2026年第7期(总第1151期)
演讲主题：Harmonizing SAA and DRO
主讲人：Pan Kai 香港理工大学副教授
主持人：吴庆华 管理科学系教授
活动时间：2025年3月15日（周日）09:30-11:00
活动地址:管院大楼125教室
主讲人简介：
Kai Pan is currently an Associate Professor in Operations Management at the Faculty of Business of The Hong Kong Polytechnic University (PolyU), the Director of the MSc Program in Operations Management (MScOM), and the Deputy Director of the Doctor of Business Management (DBM) Program. He received his Ph.D. degree from the University of Florida, USA, in 2016 and his Bachelor's degree from Zhejiang University, China, in 2010. His research interests include Stochastic and Discrete Optimization, Robust and Data-Driven Optimization, Dynamic Programming, and their applications in Energy Market, Smart City, Supply Chain, Shared Mobility, Telecommunication, and Marketing. His research on these topics has been published in Operations Research, Manufacturing and Service Operations Management, INFORMS Journal on Computing, Production and Operations Management, IISE Transactions, European Journal of Operational Research, IEEE Transactions on Power Systems, Transportation Research Part B, etc. He was the first-place winner of the IISE Pritsker Doctoral Dissertation Award in 2017 and the awardee of the PolyU Young Innovative Researcher Award (YIRA) 2025. He serves as an Associate Editor for IISE Transactions, Decision Sciences, and Omega, and has served as a Secretary/Treasurer for the INFORMS Computing Society (ICS).
活动简介：
Decision-makers often encounter uncertainty, and the distribution of uncertain parameters plays a crucial role in making reliable decisions. However, complete information is rarely available. The sample average approximation (SAA) approach utilizes historical data to address this, but struggles with insufficient data. Conversely, moment-based distributionally robust optimization (DRO) effectively employs partial distributional information but can yield conservative solutions even with ample data. To bridge these approaches, we propose a novel method called harmonizing optimization (HO), which integrates SAA and DRO by adaptively adjusting the weights of data and information based on sample size N. This allows HO to amplify data effects in large samples while emphasizing information in smaller ones. More importantly, HO performs well across varying data sizes without needing to classify them as large or small. We provide practical methods for determining these weights and demonstrate that HO offers finite-sample performance guarantees, proving asymptotic optimality when the weight of information follows a 1/\sqrt{N}-rate. In addition, HO can be applied to enhance scenario reduction, improving approximation quality and reducing completion time by retaining critical information from reduced scenarios. Numerical results show significant advantages of HO in solution quality compared to Wasserstein-based DRO, and highlight its effectiveness in scenario reduction.
