Why Warmup the Learning Rate? Underlying Mechanisms and Improvements

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Kalra, Dayal Singh, Barkeshli, Maissam
Format:	Preprint
Published:	2024
Subjects:	Machine Learning Disordered Systems and Neural Networks
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Internet

https://arxiv.org/abs/2406.09405