{"total":32,"rows":[{"id":"2111.12151","title":"Best Arm Identification with Safety Constraints","created":"2021-11-23","cited_by_count":25,"area":null},{"id":"2409.05181","title":"Sliding-Window Thompson Sampling for Non-Stationary Settings","created":"2024-09-08","cited_by_count":17,"area":null},{"id":"2112.00195","title":"Efficient Online Bayesian Inference for Neural Bandits","created":"2021-12-01","cited_by_count":15,"area":null},{"id":"2204.00706","title":"Strategies for Safe Multi-Armed Bandits with Logarithmic Regret and Risk","created":"2022-04-01","cited_by_count":15,"area":null},{"id":"2506.16658","title":"Multi-Armed Bandits With Machine Learning-Generated Surrogate Rewards","created":"2025-06-20","cited_by_count":14,"area":null},{"id":"2210.13623","title":"Reinforcement Learning and Bandits for Speech and Language Processing: Tutorial, Review and Outlook","created":"2022-10-24","cited_by_count":10,"area":null},{"id":"2306.12774","title":"Pure Exploration in Bandits with Linear Constraints","created":"2023-06-22","cited_by_count":10,"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":"2210.12669","title":"Meta Learning of Interface Conditions for Multi-Domain Physics-Informed Neural Networks","created":"2022-10-23","cited_by_count":6,"area":null},{"id":"2309.02202","title":"On the Complexity of Differentially Private Best-Arm Identification with Fixed Confidence","created":"2023-09-05","cited_by_count":6,"area":null},{"id":"2111.13415","title":"ESCADA: Efficient Safety and Context Aware Dose Allocation for Precision Medicine","created":"2021-11-26","cited_by_count":5,"area":null},{"id":"2309.03145","title":"The Best Arm Evades: Near-optimal Multi-pass Streaming Lower Bounds for Pure Exploration in Multi-armed Bandits","created":"2023-09-06","cited_by_count":5,"area":null},{"id":"2206.03019","title":"The Survival Bandit Problem","created":"2022-06-07","cited_by_count":4,"area":null},{"id":"2108.00236","title":"Debiasing Samples from Online Learning Using Bootstrap","created":"2021-07-31","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":"2405.11171","title":"Graph Feedback Bandits with Similar Arms","created":"2024-05-18","cited_by_count":2,"area":null},{"id":"2501.16018","title":"Strategic Multi-Armed Bandit Problems Under Debt-Free Reporting","created":"2025-01-27","cited_by_count":2,"area":null},{"id":"2112.06728","title":"Safe Linear Leveling Bandits","created":"2021-12-13","cited_by_count":1,"area":null},{"id":"2211.01561","title":"Benefits of Monotonicity in Safe Exploration with Gaussian Processes","created":"2022-11-03","cited_by_count":1,"area":null},{"id":"2303.17043","title":"Federated Learning for Heterogeneous Bandits with Unobserved Contexts","created":"2023-03-29","cited_by_count":1,"area":null},{"id":"2307.14138","title":"Piecewise-Stationary Combinatorial Semi-Bandit with Causally Related Rewards","created":"2023-07-26","cited_by_count":1,"area":null},{"id":"2412.13559","title":"Indirect Query Bayesian Optimization with Integrated Feedback","created":"2024-12-18","cited_by_count":1,"area":null},{"id":"2503.00387","title":"LNUCB-TA: Linear-nonlinear Hybrid Bandit Learning with Temporal Attention","created":"2025-03-01","cited_by_count":1,"area":null},{"id":"2505.23720","title":"COBRA: Contextual Bandit Algorithm for Ensuring Truthful Strategic Agents","created":"2025-05-29","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":"2404.12186","title":"Privacy-Preserving UCB Decision Process Verification via zk-SNARKs","created":"2024-04-18","cited_by_count":0,"area":null},{"id":"2410.18844","title":"Learning to Explore with Lagrangians for Bandits under Unknown Linear Constraints","created":"2024-10-24","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":"2503.02043","title":"Constrained Linear Thompson Sampling","created":"2025-03-03","cited_by_count":0,"area":null},{"id":"2503.07877","title":"Cost-Aware Optimal Pairwise Pure Exploration","created":"2025-03-10","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":"2608.26755","title":"Safety by Design: Realized-Cost Constraints for Contextual Bandits with Continuous Actions","created":"2026-08-27","cited_by_count":0,"area":null}],"next_cursor":null}