Online Algorithms

Lossless Acceleration of Large Language Models with Hierarchical Drafting based on Temporal Locality in Speculative Decoding NAACL 2025 Lower Bounds for Time-Varying Kernelized Bandits AISTATS 2025 Minimum Empirical Divergence for Sub-Gaussian Linear Bandits AISTATS 2025 Multi-agent Stochastic Bandits Robust to Adversarial Corruptions L4DC 2025 Multi-player Multi-armed Bandits with Delayed Feedback IJCAI 2025 Multiple Trade-offs: An Improved Approach for Lexicographic Linear Bandits AAAI 2025 Nearly Tight Bounds for Exploration in Streaming Multi-Armed Bandits with Known Optimality Gap AAAI 2025 Near-Optimal Regret Bounds for Federated Multi-armed Bandits with Fully Distributed Communication UAI 2025 Online Assortment and Price Optimization Under Contextual Choice Models AISTATS 2025 Online Generalized Magician’s Problem with Multiple Workers UAI 2025 Online Learning with Stochastically Partitioning Experts UAI 2025 Online MDP with Prototypes Information: A Robust Adaptive Approach AAAI 2025 Online Quantile Regression JMLR 2025 On Stochastic Contextual Bandits with Knapsacks in Small Budget Regime ICLR 2025 On Tradeoffs in Learning-Augmented Algorithms AISTATS 2025 Optimal Strong Regret and Violation in Constrained MDPs via Policy Optimization ICLR 2025 Optimistic Safety for Online Convex Optimization with Unknown Linear Constraints AISTATS 2025 Pairwise Elimination with Instance-Dependent Guarantees for Bandits with Cost Subsidy ICLR 2025 Problem-dependent Regret for Lexicographic Multi-Armed Bandits with Adversarial Corruptions IJCAI 2025 QuACK: A Multipurpose Queuing Algorithm for Cooperative k-Armed Bandits AISTATS 2025 Regret-Optimal List Replicable Bandit Learning: Matching Upper and Lower Bounds ICLR 2025 Revisiting Online Learning Approach to Inverse Linear Optimization: A Fenchel–Young Loss Perspective and Gap-Dependent Regret Analysis AISTATS 2025 Risk-sensitive Bandits: Arm Mixture Optimality and Regret-efficient Algorithms AISTATS 2025 Safe Cooperative Multi-Agent Reinforcement Learning with Function Approximation L4DC 2025 Safety in the Face of Adversity: Achieving Zero Constraint Violation in Online Learning with Slowly Changing Constraints AISTATS 2025