Multi-Armed Bandits

Best-Arm Identification in Unimodal Bandits AISTATS 2025 Best Arm Identification with Possibly Biased Offline Data UAI 2025 Constant-Factor Distortion Mechanisms for k-Committee Election AAAI 2025 Contextual Bandits with Stage-wise Constraints JMLR 2025 Corruption-Robust Variance-aware Algorithms for Generalized Linear Bandits under Heavy-tailed Rewards UAI 2025 Cost-Aware Optimal Pairwise Pure Exploration AISTATS 2025 Cross-Domain Off-Policy Evaluation and Learning for Contextual Bandits ICLR 2025 Data-Driven Upper Confidence Bounds with Near-Optimal Regret for Heavy-Tailed Bandits AISTATS 2025 Delay as Payoff in MAB AAAI 2025 Differentially Private Kernelized Contextual Bandits AISTATS 2025 DOPL: Direct Online Preference Learning for Restless Bandits with Preference Feedback ICLR 2025 Dynamic Assortment Selection and Pricing with Censored Preference Feedback ICLR 2025 Efficient Algorithms for Logistic Contextual Slate Bandits with Bandit Feedback UAI 2025 Efficient Graph Bandit Learning with Side-Observations and Switching Constraints AAAI 2025 Every Bit Helps: Achieving the Optimal Distortion with a Few Queries AAAI 2025 Explicit and Implicit Examinee-Question Relation Exploiting for Efficient Computerized Adaptive Testing AAAI 2025 FCOM: A Federated Collaborative Online Monitoring Framework via Representation Learning AAAI 2025 Fixed-Budget Change Point Identification in Piecewise Constant Bandits AISTATS 2025 FLIPHAT: Joint Differential Privacy for High Dimensional Linear Bandits AISTATS 2025 Forecasting Competitions with Correlated Events AAAI 2025 Geometry-Aware Approaches for Balancing Performance and Theoretical Guarantees in Linear Bandits ICLR 2025 HAVER: Instance-Dependent Error Bounds for Maximum Mean Estimation and Applications to Q-Learning and Monte Carlo Tree Search AISTATS 2025 HR-Bandit: Human-AI Collaborated Linear Recourse Bandit AISTATS 2025 In-Domain African Languages Translation Using LLMs and Multi-armed Bandits ACL 2025 Investment-Driven Social Influence: A Statistical Physics Approach to Advertising Response ACL 2025