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: 2022年10月13日上午8:30-9:30
报告地点: 腾讯会议(线上)
会议ID:775-893-216 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。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必赢3003am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。