Almost Optimal Variance-Constrained Best Arm Identification
Published in IEEE Transactions on Information Theory (IEEE TIT), Volume 69, Issue 4, April 2023, doi: 10.1109/TIT.2022.3222231., 2023
Yunlong Hou, Vincent Y. F. Tan and Zixin Zhong
Posts by Collection
publications
Probably Anytime-Safe Stochastic Combinatorial Semi-Bandits
Published in International Conference on Machine Learning (ICML), 2023, 2023
Yunlong Hou, Vincent Y. F. Tan and Zixin ZhongAlmost Minimax Optimal Best Arm Identification in Piecewise Stationary Linear Bandits
Published in Conference on Neural Information Processing Systems (NeurIPS), 2024, 2024
Yunlong Hou, Vincent Y. F. Tan and Zixin ZhongBanditSpec: Adaptive Speculative Decoding via Bandit Algorithms
Published in International Conference on Machine Learning (ICML), 2025, 2025
Yunlong Hou, Fengzhuo Zhang, Cunxiao Du, Xuan Zhang, Jiachun Pan, Tianyu Pang, Chao Du, Vincent Y. F. Tan and Zhuoran YangDemystifying the Slash Pattern in Attention: The Role of RoPE
Published in The first Foundations of Deep Generative Models workshop, ICML 2026, 2026
Yuan Cheng, Fengzhuo Zhang, Yunlong Hou, Cunxiao Du, Chao Du, Tianyu Tang, Aixin Sun and Zhuoran YangRethinking ‘‘RL Generalizes, SFT Memorizes’’: The Role of SFT Data
Published in The first Foundations of Deep Generative Models workshop, ICML 2026; 2026 INFORMS Annual Meeting., 2026
Yunlong Hou, Fengzhuo Zhang, Yuan Cheng, Jiachun Pan, Xingyao Li and Zhuoran YangOn the Benefits of Free Exploration for Regret Minimization in Multi-Armed Bandits
Published in , 2026
Yunlong Hou, Zixin Zhong and Vincent Y. F. TanBayesian Best-Arm Identification with Abstention: A Polynomial-to-Exponential Phase Transition
Published in , 2026
Yuqi Huang, Yunlong Hou and Vincent Y. F. Tantalks
teaching
Teaching experience 1
Undergraduate course, University 1, Department, 2014
This is a description of a teaching experience. You can use markdown like any other post.
Teaching experience 2
Workshop, University 1, Department, 2015
This is a description of a teaching experience. You can use markdown like any other post.