Timezone: »

Exploring Generalization in Deep Learning
Behnam Neyshabur · Srinadh Bhojanapalli · David Mcallester · Nati Srebro

Tue Dec 05 06:30 PM -- 10:30 PM (PST) @ Pacific Ballroom #142 #None

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.

Author Information

Behnam Neyshabur (New York University)
Srinadh Bhojanapalli (Google Research)
David Mcallester (Toyota Tech Institute Chicago)
Nati Srebro (TTI-Chicago)

More from the Same Authors