Bayesian Deep Learning and a Probabilistic Perspective of Generalization

02/20/2020 ∙ by Andrew Gordon Wilson, et al. ∙ 41

The key distinguishing property of a Bayesian approach is marginalization, rather than using a single setting of weights. Bayesian marginalization can particularly improve the accuracy and calibration of modern deep neural networks, which are typically underspecified by the data, and can represent many compelling but different solutions. We show that deep ensembles provide an effective mechanism for approximate Bayesian marginalization, and propose a related approach that further improves the predictive distribution by marginalizing within basins of attraction, without significant overhead. We also investigate the prior over functions implied by a vague distribution over neural network weights, explaining the generalization properties of such models from a probabilistic perspective. From this perspective, we explain results that have been presented as mysterious and distinct to neural network generalization, such as the ability to fit images with random labels, and show that these results can be reproduced with Gaussian processes. Finally, we provide a Bayesian perspective on tempering for calibrating predictive distributions.

READ FULL TEXT
POST COMMENT

Comments

There are no comments yet.

Authors

page 15

page 24

page 25

page 26

Code Repositories

This week in AI

Get the week's most popular data science and artificial intelligence research sent straight to your inbox every Saturday.