Why is Normalization Preferred? A Worst-Case Complexity Theory for Stochastically Preconditioned SGD under Heavy-Tailed Noise

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Fang, Yuchen, Demmel, James, Lavaei, Javad
Format:	Preprint
Published:	2026
Subjects:	Machine Learning Numerical Analysis Optimization and Control
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Internet

https://arxiv.org/abs/2602.13413