 uniINF: Best-of-Both-Worlds Algorithm for Parameter-Free Heavy-Tailed MABsInternational Conference on Learning Representations (ICLR), 2024 |
 |
 Stability-penalty-adaptive follow-the-regularized-leader: Sparsity,
game-dependency, and best-of-both-worldsNeural Information Processing Systems (NeurIPS), 2023 |
 On the Minimax Regret for Online Learning with Feedback GraphsNeural Information Processing Systems (NeurIPS), 2023 |
 Best-of-Three-Worlds Linear Bandit Algorithm with Variance-Adaptive
Regret BoundsAnnual Conference Computational Learning Theory (COLT), 2023 |
