count":1,"area":null},{"id":"2306.09136","title":"Finite-Time Logarithmic Bayes Regret Upper Bounds","created":"2023-06-15","cited_by_count":0,"area":null},{"id":"2506.15943","title":"On the optimal regret of collaborative personalized linear bandits","created":"2025-06-19","cited_by_count":0,"area":null},{"id":"2605.29788","title":"Certified Policy Optimisation for Nested Causal Bandits via PAC-Bayes Risk","created":"2026-05-28","cited_by_count":0,"area":null},{"id":"2606.23414","title":"Leveraging Similarities in Multi-Armed Bandits","created":"2026-06-22","cited_by_count":0,"area":null},{"id":"2609.37800","title":"Challenges and Solutions for Bandits in the Wild: Warm-Started Mixture Bandits for Cross-Cohort Slate Recommendation","created":"2026-09-29","cited_by_count":0,"area":null},{"id":"2610.17203","title":"Online LLM Personalization from Pairwise Preferences Across Users","created":"2026-10-12","cited_by_count":0,"area":null}],"next_cursor":null}