Dr. Shengbo Wang

Biography

Dr. Shengbo Wang is an Assistant Professor in the Daniel J. Epstein Department of Industrial and Systems Engineering at the University of Southern California. He received his Ph.D. in Management Science and Engineering from Stanford University, where he was co-advised by Professors Peter Glynn and Jose Blanchet. His research interests span a broad spectrum of applied probability, stochastic modeling, reinforcement learning, distributionally robust control, simulation methods, and machine learning. Dr. Wang focuses on developing tractable probabilistic models and designing algorithms for data-driven dynamic decision-making under uncertainty, specifically addressing the reliability and scalability challenges in modern managerial engineering applications. His work incorporates design and analysis of algorithms tailored to learning control in dynamic engineering systems, with applications in management science and operations research. Key areas of his research include designing sample-efficient estimators, achieving efficient reinforcement learning control for stable stochastic systems, and developing statistically tractable data-driven modeling paradigms. He is also advancing deep learning techniques for policy learning and developing computationally efficient estimation procedures using applied probabilistic tools.

Research Interests

Awards