English
Related papers

Related papers: Muon is Scalable for LLM Training

200 papers

The Muon optimizer has emerged as a compelling alternative to Adam for training large language models, achieving remarkable computational savings through gradient orthogonalization. However, Muon's optimizer state is more sensitive to…

Machine Learning · Computer Science 2026-05-13 Yupeng Su , Ruijie Zhang , Ziyue Liu , Yequan Zhao , Zheng Zhang

The Muon optimizer has received considerable attention for its strong performance in training large language models, yet the design principle behind its matrix-gradient orthogonalization remains largely elusive. In this paper, we introduce…

Optimization and Control · Mathematics 2026-04-03 Zhehang Du , Weijie Su

While large language models (LLMs) have emerged as a significant advancement in artificial intelligence, the hardware and computational costs for training LLMs are also significantly burdensome. Among the state-of-the-art optimizers, AdamW…

Machine Learning · Computer Science 2026-02-02 Yufei Gu , Zeke Xie

Muon updates matrix parameters via the matrix sign of the gradient and has shown strong empirical gains, yet its dynamics and scaling behavior remain unclear in theory. We study Muon in a linear associative memory model with softmax…

Machine Learning · Computer Science 2026-05-26 Binghui Li , Kaifei Wang , Han Zhong , Pinyan Lu , Liwei Wang

We introduce Pion, a spectrum-preserving optimizer for large language model (LLM) training based on orthogonal equivalence transformation. Unlike additive optimizers such as Adam and Muon, Pion updates each weight matrix through left and…

Machine Learning · Computer Science 2026-05-13 Kexuan Shi , Hanxuan Li , Zeju Qiu , Yandong Wen , Simon Buchholz , Weiyang Liu

Muon is a matrix-aware optimizer that leverages Newton-Schulz (NS) iterations to enforce spectral gradient orthogonalization by driving all singular values of the momentum matrix toward 1. While this uniform spectral whitening enhances…

Machine Learning · Computer Science 2026-05-20 Chongyu Fan , Gaowen Liu , Mingyi Hong , Ramana Rao Kompella , Sijia Liu

Recently, a new optimization method based on the linear minimization oracle (LMO), called Muon, has been attracting increasing attention since it can train neural networks faster than existing adaptive optimization methods, such as Adam. In…

Machine Learning · Computer Science 2025-10-01 Yuki Takezawa , Anastasia Koloskova , Xiaowen Jiang , Sebastian U. Stich

The Muon optimizer has rapidly emerged as a powerful, geometry-aware alternative to AdamW, demonstrating strong performance in large-scale training of neural networks. However, a critical theory-practice disconnect exists: Muon's efficiency…

Machine Learning · Computer Science 2025-10-24 Egor Shulgin , Sultan AlRashed , Francesco Orabona , Peter Richtárik

Muon has emerged as a strong competitor to AdamW for language model pre-training, yet its behavior at scale is sensitive to weight decay. Recent work has observed that, for Muon without decoupled weight decay, the spectral norm of weight…

Machine Learning · Computer Science 2026-05-12 Kai Lion , Florian Hübler , Bingcong Li , Antonio Orvieto , Niao He

Orthogonality-based optimizers, such as Muon, have recently shown strong performance across large-scale training and community-driven efficiency challenges. However, these methods rely on a costly gradient orthogonalization step. Even…

Artificial Intelligence · Computer Science 2025-12-05 Thibaut Boissin , Thomas Massena , Franck Mamalet , Mathieu Serrurier

Orthogonalized-momentum optimizers such as Muon improve transformer training by approximately whitening/orthogonalizing matrix-valued momentum updates via a short polar-decomposition iteration. However, polar-factor approximations typically…

Machine Learning · Computer Science 2026-03-19 Ben S. Southworth , Stephen Thomas

Muon has emerged as an efficient alternative to Adam for pretraining, yet remains underused for fine-tuning. A key obstacle is that most open models are pretrained with Adam, and naively switching to Muon for fine-tuning leads to degraded…

Machine Learning · Computer Science 2026-05-12 Xingyu Qu , Peigeng Huang , Samuel Horvath

The Muon optimizer is consistently faster than Adam in training Large Language Models (LLMs), yet the mechanism underlying its success remains unclear. This paper demystifies this mechanism through the lens of associative memory. By…

Machine Learning · Computer Science 2025-10-07 Shuche Wang , Fengzhuo Zhang , Jiaxiang Li , Cunxiao Du , Chao Du , Tianyu Pang , Zhuoran Yang , Mingyi Hong , Vincent Y. F. Tan

MLP is a heavily used backbone in modern deep learning (DL) architectures for supervised learning on tabular data, and AdamW is the go-to optimizer used to train tabular DL models. Unlike architecture design, however, the choice of…

Machine Learning · Computer Science 2026-04-20 Yury Gorishniy , Ivan Rubachev , Dmitrii Feoktistov , Artem Babenko

The $\mu$-parameterization ($\mu$P) provides a principled foundation for large language model (LLM) training by prescribing width-independent learning dynamics, which in turn enables predictable scaling behavior and robust hyperparameter…

Machine Learning · Computer Science 2026-01-08 John Zhao

The recently proposed Muon optimizer updates weight matrices via orthogonalized momentum and has demonstrated strong empirical success in large language model training. However, it remains unclear how to determine the learning rates for…

Machine Learning · Computer Science 2025-09-09 Minxin Zhang , Yuxuan Liu , Hayden Schaeffer

Orthogonalized-update optimizers such as Muon improve training of matrix-valued parameters, but existing extensions typically either rescale updates after orthogonalization or use heavier whitening-based preconditioners before it. We…

Machine Learning · Computer Science 2026-05-12 Da Chang , Qiankun Shi , Lvgang Zhang , Yu Li , Ruijie Zhang , Yao Lu , Yongxiang Liu , Ganzhao Yuan

Training large language models requires optimization algorithms that are not only statistically effective, but also computationally and memory efficient at extreme scale. Although Adam remains the dominant optimizer for large-scale…

Machine Learning · Computer Science 2026-05-12 Aditya Ranganath

Adversarial training (AT) remains one of the most reliable empirical defenses against adversarial attacks. Its robustness critically depends on how the underlying min-max objective is optimized. In practice, Stochastic Gradient Descent…

Machine Learning · Computer Science 2026-05-27 Jun Yan , Weiquan Huang , Jiankai Zuo , Yujian Mo , Xi Fang , Chengliang Wu , Zeming Wei

Muon has recently emerged as a competitive alternative to AdamW for large-scale pre-training, with orthogonalization via Newton-Schulz (NS) iterations as its core operation. Existing Muon variants apply a uniform NS schedule to all…

Machine Learning · Computer Science 2026-05-19 Xinlin Zhuang , Panyi Ouyang , Yichen Li , Jiangming Shi , Yizhang Chen , Shuman Liu , Ying Qian , Weiyang Liu , Haibo Zhang , Imran Razzak