{"total":18,"rows":[{"id":"2310.02023","title":"Nash Regret Guarantees for Linear Bandits","created":"2023-10-03","cited_by_count":9,"area":null},{"id":"2205.08875","title":"Multi-disciplinary fairness considerations in machine learning for clinical trials","created":"2022-05-18","cited_by_count":8,"area":null},{"id":"2301.09223","title":"Doubly Adversarial Federated Bandits","created":"2023-01-22","cited_by_count":7,"area":null},{"id":"2101.10998","title":"SDF-Bayes: Cautious Optimism in Safe Dose-Finding Clinical Trials with Drug Combinations and Heterogeneous Patient Groups","created":"2021-01-26","cited_by_count":6,"area":null},{"id":"2503.09226","title":"Towards Regulatory-Confirmed Adaptive Clinical Trials: Machine Learning Opportunities and Solutions","created":"2025-03-12","cited_by_count":3,"area":null},{"id":"2204.04773","title":"Worst-case Performance of Greedy Policies in Bandits with Imperfect Context Observations","created":"2022-04-10","cited_by_count":2,"area":null},{"id":"2502.21304","title":"Clustering Context in Off-Policy Evaluation","created":"2025-02-28","cited_by_count":2,"area":null},{"id":"2510.10730","title":"Provable Anytime Ensemble Sampling Algorithms in Nonlinear Contextual Bandits","created":"2025-10-12","cited_by_count":2,"area":null},{"id":"2506.07275","title":"Tailored Behavior-Change Messaging for Physical Activity: Integrating Contextual Bandits and Large Language Models","created":"2025-06-08","cited_by_count":1,"area":null},{"id":"2510.19014","title":"Prior-informed optimization of treatment recommendation via bandit algorithms trained on large language model-processed historical records","created":"2025-10-21","cited_by_count":1,"area":null},{"id":"2601.02870","title":"Quantum-Enhanced Neural Contextual Bandit Algorithms","created":"2026-01-06","cited_by_count":1,"area":null},{"id":"2602.00417","title":"Shuffle and Joint Differential Privacy for Generalized Linear Contextual Bandits","created":"2026-01-31","cited_by_count":1,"area":null},{"id":"2605.24803","title":"Active Learning for Stochastic Contextual Linear Bandits","created":"2026-05-24","cited_by_count":1,"area":null},{"id":"2311.18725","title":"AI in Pharma for Personalized Sequential Decision-Making: Methods, Applications and Opportunities","created":"2023-11-30","cited_by_count":0,"area":null},{"id":"2411.05661","title":"Multi-armed Bandits with Missing Outcome","created":"2024-11-08","cited_by_count":0,"area":null},{"id":"2501.19401","title":"DAL: A Practical Prior-Free Black-Box Framework for Piecewise Stationary Bandits","created":"2025-01-31","cited_by_count":0,"area":null},{"id":"2603.03778","title":"Inverse Contextual Bandits without Rewards: Learning from a Non-Stationary Learner via Suffix Imitation","created":"2026-03-04","cited_by_count":0,"area":null},{"id":"2603.12530","title":"Mixing Makes Markovian Contexts Cheap for Linear Bandits","created":"2026-03-13","cited_by_count":0,"area":null}],"next_cursor":null}