{"total":59,"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":"2111.06929","title":"Hierarchical Bayesian Bandits","created":"2021-11-12","cited_by_count":35,"area":null},{"id":"2107.06196","title":"No Regrets for Learning the Prior in Bandits","created":"2021-07-13","cited_by_count":30,"area":null},{"id":"2108.06422","title":"Metadata-based Multi-Task Bandits with Bayesian Hierarchical Models","created":"2021-08-13","cited_by_count":24,"area":null},{"id":"2202.10066","title":"Multi-task Representation Learning with Stochastic Linear Bandits","created":"2022-02-21","cited_by_count":21,"area":null},{"id":"2202.01454","title":"Deep Hierarchy in Bandits","created":"2022-02-03","cited_by_count":19,"area":null},{"id":"2107.05320","title":"Metalearning Linear Bandits by Prior Update","created":"2021-07-12","cited_by_count":16,"area":null},{"id":"2202.13234","title":"Safe Exploration for Efficient Policy Evaluation and Comparison","created":"2022-02-26","cited_by_count":15,"area":null},{"id":"2205.15124","title":"Mixed-Effect Thompson Sampling","created":"2022-05-30","cited_by_count":14,"area":null},{"id":"2302.03319","title":"Leveraging Demonstrations to Improve Online Learning: Quality Matters","created":"2023-02-07","cited_by_count":13,"area":null},{"id":"2112.14233","title":"Multitask Learning and Bandits via Robust Statistics","created":"2021-12-28","cited_by_count":11,"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":"2202.07079","title":"Synthetically Controlled Bandits","created":"2022-02-14","cited_by_count":8,"area":null},{"id":"2202.13001","title":"Non-stationary Bandits and Meta-Learning with a Small Set of Optimal Arms","created":"2022-02-25","cited_by_count":8,"area":null},{"id":"2307.02295","title":"Meta-Learning Adversarial Bandit Algorithms","created":"2023-07-05","cited_by_count":8,"area":null},{"id":"2305.03784","title":"Neural Exploitation and Exploration of Contextual Bandits","created":"2023-05-05","cited_by_count":7,"area":null},{"id":"2306.06291","title":"Optimal Multitask Linear Regression and Contextual Bandits under Sparse Heterogeneity","created":"2023-06-09","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":"2205.15100","title":"Meta Representation Learning with Contextual Linear Bandits","created":"2022-05-30","cited_by_count":6,"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":"2205.14128","title":"Meta-Learning Adversarial Bandits","created":"2022-05-27","cited_by_count":5,"area":null},{"id":"2211.15129","title":"On the Sample Complexity of Representation Learning in Multi-task Bandits with Global and Local structure","created":"2022-11-28","cited_by_count":5,"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":"2111.04835","title":"Safe Data Collection for Offline and Online Policy Learning","created":"2021-11-08","cited_by_count":4,"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":"2306.13053","title":"Context-lumpable stochastic bandits","created":"2023-06-22","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":"2404.00688","title":"Meta Learning in Bandits within Shared Affine Subspaces","created":"2024-03-31","cited_by_count":4,"area":null},{"id":"2507.02762","title":"Contextual Online Pricing with (Biased) Offline Data","created":"2025-07-03","cited_by_count":4,"area":null},{"id":"2210.03528","title":"Tractable Optimality in Episodic Latent MABs","created":"2022-10-05","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":"2205.15921","title":"Online Meta-Learning in Adversarial Multi-Armed Bandits","created":"2022-05-31","cited_by_count":2,"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":"2410.14839","title":"Multi-Task Dynamic Pricing in Credit Market with Contextual Information","created":"2024-10-18","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":"2409.06329","title":"Modified Meta-Thompson Sampling for Linear Bandits and Its Bayes Regret Analysis","created":"2024-09-10","cited_by_count":1,"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":"2107.03263","title":"Bandits with Stochastic Experts: Constant Regret, Empirical Experts and Episodes","created":"2021-07-07","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":"2207.11545","title":"Learning to Sell a Focal-ancillary Combination","created":"2022-07-23","cited_by_count":0,"area":null},{"id":"2305.11908","title":"Sequential Best-Arm Identification with Application to Brain-Computer Interface","created":"2023-05-17","cited_by_count":0,"area":null},{"id":"2306.09136","title":"Finite-Time Logarithmic Bayes Regret Upper Bounds","created":"2023-06-15","cited_by_count":0,"area":null},{"id":"2309.01453","title":"Interactive Graph Convolutional Filtering","created":"2023-09-04","cited_by_count":0,"area":null},{"id":"2311.09483","title":"Adaptive Interventions with User-Defined Goals for Health Behavior Change","created":"2023-11-16","cited_by_count":0,"area":null},{"id":"2410.03651","title":"Minimax-optimal trust-aware multi-armed bandits","created":"2024-10-04","cited_by_count":0,"area":null},{"id":"2505.18269","title":"Representative Action Selection for Large Action Space Bandit Families","created":"2025-05-23","cited_by_count":0,"area":null},{"id":"2512.10952","title":"Hierarchical Dataset Selection for High-Quality Data Sharing","created":"2025-12-11","cited_by_count":0,"area":null},{"id":"2512.12693","title":"Co-Exploration and Co-Exploitation via Shared Structure in Multi-Task Bandits","created":"2025-12-14","cited_by_count":0,"area":null},{"id":"2602.00943","title":"Dynamic Prior Thompson Sampling for Cold-Start Exploration in Recommender Systems","created":"2026-02-01","cited_by_count":0,"area":null},{"id":"2602.17958","title":"Bayesian Online Model Selection","created":"2026-02-20","cited_by_count":0,"area":null},{"id":"2603.20408","title":"Meta-Learning for Repeated Bayesian Persuasion","created":"2026-03-20","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":"2609.09907","title":"Meta-LinEXP3: Online-within-Online Learning for Adversarial Linear Contextual Bandits","created":"2026-09-09","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}