papers AI Learner
The Github is limit! Click to go to the new site.

On Dropout and Nuclear Norm Regularization

2019-05-28
Poorya Mianjy, Raman Arora

Abstract

We give a formal and complete characterization of the explicit regularizer induced by dropout in deep linear networks with squared loss. We show that (a) the explicit regularizer is composed of an $\ell_2$-path regularizer and other terms that are also re-scaling invariant, (b) the convex envelope of the induced regularizer is the squared nuclear norm of the network map, and (c) for a sufficiently large dropout rate, we characterize the global optima of the dropout objective. We validate our theoretical findings with empirical results.

Abstract (translated by Google)
URL

http://arxiv.org/abs/1905.11887

PDF

http://arxiv.org/pdf/1905.11887


Similar Posts

Comments