Yan Li

Dr. Yan Li is an Assistant Professor in the Department of Industrial and Systems Engineering at Texas A&M University. He earned his Ph.D. in Operations Research from Georgia Institute of Technology (2024), advised by George Lan and co-advised by Tuo Zhao, with collaborations involving Anton Kleywegt and Alexander Shapiro. His research focuses on the computational perspective of learning optimal decisions from data, emphasizing first-order methods and their applications in data science.

• B.S. in Mathematics and Applied Mathematics & B.B.A. in Accounting, Nankai University (2016)
• M.S. in Statistics, Georgia Institute of Technology (2018)
• Ph.D. in Operations Research, Georgia Institute of Technology (2024)

Dr. Li’s research interests span dynamic optimization (Markov decision processes, reinforcement learning), robust/risk-averse optimization, minimax optimization, and optimization for machine learning. His work addresses computation- and sample-efficient algorithms, distributional ambiguity in dynamic optimization, and gradient-based methods for ML applications. Industry collaborations include Meta (ads ranking optimization) and Bytedance (deep retrieval models), with ongoing projects in urban transportation and recommendation systems.

His publications include 15 recent articles on policy optimization, stochastic minimax methods, and implicit regularization in reinforcement learning. Awards include the Alice and John Jarvis Ph.D. Student Research Award, The Margaret and Stephen Kendrick Research Excellence Award, and the ISyE Outstanding Graduate Student Instructor Award. Teaching accolades highlight his clarity, passion, and accessibility in courses like ISEN 310 (Uncertainty Modeling) and ISEN 320 (Operations Research I).

• Peer reviewer for journals like Mathematical Programming and conferences including ICML and NeurIPS
• Industry partnerships with Ford (multi-agent RL) and Meta (embedding learning)
• Active in optimization communities (INFORMS, MOPTA)