Poster
Exploring Generalization in Deep Learning
Behnam Neyshabur · Srinadh Bhojanapalli · David Mcallester · Nati Srebro
Pacific Ballroom #142
Keywords: [ Deep Learning ]
[
Abstract
]
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.
Live content is unavailable. Log in and register to view live content