Stochastic Collapse: How Gradient Noise Attracts SGD Dynamics Towards Simpler Subnetworks

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Chen, Feng, Kunin, Daniel, Yamamura, Atsushi, Ganguli, Surya
Format:	Preprint
Published:	2023
Subjects:	Machine Learning Artificial Intelligence
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Internet

https://arxiv.org/abs/2306.04251