ENGLISH

【上海交通大学】A Framework for Analyzing Variance Reduced Stochastic Gradient Methods and a New One for Non-smooth Non-convex Optimization

发布时间:2022年10月10日 14:50 浏览量:

报告题目A Framework for Analyzing Variance Reduced Stochastic Gradient Methods and a New One for Non-smooth Non-convex Optimization

报告人: 梁经纬 副教授(上海交通大学)

报告时间: 20221013日上午8:30-9:30

报告地点: 腾讯会议(线上)

会议ID775-893-216       会议密码:2210

报告校内联系人:肖现涛 教授  联系电话:84708351-8307


报告摘要: Over the past years, stochastic optimization methods are becoming increasingly popular in traditional areas including inverse problems and signal/image processing. In this talk, I will introduce SPRING, a novel stochastic version of proximal alternating linearized minimization (PALM) algorithm for solving a class of non-smooth and non-convex optimization problems which arise in many statistical machine learning, computer vision and imaging applications. Theoretically, I will show that our proposed method with variance-reduced stochastic gradient estimators, such as SAGA and SARAH, achieves state-of-the-art oracle complexities. Numerical experiments on sparse non-negative matrix factorization, sparse principal component analysis and blind image deconvolution are also presented to demonstrate the efficiency of our algorithm.


报告人简介: 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。20172020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。20217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。



邮编:116024

电话:(86)-531-88565657

地址:大连市甘井子区凌工路2号

Copyright© 大连理工大学数学科学学院2024      辽ICP备05001357号