Weight Decay may matter more than muP for Learning Rate Transfer in Practice

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Kosson, Atli, Welborn, Jeremy, Liu, Yang, Jaggi, Martin, Chen, Xi
Format:	Preprint
Published:	2025
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/2510.19093