Ronald J. and Carol T. Beerman Postdoctoral Fellow
Education
- Ph.D. Computer Science (2026), Carnegie Mellon University
- B.S. Applied Math (2020), Chinese University of Hong Kong, Shenzhen
About
I'm the Beerman Postdoctoral Fellow in the School of Industrial and Systems Engineering (ISyE) at Georgia Tech, hosted by Debankur Mukherjee and Siva Theja Maguluri. I received my Ph.D. from the Computer Science Department of Carnegie Mellon University, where I was very fortunate to be advised by Professor Weina Wang. Prior to starting my Ph.D., I was an undergraduate student at the Chinese University of Hong Kong, Shenzhen (CUHK-Shenzhen), where I graduated from the mathematics major with a Bachelor of Science degree.
Research
My research focuses on fundamental theoretical questions in large-scale stochastic systems, particularly in queueing theory, restless bandits, and weakly-coupled MDPs. These models are foundational to modern operations research and computer science, with applications ranging from cloud computing and reinforcement learning to healthcare and ride sharing. By developing new analytical tools and frameworks, I have made significant progress on decades-old open problems, such as removing the global attractor assumption for restless bandits, and proving a new universal bound for the G/G/n queue.
Awards and Honors
- Outstanding Student Poster Award, Stochastic Network Conference
- Young European Queueing Theorists (YEQT) Workshop, Invited Speaker
- NeurIPS Spotlight (top 3.18% of submissions) — Projection-Based Lyapunov Method for Fully Heterogeneous Weakly-Coupled MDPs
- IFIP Performance 2023 Best Paper Award — Performance of the Gittins Policy in the G/G/1 and G/G/k, With and Without Setup Times
- NeurIPS Spotlight (top 3.06% of submissions) — Restless Bandits with Average Reward: Breaking the Uniform Global Attractor Assumption
- ACM SIGMETRICS 2021 Student Research Competition, Second Place
Representative Publications
Hong, Y. (2025). An interpretable universal bound for multiserver queues via a leave-one-out technique. arXiv:2510. 11015 [Math. PR]. doi:10.48550/arXiv.2510.11015
Zhang, X., Hong, Y., & Wang, W. (2025). Projection-based Lyapunov method for fully heterogeneous weakly-coupled MDPs. Advances in Neural Information Processing Systems 38 (NeurIPS 2025), 38, 91054–91076. doi:10.52202/085713-3045
Hong, Y., Xie, Q., Chen, Y., & Wang, W. (2025). Unichain and Aperiodicity Are Sufficient for Asymptotic Optimality of Average-Reward Restless Bandits. Mathematics of Operations Research. doi:10.1287/moor.2024.0678
Hong, Y., Xie, Q., Chen, Y., & Wang, W. (2023). Restless Bandits with Average Reward: Breaking the Uniform Global Attractor Assumption. Advances in Neural Information Processing Systems 36 (NeurIPS 2023), 36, 12810–12844.
Hong, Y., & Scully, Z. (2024). Performance of the Gittins policy in the G/G/1 and G/G/k, with and without setup times. Perform. Evaluation, 163, 102377. doi:10.1016/J.PEVA.2023.102377