Iterative Orthogonalization Scaling Laws

Fuente: arXiv
Saved in:
Bibliographic Details
Main Author: Selvaraj, Devan
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916725840150528
author Selvaraj, Devan
author_facet Selvaraj, Devan
contents The muon optimizer has picked up much attention as of late as a possible replacement to the seemingly omnipresent Adam optimizer. Recently, care has been taken to document the scaling laws of hyper-parameters under muon such as weight decay and learning rate. However, at much larger scales the iterative orthogonalization procedure present in muon may suffer a possible issue as the singular values of random matrices shrink with scale. This paper shows this scaling behavior theoretically and empirically on random matrices but does not suggest what to do about it.
format Preprint
id arxiv_https___arxiv_org_abs_2505_04005
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Iterative Orthogonalization Scaling Laws
Selvaraj, Devan
Machine Learning
68T07
The muon optimizer has picked up much attention as of late as a possible replacement to the seemingly omnipresent Adam optimizer. Recently, care has been taken to document the scaling laws of hyper-parameters under muon such as weight decay and learning rate. However, at much larger scales the iterative orthogonalization procedure present in muon may suffer a possible issue as the singular values of random matrices shrink with scale. This paper shows this scaling behavior theoretically and empirically on random matrices but does not suggest what to do about it.
title Iterative Orthogonalization Scaling Laws
topic Machine Learning
68T07
url https://arxiv.org/abs/2505.04005