Online Program Home
My Program

Abstract Details

Activity Number: 602 - Theory at the Intersection of Machine Learning and Statistics
Type: Invited
Date/Time: Thursday, August 2, 2018 : 8:30 AM to 10:20 AM
Sponsor: IMS
Abstract #326813 Presentation
Title: Statistical Properties of Deep Networks
Author(s): Peter Bartlett*
Companies: UC Berkeley
Keywords: Neural Networks; Pattern Classification; Risk Bounds

Deep neural networks have improved state-of-the-art performance for prediction problems across an impressive range of application areas, and they have become a central ingredient in AI systems. This talk considers the statistical properties of deep networks, in particular, how their performance on training data compares to predictive accuracy, and how to measure the complexity of functions computed by these networks. For multiclass classification problems, we present margin-based misclassification probability bounds that scale with a certain margin-normalized "spectral complexity," involving the product of the spectral norms of the weight matrices in the network. We show how these bounds give insight into the observed performance of these networks in practical problems.

Joint work with Matus Telgarsky and Dylan Foster.

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

Back to the full JSM 2018 program