I am a final-year PhD student in the Statistics Department at the University of Michigan advised by Ambuj Tewari. Previously, I worked on recommendation systems and search engines as a machine learning engineer in the industry.

My research interests are broadly in design and analysis of algorithms for sequential decision making under uncertainty. I have worked on problems including non-stationary bandits, offline reinforcement learning, constrained reinforcement learning.

Outside of work, I enjoy running and playing the piano.

Publications

1. Offline Constrained Reinforcement Learning with Arbitrary Data Distributions under Partial Coverage
   Kihyuk Hong, Ambuj Tewari
   In Preparation, 2025
2. A Computationally Efficient Algorithm for Infinite-Horizon Average-Reward Linear MDPs
   Kihyuk Hong, Ambuj Tewari
   In Submission, 2025
3. Reinforcement Learning for Infinite-Horizon Average-Reward Linear MDPs via Approximation by Discounted-Reward MDPs
   Kihyuk Hong, Woojin Chae, Yufan Zhang, Dabeen Lee, Ambuj Tewari
   International Conference on Artificial Intelligence and Statistics (AISTATS), 2025
4. Learning Infinite-Horizon Average-Reward Linear Mixture MDPs of Bounded Span
   Woojin Chae, Kihyuk Hong, Yufan Zhang, Ambuj Tewari, Dabeen Lee
   International Conference on Artificial Intelligence and Statistics (AISTATS), 2025
5. A Primal-Dual Algorithm for Offline Constrained Reinforcement Learning with Linear MDPs
   Kihyuk Hong, Ambuj Tewari
   International Conference on Machine Learning (ICML), 2024
6. A Primal-Dual-Critic Algorithm for Offline Constrained Reinforcement Learning
   Kihyuk Hong, Yuhang Li, Ambuj Tewari
   International Conference on Artificial Intelligence and Statistics (AISTATS), 2024
7. An Optimization-Based Algorithm for Non-Stationary Kernel Bandits without Prior Knowledge
   Kihyuk Hong, Yuhang Li, Ambuj Tewari
   International Conference on Artificial Intelligence and Statistics (AISTATS), 2023

Talks

1. Invited Talk, Stanford University. Computer Science Department. Feb 2025.
2. University of Michigan. Statistics Department Seminar. Dec 2024.
3. An algorithm for infinite-horizon average reward RL with linear MDPs. RL Theory Workshop. Jun 2024.
4. Introduction to reinforcement learning, guest lecture for STATS 503, University of Michigan. May 2023.

Mentoring

• Yuhang Li, 06/2022 – 09/2023. Published 2 papers together.
• Yufan Zhang, 02/2024 – 08/2024. Published 2 papers together.

Teaching

• Teaching assistant, Advanced Statistical Learning (STATS 601), University of Michigan. Winter 2025
• Teaching assistant, Regression analysis (STATS 600), University of Michigan. Fall 2024
• Teaching assistant, Regression analysis (STATS 600), University of Michigan. Fall 2023
• Teaching assistant, Introduction to data science (STATS 206), University of Michigan. Fall 2021
• Teaching assistant, Survey sampling techniques (STATS 480), University of Michigan. Winter 2021
• Teaching assistant, Introduction to statistics and data analysis (STATS 250), University of Michigan. Fall 2020

Education

• PhD Statistics. University of Michigan. 2020 - current.
• MS Statistics. Stanford University. 2008 - 2010.
• BS Biomedical Engineering & Applied Math. Johns Hopkins University. 2004 - 2008.

Professional Experience

• Machine Learning Enigineer. Naver. Nov 2013 - Apr 2020.
• Software Engineer. Meta. Aug 2010 - Nov 2013.

Services

Reviewer

• International Conference on Artificial Intelligence and Statistics (AISTATS)
• Journal of Machine Learning Research (JMLR)
• Statistical Science

Organizer

• Department Representative, Michigan Student Symposium for Interdisciplinary Statistical Sciences (MSSISS), University of Michigan. 2023.