 QuACK: A Multipurpose Queuing Algorithm for Cooperative -Armed
BanditsInternational Conference on Artificial Intelligence and Statistics (AISTATS), 2024 |
 |
 Variance-Aware Regret Bounds for Stochastic Contextual Dueling BanditsInternational Conference on Learning Representations (ICLR), 2023 |
 Active Ranking of Experts Based on their Performances in Many TasksInternational Conference on Machine Learning (ICML), 2023 |
 Borda Regret Minimization for Generalized Linear Dueling BanditsInternational Conference on Machine Learning (ICML), 2023 |
 When Can We Track Significant Preference Shifts in Dueling Bandits?Neural Information Processing Systems (NeurIPS), 2023 |
 An Asymptotically Optimal Batched Algorithm for the Dueling Bandit
ProblemNeural Information Processing Systems (NeurIPS), 2022 |
 Batched Dueling BanditsInternational Conference on Machine Learning (ICML), 2022 |
 Preference learning along multiple criteria: A game-theoretic
perspectiveNeural Information Processing Systems (NeurIPS), 2021 |
 Adversarial Dueling BanditsInternational Conference on Machine Learning (ICML), 2020 |
 Combinatorial Pure Exploration of Dueling BanditInternational Conference on Machine Learning (ICML), 2020 |
 Preferential Batch Bayesian OptimizationInternational Workshop on Machine Learning for Signal Processing (MLSP), 2020 |
 Active embedding search via noisy paired comparisonsInformation Theory and Applications Workshop (ITA), 2019 |
 |
 |
 |
 |
