题  目： A framework for analyzing variance reduced stochastic gradient methods and a new one

报告人：梁经纬

单  位：上海交通大学

时  间：2021年12月16日14:00

腾讯ID：256-424-517

摘要: Over the past years, variance reduced stochastic gradient methods have become increasingly popular, not only in the machine learning community, but also other areas including inverse problems and mathematical imaging to name a few. However, despite the varieties of variance reduced stochastic gradient descent methods, their analysis varies from each other. In this talk, I will first present a unified framework, under which we manage to abstract different variance reduced stochastic gradient methods into one. Then I will introduce a new stochastic method for composed optimization problems, and illustrate its performance via several imaging problems.

个人简介： 梁经纬，副教授，上海交通大学自然科学研究院。梁经纬于2013年获得上海交通大学数学硕士学位，之后于2016年获得法国卡昂大学数学博士学位。2017至2020年，梁经纬在英国剑桥大学理论物理与应用数学系从事博士后研究工作，并于2020年底加入伦敦玛丽王后大学数学科学学院任数据科学讲师。2021年7月，正式加入上海交通大学。梁经纬的主要研究兴趣为数学图像处理，非光滑优化和数据科学等。