学术报告

【online】机器学习中的优化问题选讲 (及加州大学戴维斯分校数学系博士招生宣讲会 )

发布人:发布时间: 2021-11-02

字体大小: 【小】 【中】 【大】

题目:机器学习中的优化问题选讲 (及加州大学戴维斯分校数学系博士招生宣讲会 )

 

报告人:马士谦 教授(UC Davis 数学系)

 

时间:2021年11月5日  12:00-13:00

 

报告方式:腾讯会议   ID号:615967184

 

摘要:本次报告介绍机器学习中的一类重要问题:最优传输问题,及其优化算法的设计和理论。在机器学习和深度学习中有着重要应用的最优传输问题, 本质上是一个最优化问题。最优传输问题中一个重要的研究方向是如何降维,从而在样本量有限的情况下近似求解该问题。我们介绍一种新的降维技术:投影鲁棒的最优传输。这个问题可以看成是一个黎曼流形上的极小极大问题。我们介绍这类问题的一种新的求解方法。另一个相关的问题是在有多个agent的情况下,如何解决最优传输问题的公平性问题。这个问题可以看成是一个凸的极小极大问题。我们针对这种问题介绍一种新的坐标下降方法。

 

报告人简介:Shiqian Ma is currently a tenured associate professor in the Department of Mathematics at University of California, Davis. He received his BS in Mathematics from Peking University in 2003, MS in Computational Mathematics from the Chinese Academy of Sciences in 2006, and PhD in Industrial Engineering and Operations Research from Columbia University in 2011. Shiqian was an NSF postdoctoral fellow in the Institute for Mathematics and its Applications at the University of Minnesota during 2011-2012 and an assistant professor in the Department of Systems Engineering and Engineering Management at the Chinese University of Hong Kong during 2012-2017. His current research interests include theory and algorithms for large-scale optimization, and their various applications in machine learning, signal processing and statistics. Shiqian received the INFORMS Optimization Society Best Student Paper Prize in 2010, and an honorable mention in the INFORMS George Nicholson Student Paper Competition in 2011. He was one of the finalists for the 2011 IBM Herman Goldstine fellowship. He received the Journal of the Operations Research Society of China Excellent Paper Award in 2016. Shiqian served as the area chair for ICML 2021 and currently serves on the editorial board of Journal of Scientific Computing.

 

邀请人:杨俊锋 教授