CDM Seminar - Entropic Regularization for Wasserstein Distributionally Robust Optimization
Abstract:
Wasserstein distributionally robust optimization sometimes 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.
Short bio: 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 robust optimization.
Wasserstein distributionally robust optimization sometimes 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.
Short bio: 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 robust optimization.
Practical information
- Informed public
- Registration required
Organizer
- Prof. Daniel Khun