arXiv Machine Learning

LionMuon: Alternating Spectral and Sign Descent for Efficient Training

LionMuon is a new optimizer that alternates between Lion’s sign-based updates and Muon’s spectral matrix-sign updates on a fixed period P, sharing a single dual-EMA momentum buffer. This design keeps the memory footprint the same as Lion and half that of AdamW while reducing the average iteration cost compared to Muon. Experiments on 124M, 355M, and 720M models show LionMuon Pareto-dominates Muon, Lion, Signum, and AdamW across datasets and architectures, achieving lower validation loss with less compute.

arXiv AI
Aug 25

A Physical Response-and-Memory Model for Muon Optimization

The paper introduces a physical response-and-memory model for the Muon optimizer, explaining its semi‑orthogonalized momentum update as the maximally dissipative direction under an output‑side safety budget. It treats the weight matrix as a responsive medium with internal stress, showing that momentum corresponds to accumulated stress whose relaxation occurs over multiple timescales—fast and slow. Based on this, the authors propose the Bi‑Maxwell optimizer, which uses a two‑timescale memory kernel and achieves target loss in fewer steps on a public large‑language‑model benchmark.

By Yinze Hu, Hongjun Xiang, Xingao Gong, Hongyu Yu
arXiv Machine Learning
Aug 27

Spectral Allocation: Why Muon Outperforms Adam, and How to Improve Muon

The paper investigates why the orthogonal optimiser Muon outperforms Adam in large language model pretraining by analysing the spectral properties of Transformer loss landscapes. It finds that Muon’s momentum buffers exhibit an anisotropic spectral profile with a volatile head and a tolerant bulk, enabling larger effective step sizes. Building on this insight, the authors propose Spectral‑Aware Muon (SAMuon) and a lightweight variant, which adjust the bulk scaling while keeping the head unchanged, achieving 13–24 % fewer training tokens than Muon without extra FLOPs.

By Xiaodong Wu, Wenyi Yu, Chao Zhang, Philip Woodland
arXiv Machine Learning
2d ago

Variance-Adaptive Muon: Pre-Orthogonalization Variance Modulation for Efficient Language Model Pretraining

The paper introduces two variance‑adaptive variants of the Muon optimizer—Muon‑NSR and Muon‑VS—for language model pretraining. Both methods incorporate gradient‑variance information into Muon’s orthogonalization process without adding extra hyperparameters, preserving its spectral normalization structure. Experiments on Llama‑style and GPT‑2 models ranging from 125 M to 1.2 B parameters show that these variants outperform well‑tuned Muon baselines and achieve up to a 1.33× step‑to‑target speedup on Llama‑1.2B.

By Jingru Li, Yibo Fan, Huan Li
arXiv Machine Learning
Jun 3

MuLoCo: Muon is a practical inner optimizer for DiLoCo

arXiv:2505. 23725v3 Announce Type: replace Abstract: DiLoCo is a powerful framework for training large language models (LLMs), enabling larger optimal batch sizes and increased accelerator utilization under networking constraints.

By Benjamin Th\'erien, Xiaolong Huang, Aaron Defazio, Irina Rish, Eugene Belilovsky
arXiv Machine Learning
Jun 9

Convergence Bound and Critical Batch Size of Muon Optimizer

arXiv:2507. 01598v5 Announce Type: replace Abstract: Muon, a recently proposed optimizer that leverages the inherent matrix structure of neural network parameters, has demonstrated strong empirical performance, indicating its potential as a successor to standard optimizers such as AdamW.

By Naoki Sato, Hiroki Naganuma, Hideaki Iiduka
arXiv AI
Jun 4

Spectral Scaling Laws of Muon

arXiv:2606. 04058v1 Announce Type: cross Abstract: Orthonormalized update rules have rapidly become a leading choice of optimizer for training large language models, with recent open-source state-of-the-art models adopting Muon.

By Gagik Magakyan, Pablo Parrilo, Asuman Ozdaglar
arXiv AI
Jun 12

LoRA-Muon: Spectral Steepest Descent on the Low-Rank Manifold

arXiv:2606. 12921v1 Announce Type: cross Abstract: Low-Rank Adaptation (LoRA) significantly reduces compute and memory costs for finetuning Deep Learning models but is often harder to tune than dense training: when using factor-wise optimizers such as AdamW, it is sensitive to initialization choices, its optimal learning rates transfer poorly across ranks, and it often fails to beat dense baselines.

By Franz Louis Cesista, Katherine Crowson, C\'edric Simal, Stella Biderman