报告题目：A Few Thoughts on Deep Learning-Based PDE Solvers

报告时间：2021年5月26日，星期三，上午9:00—11:00（北京时间）

腾讯会议ID：298 700 073

报告人：Haizhao Yang（杨海钊），普渡大学

报告摘要:

The remarkable success of deep learning in computer science has evinced potentially great applications of deep learning in computational and applied mathematics. Understanding the mathematical principles of deep learning is crucial to validating and advancing deep learning-based PDE solvers. We present a few thoughts on the theoretical foundation of this topic for high-dimensional partial differential equations including approximation, optimization, and generalization. Though our analysis is not a complete story and there are many missing pieces to make it well-justified, it may still be helpful to provide some insights into deep learning.

报告人简介：

Haizhao Yang has been an assistant professor of mathematics and data science at Purdue University since 2019. Prior to that, he was an assistant professor at the National University of Singapore from 2017 to 2019, and a visiting assistant professor at Duke University from 2015 to 2017. He received a B.Sc. at Shanghai Jiao Tong University in 2010, an M.Sc. at the University of Texas at Austin in 2012, and a Ph.D. at Stanford University in 2015. His research focuses on machine learning, data science, applied and computational mathematics. He is a recipient of the National Science Foundation CAREER Award (2020) for his contribution to deep learning-based scientific computing.