Entropic Regularization for Wasserstein Distributionally Robust Optimization
讲座通知 2025 年 12月 3 日（星期三）， 下午 15:30 - 16:30 信息管理与工程学院102室 上海市杨浦区武东路100号 主题 Entropic Regularization for Wasserstein Distributionally Robust Optimization 主讲人 Jie Wang The Chinese University of Hong Kong, Shenzhen Dr. Jie Wang is an Assistant Professor in the School of Artificial Intelligence and School of Data Science at The Chinese University of Hong Kong, Shenzhen, and was the first faculty joining its newly established AI School. He received his Ph.D in Industrial Engineering at Georgia Institute of Technology in 2025. His research focuses on optimization and statistics. Dr. Jie Wang’s work has been recognized with multiple awards, such as Winner in the 2022 INFORMS Poster Competition, Winner of the 2023 INFORMS Data Mining Society’s Best Theoretical Paper, Runner-up of the INFORMS 2024 Data Mining Best Paper Award Competition, Runner-up of the INFORMS 2024 Computing Society Student Paper Award, and Winner of the INFORMS 2024 Data Mining Society's Data Competition. 讲座简介 Wasserstein distributionally robust optimization often encounters computation intractability. To tackle the computational challenge, we develop a novel approach that combines entropic regularization into the distributionally robust risk function. This regularization brings a notable improvement in computation compared with the original formulation. We develop efficient stochastic gradient methods with biased oracles to optimize the regularized objective, proving that our approach achieves near-optimal sample complexity. Furthermore, by leveraging state-of-the-art diffusion models, we develop a method to sample from the worst-case distribution. This technique achieves global convergence under mild assumptions by employing tools from bilevel optimization in the space of continuous probability densities. We numerically validate our proposed method in supervised learning, reinforcement learning, and contextual learning.
上海财经大学（武东路校区）
