Online Program Home
  My Program

All Times EDT

Abstract Details

Activity Number: 294 - Uncertainty Quantification in Deep Learning
Type: Invited
Date/Time: Wednesday, August 11, 2021 : 3:30 PM to 5:20 PM
Sponsor: Section on Bayesian Statistical Science
Abstract #316754
Title: Uncertainty Quantification for Sparse Deep Learning
Author(s): Veronika Rockova* and Yuexi Wang
Companies: University of Chicago and University of Chicago
Keywords:
Abstract:

Deep learning methods continue to have a decided impact on machine learning, both in theory and in practice. Statistical theoretical developments have been mostly concerned with approximability or rates of estimation when recovering infinite dimensional objects (curves or densities). Despite the impressive array of available theoretical results, the literature has been largely silent about uncertainty quantification for deep learning. This paper takes a step forward in this important direction by taking a Bayesian point of view. We study Gaussian approximability of certain aspects of posterior distributions of sparse deep ReLU architectures in non-parametric regression. Building on tools from Bayesian non-parametrics, we provide semi-parametric Bernstein-von Mises theorems for linear and quadratic functionals, which guarantee that implied Bayesian credible regions have valid frequentist coverage. Our results provide new theoretical justifications for (Bayesian) deep learning with ReLU activation functions, highlighting their inferential potential. (Joint work with Yuexi Wang)


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

Back to the full JSM 2021 program