Optimal Learning-Rate Schedules under Functional Scaling Laws: Power Decay and Warmup-Stable-Decay

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Li, Binghui, Wang, Zilin, Chen, Fengling, Zhao, Shiyang, Zheng, Ruiheng, Wu, Lei
Format:	Preprint
Published:	2026
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/2602.06797