Why Do We Need Weight Decay in Modern Deep Learning?

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	D'Angelo, Francesco, Andriushchenko, Maksym, Varre, Aditya, Flammarion, Nicolas
Format:	Preprint
Published:	2023
Subjects:	Machine Learning
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Internet

https://arxiv.org/abs/2310.04415