报告题目： Wasserstein Distributionally Robust Optimization
报告人： Dr. Rui Gao, University of Texas at Austin
主持人： 查宏远 教授
报告时间： 2019年1月3日 周四13:30-15:00
We consider distributionally robust optimization problems, which seek solutions that hedge against a family of distributions that are close to the empirical distribution in Wasserstein distance. In the first part of this talk, we show that Wasserstein robust empirical risk minimization is asymptotically equivalent to a regularization problem with a gradient-norm penalty. Generalization bounds for such regularization is derived. In the second part, leveraging tools from the Wasserstein distributionally robust optimization, we develop a scalable and nearly optimal approach for robust hypotheses testing.
Dr. Rui Gao is an Assistant Professor of Information, Risk, and Operations Management at the University of Texas at Austin. He received his Ph.D. in Operations Research from Georgia Institute of Technology in 2018. His research interests lie in the intersection between optimization under uncertainty and statistical learning, with applications in data analytics and deep learning.