报告题目：Algorithmic Design for Wassernstein Distributionally Robust Optimization in Machine Learning

　　报告时间：2020年10月28日（周三）10:15-11:15

　　报告地点：北辰校区理学院（西教五）416　　

　　报告嘉宾：陈彩华 副教授（南京大学）

　　报告摘要：Wasserstein Distributionally Robust Stochastic Optimization (DRSO) is concerned with finding decisions that perform well on data that are drawn from the worstcase probability distribution within a Wasserstein ball centered at a certain nominal distribution. In recent years, it has been shown that various DRSO formulations of learning models admit tractable convex reformulations. However, most existing works propose to solve these convex reformulations by general-purpose solvers, which are not well suited for tackling largescale problems. 

  In this talk,we focus on Wasserstein distributionally robust support vector machine (DRSVM) problems and logistic regression (DRLR) problems, and propose two novel first order algorithms to solve them. The updates in each iteration of these algorithms can be computed in a highly efficient manner. Our numerical results indicate that the proposed methods are orders of magnitude faster than the state-of-the-art, and the performance gap grows considerably as the problem size increases.Advanced models such as robust classifi-cation with fairness and unlabelled data are also discussed.　　

　　嘉宾简介：陈彩华，副教授，南京大学理学博士，新加坡国立大学联合培养博士，曾赴新加坡国立大学、香港中文大学、香港理威廉希尔中文官方网站学、香港浸会大学等学习与访问。主持/完成的基金包括国家自然科学基金面上项目、青年项目，江苏省自然科学基金面上项目、青年项目，参与国家自然科学基金重点项目，代表作发表在Mathematical Programming，SIAM Journal on Optimization,SIAM Journal on Imaging Science及CVPR、NIPS等国际知名学术期刊与会议，其中多篇论文入选ESI高被引论文。获华人数学家联盟最佳论文奖（2017、2018连续两年），中国运筹学会青年科技奖（2018），南京大学青年五四奖章(2019)，入选首批南京大学仲英青年学者（全校10人，2018）及江苏省社科优青（2019）。