Deeper or Wider: A Perspective from Optimal Generalization Error with Sobolev Loss

Yahong Yang; Juncai He

2024 ICML ICML 2024

Deeper or Wider: A Perspective from Optimal Generalization Error with Sobolev Loss

Abstract

No abstract available. No abstract was captured for this paper when its proceedings were scraped - most often an older edition published without one online. How the corpus is built.

Authors

Yahong Yang, Juncai He

Topics

Machine Learning > Optimization & Theory > Learning Theory Machine Learning > Optimization & Theory > Statistical Learning Deep Learning > Architectures > Neural Networks

Keywords

generalization error deep neural network wide neural network regularity sample points sobolev loss

Download PDF