Exploring Generalization in Deep Learning

Code

• github.com/bneyshabur/generalization-bounds
  Officialpytorch★ 0
• github.com/yih117/Analyzing-the-Generalization-Capability-of-SGLD-Using-Properties-of-Gaussian-Channels
  pytorch★ 0

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.

Tasks

Reproductions