| title | MUON-RT Reusing the Teacher's Trajectory for Momentum-Free Muon for LLM Self-Distillation |
|---|---|
| authors | Aryan Das, Vinay Kumar Verma, Aakansha Mishra |
| date | 2026-10-30 |
| venue | arXiv (preprint, not peer reviewed) |
| id | arXiv:2610.41104 |
| affiliation | Indian Institute of Technology, Kanpur |
| upvotes | 14 (Hugging Face Daily Papers, 2026-11-06) |
| links | abs pdf hf |
| cite | |
| abstract | Self-distillation methods for large language models with an exponential moving average (EMA) teacher already retain a history of student updates. Muon nevertheless stores a separate momentum buffer, increasing persistent training memory. We propose Muon with Reused Teacher (Muon-RT), which reuses the teacher-student displacement to eliminate momentum buffers for hidden weight matrices. We show that this displacement encodes an exponentially weighted history of applied updates and smooths temporally uncorrelated noise under a local model. Muon-RT removes its radial component, normalizes it spectrally, and mixes it with the current gradient after Newton-Schulz (NS) orthogonalization. Under explicit regularity and alignment assumptions, we establish linear contraction of an expected objective-gap bound toward a residual error level. With Self-Distillation Fine-Tuning (SDFT) on Qwen2.5-7B-Instruct, Muon-RT improves average accuracy over AdamW by 2.6 points with 42% less persistent memory, and over momentum Muon by 5.4 points with 27% less persistent memory. With Self-Distillation Policy Optimization (SDPO) on Olmo-3-7B-Instruct, it improves average accuracy over AdamW by 2.0 points. |
bibtex
@misc{das2026muon,
title={MUON-RT Reusing the Teacher's Trajectory for Momentum-Free Muon for LLM Self-Distillation},
author={Aryan Das and Vinay Kumar Verma and Aakansha Mishra},
year={2026},
eprint={2610.41104},
archivePrefix={arXiv},
url={https://arxiv.org/abs/2610.41104}
}