ML Seminar: Numerical understanding of neural networks: from representation to learning dynamics

The UMN Machine Learning Seminar Series brings together faculty, students, and local industrial partners who are interested in the theoretical, computational, and applied aspects of machine learning, to pose problems, exchange ideas, and foster collaborations. The talks are every Tuesday from 11 a.m. - 12 p.m. during the Spring 2024 semester.

This week's speaker, Hongkai Zhao (Duke University), will be giving a talk titled "Numerical understanding of neural networks: from representation to learning dynamics".

Abstract

In this talk we present both numerical analysis and experiments to study a few basic computational issues in practice: (1) the numerical error one can achieve given a finite machine precision, (2) the learning dynamics and computation cost to achieve a given accuracy, and (3) stability with respect to perturbations. These issues are addressed for both approximation and optimization in asymptotic and non-asymptotic regimes.

Biography

Hongkai Zhao is Ruth F. DeVarney Distinguished Professor of Mathematics at Duke University. He got his Ph.D in Mathematics from UCLA in 1996. Hongkai Zhao received Sloan Fellowship in 2002 and the Feng Kang Prize in Scientific Computing in 2007. He is a SIAM Fellow.