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.
@article{arxiv.1706.08947,
title = {Exploring Generalization in Deep Learning},
author = {Behnam Neyshabur and Srinadh Bhojanapalli and David McAllester and Nathan Srebro},
journal= {arXiv preprint arXiv:1706.08947},
year = {2017}
}