Haoyang Hong
Portrait of Haoyang Hong

Haoyang Hong

Second-year Ph.D. Student in AI, Oregon State University · Advisor: Huazheng Wang · Corvallis, OR
B.S. in Statistics, University of Science and Technology of China
Reinforcement Learning Theory Bandit Theory Online Learning Robustness Multi-Fidelity Learning
Google Scholar GitHub LinkedIn CV (PDF) Open to Summer 2026 Research Internships

About

I am a second-year Ph.D. student in Artificial Intelligence in the School of Electrical Engineering and Computer Science (EECS) at Oregon State University, advised by Dr. Huazheng Wang. Before OSU, I received my B.S. in Statistics from the University of Science and Technology of China (USTC), School of the Gifted Young.

My research studies how learning systems make decisions under uncertainty, with a focus on reinforcement learning theory, bandit theory, online learning, robustness, and statistical inference under adaptive data collection. I am also interested in how these tools can support reliable and cost-aware AI systems, including multi-fidelity learning and adaptive feedback allocation.

News

  • Preprint released: Beyond Static Bias: Adaptive Multi-Fidelity Bandits with Improving Proxies.

  • Paper accepted to RLC 2026: Online KL-Regularized Reinforcement Learning with Function Approximation under Misspecification.

  • Paper accepted to ICML 2026: When Can You Poison Rewards? A Tight Characterization of Reward Poisoning in Linear MDPs.

  • Paper accepted to NeurIPS 2025: Design-Based Bandits under Network Interference.

Publications and Preprints

Contact

Email: honghao@oregonstate.edu · Office: Corvallis, OR · Open to collaboration.

Happy to chat!