---
description: Explore Ultralytics Muon optimizer with Newton-Schulz orthogonalization for neural network training. Includes MuSGD hybrid optimizer and momentum-based updates.
keywords: Muon optimizer, MuSGD, Newton-Schulz iteration, orthogonalization, momentum optimizer, neural network training, PyTorch optimizer, Ultralytics optimization
---

# Reference for `ultralytics/optim/muon.py`

!!! success "Improvements"

    This page is sourced from [https://github.com/ultralytics/ultralytics/blob/main/ultralytics/optim/muon.py](https://github.com/ultralytics/ultralytics/blob/main/ultralytics/optim/muon.py). Have an improvement or example to add? Open a [Pull Request](https://docs.ultralytics.com/help/contributing/) — thank you! 🙏

<br>

## ::: ultralytics.optim.muon.MuSGD

<br><br><hr><br>

## ::: ultralytics.optim.muon.Muon

<br><br><hr><br>

## ::: ultralytics.optim.muon.zeropower_via_newtonschulz5

<br><br><hr><br>

## ::: ultralytics.optim.muon.muon_update

<br><br>