Exploring Generalization in Deep Learning

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.

Authors

• Behnam Neyshabur
• Srinadh Bhojanapalli
• David McAllester Bart Selman
• Nati Srebro

Keywords

No keywords are indexed for this paper.