Poster

Exploring Generalization in Deep Learning

Behnam Neyshabur ⋅ Srinadh Bhojanapalli ⋅ David Mcallester ⋅ Nati Srebro

Keywords: Deep Learning

2017 Poster

[ Paper]

Abstract

With a goal of understanding what drives generalization in deep networks, we consider several recently suggested explanations, including norm-based control, sharpness and robustness. We study how these measures can ensure generalization, highlighting the importance of scale normalization, and making a connection between sharpness and PAC-Bayes theory. We then investigate how well the measures explain different observed phenomena.

Chat is not available.