Gradient Descent Converges Linearly to Flatter Minima than Gradient Flow in Shallow Linear Networks

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Beneventano, Pierfrancesco, Woodworth, Blake
Format:	Preprint
Published:	2025
Subjects:	Machine Learning Optimization and Control
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Internet

https://arxiv.org/abs/2501.09137