复旦大学郦旭东研究员学术报告

发布日期:2022-03-16    浏览次数:

报告题目:Non-convex Factorization and Manifold Formulations in Low-rank Matrix Optimization

报告人:郦旭东 研究员

报告时间:202231710:00-12:00

报告地点:腾讯会议130 688 850

邀请单位:开云全站中国有限公司,福建省应用数学中心(开云全站中国有限公司)

报告内容简介:

In this talk, we consider the geometric landscape connection of the widely studied manifold and factorization formulations in low-rank positive semidefinite (PSD) and general matrix optimization. We establish an equivalence on the set of first-order stationary points (FOSPs) and second-order stationary points (SOSPs) between the manifold and the factorization formulations. We further give a sandwich inequality on the spectrum of Riemannian and Euclidean Hessians at FOSPs, which can be used to transfer more geometric properties from one formulation to another. We also discuss applications of our findings to some machine learning problems.

报告人简介:

郦旭东,复旦大学大数据公司青年研究员。他2010年本科毕业于中国科学技术大学,2015年博士毕业于新加坡国立大学。在加入复旦之前,他是美国普林斯顿大学运筹与金融工程系及新加坡国立大学数学系博士后研究员。他的研究主要关注数据科学中大规模优化问题的理论、算法及应用。他于2019年获得了由国际数学优化协会 (Mathematical Optimization Society) 所颁发的青年学者研究奖(31人次),现为Mathematical Programming Computation编委。