Skip to yearly menu bar Skip to main content


Spotlight

Dropout: Explicit Forms and Capacity Control

Raman Arora · Peter Bartlett · Poorya Mianjy · Nati Srebro

Abstract:

We investigate the capacity control provided by dropout in various machine learning problems. First, we study dropout for matrix completion, where it induces a distribution-dependent regularizer that equals the weighted trace-norm of the product of the factors. In deep learning, we show that the distribution-dependent regularizer due to dropout directly controls the Rademacher complexity of the underlying class of deep neural networks. These developments enable us to give concrete generalization error bounds for the dropout algorithm in both matrix completion as well as training deep neural networks.

Chat is not available.