Skip to content

intsystems/2026-Project-203

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

38 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

SignMuon: fast as Muon, communication-effective as SignSGD

License GitHub Contributors GitHub Issues GitHub Pull Requests

Author Maria Smirnova
Consultant Alexey Kravatskiy
Advisor Dmitry Kovalev, PhD

Assets

Abstract

SignSGD is a popular algorithm due to its strong performance in both centralized and decentralized settings: it performs competitively with Adam while being communication-efficient, transmitting up to 32x fewer bits than standard optimizers. This work introduces SignMuon, an algorithm that combines the structured LMO-based update of Muon with the sign compression of SignSGD. Our experiments show that SignMuon achieves performance nearly on par with Muon in the centralized setting and outperforms SignSGD in both centralized and federated settings. We establish theoretical convergence guarantees for SignMuon in the smooth non-convex regime. We further analyze specific modifications to the algorithm that enhance numerical stability without compromising communication efficiency. Finally, this work extends our framework to the broader class of SignA algorithms, where A denotes any LMO-based optimizer, providing a unified convergence analysis for sign-compressed LMO methods. Empirical validation is conducted on synthetic convex and nonconvex problems with known smoothness constants, CIFAR-airbench, federated MNIST/CIFAR-10 classification, and NanoGPT training.

Code

Centralized setting

The example of running code in the centralized setting:

python3 -m main --dataset cifar10 --optimizer signmuon --data data --device cuda:1 --epochs 50 

Federated setting

The example of running code in the federated setting:

python3 -m federated_main --model cnn2 --dataset cifar10 --algorithm signmuon --rounds 2000 --n_parties 10 --n_steps 3 --batch_size 64 --device cuda:3 --eval_freq 100

About

No description or website provided.

Topics

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

 
 
 

Contributors

Generated from kisnikser/m1p-template