【Academic Seminar】Some Statistical Results on Deep Learning: Interpolation, Optimality and Sparsity - Prof. Guang Cheng

Topic: Some Statistical Results on Deep Learning: Interpolation, Optimality and Sparsity

Speaker: Prof. Guang Cheng, Purdue University

Time and Date: 14:00 - 15:00, Tuesday, December 17, 2019

Venue: Room 110, Zhi Xin Building

Abstract：

This talk discusses three aspects of deep learning from a statistical perspective: interpolation, optimality and sparsity. The first one attempts to interpret the double descent phenomenon by precisely characterizing a U-shaped curve within the “over-fitting regime,” while the second one focuses on the statistical optimality of neural network classification in a student-teacher framework. This talk is concluded by proposing sparsity induced training of neural network with statistical guarantee. 
 

Biography：

Cheng is a Professor of Statistics at Purdue University.  He received his PhD in Statistics from University of Wisconsin-Madison in 2006. His research interests include Big Data and Deep Learning. Cheng is the recipient of the NSF CAREER award, Noether Young Scholar Award and Simons Fellowship in Mathematics. He is currently a member of Institute for Advanced Study, Princeton in the Fall of 2019. Please visit his big data theory research group at http://www.stat.purdue.edu/~chengg/