PhD student in Statistics at the University of Arizona

About Me

Hi, I'm Hao Qin, a final-year PhD student at The University of Arizona in the program of GIDP-STATS. I am fortunate to be advised by Dr. Chicheng Zhang. Before that, I received my Bachelor's degree in Applied Mathematics from Shandong University and Master's degree in Data Science from The University of Wisconsin-Madison.

Research Interests

My research interests are in the field of machine learning, especially in the area of reinforcement learning. I have a particular interest in identifying the crucial factors that quantify the exploration-exploitation trade-off in reinforcement learning, which is a fundamental problem in the field. A clear understanding of this trade-off will pave the way for designing more efficient algorithms in various applications, such as recommendation systems, robotics, and autonomous driving.

Currently, I am working on the following directions:

  • Reinforcement Learning
  • Inverse Reinforcement Learning
  • Wireless Communications

Publications

DOEC
Taming the Monster Every Context: Complexity Measure and Unified Framework for Offline-Oracle Efficient Contextual Bandits
Hao Qin, Chicheng Zhang
Conference on Learning Theory (COLT) 2026
arXiv
UNIMODAL
Physics-Informed Parametric Bandits for Beam Alignment in mmWave Communications
Hao Qin*, Thang Duong*, Ming F. Li, Chicheng Zhang
International Symposium on Modeling and Optimization in Mobile, Ad hoc, and Wireless Networks (WiOpt) 2026
arXiv
EXP-KL-MS
Achieving Adaptivity and Optimality for Multi-Armed Bandits using Exponential-Kullback Leibler Maillard Sampling
Hao Qin, Kwang-Sung Jun, Chicheng Zhang
In submission
arXiv
KL-MS
Kullback-Leibler Maillard Sampling for Multi-armed Bandits with Bounded Rewards
Hao Qin, Kwang-Sung Jun, Chicheng Zhang
Conference on Neural Information Processing Systems (NeurIPS) 2023
arXiv | Code

News

Soft Performance Difference Lemma

8 minute read

This note presents the soft performance difference lemma, which is a fundamental result in regularized reinforcement learning. Nowadays, regularized reinforc...