Online Program Home
My Program

Abstract Details

Activity Number: 141 - Statistical Understanding of Deep Learning
Type: Invited
Date/Time: Monday, July 29, 2019 : 10:30 AM to 12:20 PM
Sponsor: Section on Statistical Learning and Data Science
Abstract #300361
Title: Some Statistical Insights into Deep Learning
Author(s): Hao Wu* and Yingying Fan and Jinchi Lv
Companies: University of Southern California and University of Southern California and University of Southern California
Keywords: deep learning; statistical insights; latent structure; subspace clustering; classification; Gaussian mixture

Deep learning is a popular machine learning method that has gained a lot of interest in recent years, and it has benefited almost every aspect of modern big data applications. Most deep learning methods are regarded as black-box procedures, in the sense that their statistical properties still largely remain mysterious. In our recent paper (joint with Yingying Fan and Jinchi Lv), a simulation study was designed with latent subspace structure motivated by image recognition. We empirically demonstrated that the performance of deep neural network (DNN) is comparable to the ideal procedure knowing the true latent subspace information a priori. We showed that DNN does not really do efficient clustering in any of its layers. We also provided statistical theory and heuristic arguments to support our empirical discoveries and demonstrated the utility of our theoretical framework on the real data application. In this talk, I will introduce our statistical insights into DNN.

Authors who are presenting talks have a * after their name.

Back to the full JSM 2019 program