arxiv:1706.08947

Exploring Generalization in Deep Learning

Published on Jul 6, 2017

Authors:

Abstract

Research examines various explanations for deep network generalization, focusing on norm-based control, sharpness, and robustness, while connecting sharpness to PAC-Bayes theory and evaluating explanatory power.

AI-generated summary

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.

View arXiv page View PDF Add to collection

Community

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

· Sign up or log in to comment

Upvote

Models citing this paper 0

No model linking this paper

Cite arxiv.org/abs/1706.08947 in a model README.md to link it from this page.

Datasets citing this paper 0

No dataset linking this paper

Cite arxiv.org/abs/1706.08947 in a dataset README.md to link it from this page.

Spaces citing this paper 0

No Space linking this paper

Cite arxiv.org/abs/1706.08947 in a Space README.md to link it from this page.

Collections including this paper 0

No Collection including this paper

Add this paper to a collection to link it from this page.