regret bound

Batch Ensemble for Variance Dependent Regret in Stochastic Bandits AAAI 2025 Bayesian Optimization from Human Feedback: Near-Optimal Regret Bounds ICML 2025 Bellman Unbiasedness: Toward Provably Efficient Distributional Reinforcement Learning with General Value Function Approximation ICML 2025 Be More Diverse than the Most Diverse: Optimal Mixtures of Generative Models via Mixture-UCB Bandit Algorithms ICLR 2025 BILBO: BILevel Bayesian Optimization ICML 2025 Calibrated Regression Against An Adversary Without Regret UAI 2025 CATE Estimation With Potential Outcome Imputation From Local Regression UAI 2025 Catoni Contextual Bandits are Robust to Heavy-tailed Rewards ICML 2025 Causal Bandits without Graph Learning CLeaR 2025 CONGO: Compressive Online Gradient Optimization ICLR 2025 Conservative Contextual Bandits: Beyond Linear Representations ICLR 2025 Contextual Bandits for Unbounded Context Distributions ICML 2025 Contextual Bandits with Stage-wise Constraints JMLR 2025 Continual Reinforcement Learning by Planning with Online World Models ICML 2025 Corruption-Robust Variance-aware Algorithms for Generalized Linear Bandits under Heavy-tailed Rewards UAI 2025 Data-dependent Bounds with T-Optimal Best-of-Both-Worlds Guarantees in Multi-Armed Bandits using Stability-Penalty Matching COLT 2025 Data Dependent Regret Bounds for Online Portfolio Selection with Predicted Returns ALT 2025 Data-Driven Upper Confidence Bounds with Near-Optimal Regret for Heavy-Tailed Bandits AISTATS 2025 Decentralized and Uncoordinated Learning of Stable Matchings: A Game-Theoretic Approach AAAI 2025 Decision Making in Hybrid Environments: A Model Aggregation Approach COLT 2025 Delay as Payoff in MAB AAAI 2025 Differentially Private Kernelized Contextual Bandits AISTATS 2025 Dimension-Free Adaptive Subgradient Methods with Frequent Directions ICML 2025 Dissecting the Impact of Model Misspecification in Data-Driven Optimization AISTATS 2025 DOPL: Direct Online Preference Learning for Restless Bandits with Preference Feedback ICLR 2025