 Efficient Near-Optimal Algorithm for Online Shortest Paths in Directed Acyclic Graphs with Bandit Feedback Against Adaptive AdversariesAnnual Conference Computational Learning Theory (COLT), 2025 |
 Sum-max Submodular BanditsInternational Conference on Artificial Intelligence and Statistics (AISTATS), 2023 |
 On the Minimax Regret for Online Learning with Feedback GraphsNeural Information Processing Systems (NeurIPS), 2023 |
 Sampling Equilibria: Fast No-Regret Learning in Structured GamesACM-SIAM Symposium on Discrete Algorithms (SODA), 2022 |
 Unifying mirror descent and dual averagingMathematical programming (Math. Program.), 2019 |
 Top-k Combinatorial Bandits with Full-Bandit FeedbackInternational Conference on Algorithmic Learning Theory (ALT), 2019 |
 |
