CUED Publications database

Dropout as a structured shrinkage prior

Nalisnick, E and Hernández-Lobato, JM and Smyth, P (2019) Dropout as a structured shrinkage prior. 36th International Conference on Machine Learning, ICML 2019, 2019-J. pp. 8273-8283.

Full text not available from this repository.

Abstract

© 2019 by the author(s). Dropout regularization of deep neural networks has been a mysterious yet effective tool to prevent overfitting. Explanations for its success range from the prevention of "co-adapted" weights to it being a form of cheap Bayesian inference. We propose a novel framework for understanding multiplicative noise in neural networks, considering continuous distributions as well as Bernoulli noise (i.e. dropout). We show that multiplicative noise induces structured shrinkage priors on a network's weights. We derive the equivalence through reparametrization properties of scale mixtures and without invoking any approximations. Given the equivalence, we then show that dropout's Monte Carlo training objective approximates marginal MAP estimation. We leverage these insights to propose a novel shrinkage framework for resnets, terming the prior automatic depth determination as it is the natural analog of automatic relevance determination for network depth. Lastly, we investigate two inference strategies that improve upon the aforementioned MAP approximation in regression benchmarks.

Item Type: Article
Uncontrolled Keywords: stat.ML stat.ML cs.LG
Subjects: UNSPECIFIED
Divisions: Div F > Computational and Biological Learning
Depositing User: Cron Job
Date Deposited: 30 May 2019 01:15
Last Modified: 18 Aug 2020 12:54
DOI: