白菜网送彩金可提现

学术报告-陈彩华

发布人:
责任人:
点击数:
更新时间:
2020-11-09 14:41:00

学术报告


题      目:Algorithmic Design for Wassernstein Distributionally Robust Optimization in Machine Learning



报  告  人:陈彩华   副教授  (邀请人:陈艳男 )

                                 南京大学




时      间:2020-11-09 16:30--17:30


地      点:学院401


报告人简介:

        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、香港理工大学、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)。

摘      要:

       Wasserstein Distributionally Robust Stochastic Optimization (DRSO) is concerned with finding decisions that perform well on data that are drawn from the worst-case 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 large-scale 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.