English

Generalization in Deep Learning

Machine Learning 2023-08-29 v9 Artificial Intelligence Machine Learning Neural and Evolutionary Computing

Abstract

This paper provides theoretical insights into why and how deep learning can generalize well, despite its large capacity, complexity, possible algorithmic instability, nonrobustness, and sharp minima, responding to an open question in the literature. We also discuss approaches to provide non-vacuous generalization guarantees for deep learning. Based on theoretical observations, we propose new open problems and discuss the limitations of our results.

Keywords

Cite

@article{arxiv.1710.05468,
  title  = {Generalization in Deep Learning},
  author = {Kenji Kawaguchi and Leslie Pack Kaelbling and Yoshua Bengio},
  journal= {arXiv preprint arXiv:1710.05468},
  year   = {2023}
}

Comments

Published by Cambridge University Press. BibTeX of this paper is available at: https://people.csail.mit.edu/kawaguch/bibtex.html