Fast Predictive Uncertainty for Classification with Bayesian Deep Networks release_xuzva4pzjrcgfj5zsmyorfx4hy

by Marius Hobbhahn, Agustinus Kristiadi, Philipp Hennig

Released as a article .

2022  

Abstract

In Bayesian Deep Learning, distributions over the output of classification neural networks are often approximated by first constructing a Gaussian distribution over the weights, then sampling from it to receive a distribution over the softmax outputs. This is costly. We reconsider old work (Laplace Bridge) to construct a Dirichlet approximation of this softmax output distribution, which yields an analytic map between Gaussian distributions in logit space and Dirichlet distributions (the conjugate prior to the Categorical distribution) in the output space. Importantly, the vanilla Laplace Bridge comes with certain limitations. We analyze those and suggest a simple solution that compares favorably to other commonly used estimates of the softmax-Gaussian integral. We demonstrate that the resulting Dirichlet distribution has multiple advantages, in particular, more efficient computation of the uncertainty estimate and scaling to large datasets and networks like ImageNet and DenseNet. We further demonstrate the usefulness of this Dirichlet approximation by using it to construct a lightweight uncertainty-aware output ranking for ImageNet.
In text/plain format

Archived Files and Locations

application/pdf  2.0 MB
file_3v4kwforivgwvi4xwcqjsxeehy
arxiv.org (repository)
web.archive.org (webarchive)
Read Archived PDF
Preserved and Accessible
Type  article
Stage   submitted
Date   2022-05-31
Version   v4
Language   en ?
arXiv  2003.01227v4
Work Entity
access all versions, variants, and formats of this works (eg, pre-prints)
Catalog Record
Revision: bec01b9f-bdfb-42b5-8f57-78904607de6c
API URL: JSON