 Offline-to-online hyperparameter transfer for stochastic banditsAAAI Conference on Artificial Intelligence (AAAI), 2025 |
 A Model Selection Approach for Corruption Robust Reinforcement LearningInternational Conference on Algorithmic Learning Theory (ALT), 2021 |
 Data-Driven Online Model Selection With Regret GuaranteesInternational Conference on Artificial Intelligence and Statistics (AISTATS), 2023 |
 Adaptation to Misspecified Kernel Regularity in Kernelised BanditsInternational Conference on Artificial Intelligence and Statistics (AISTATS), 2023 Yusha Liu Aarti Singh |
 A Blackbox Approach to Best of Both Worlds in Bandits and BeyondAnnual Conference Computational Learning Theory (COLT), 2023 |
 Stochastic Rising BanditsInternational Conference on Machine Learning (ICML), 2022 |
 Best of Both Worlds Model SelectionNeural Information Processing Systems (NeurIPS), 2022 |
 Leveraging Initial Hints for Free in Stochastic Linear BanditsInternational Conference on Algorithmic Learning Theory (ALT), 2022 |
 Corralling a Larger Band of Bandits: A Case Study on Switching Regret
for Linear BanditsAnnual Conference Computational Learning Theory (COLT), 2022 |
 Decentralized Cooperative Reinforcement Learning with Hierarchical
Information StructureInternational Conference on Algorithmic Learning Theory (ALT), 2021 |
 Model Selection for Generic Contextual BanditsIEEE Transactions on Information Theory (IEEE Trans. Inf. Theory), 2021 |
 Towards Costless Model Selection in Contextual Bandits: A Bias-Variance
PerspectiveInternational Conference on Artificial Intelligence and Statistics (AISTATS), 2021 |
 Thompson Sampling with a Mixture PriorInternational Conference on Artificial Intelligence and Statistics (AISTATS), 2021 |
 Leveraging Good Representations in Linear Contextual BanditsInternational Conference on Machine Learning (ICML), 2021 |
 Pareto Optimal Model Selection in Linear BanditsInternational Conference on Artificial Intelligence and Statistics (AISTATS), 2021 |
 Smooth Bandit Optimization: Generalization to Hölder SpaceInternational Conference on Artificial Intelligence and Statistics (AISTATS), 2020 |
 Online Model Selection for Reinforcement Learning with Function
ApproximationInternational Conference on Artificial Intelligence and Statistics (AISTATS), 2020 |
 Multitask Bandit Learning Through Heterogeneous Feedback AggregationInternational Conference on Artificial Intelligence and Statistics (AISTATS), 2020 |
 Model Selection in Contextual Stochastic Bandit ProblemsNeural Information Processing Systems (NeurIPS), 2020 |
