 A Unified Regularization Approach to High-Dimensional Generalized Tensor BanditsInternational Symposium on Information Theory (ISIT), 2025 |
 Provably Efficient Reinforcement Learning with Multinomial Logit Function ApproximationNeural Information Processing Systems (NeurIPS), 2024 |
 Nearly Minimax Optimal Regret for Multinomial Logistic BanditNeural Information Processing Systems (NeurIPS), 2024 |
 Improved Regret Bounds of (Multinomial) Logistic Bandits via
Regret-to-Confidence-Set ConversionInternational Conference on Artificial Intelligence and Statistics (AISTATS), 2023 |
 Towards Scalable and Robust Structured Bandits: A Meta-Learning
FrameworkInternational Conference on Artificial Intelligence and Statistics (AISTATS), 2022 |
 UCB-based Algorithms for Multinomial Logistic Regression BanditsNeural Information Processing Systems (NeurIPS), 2021 |
