English
Related papers

Related papers: Can Muon Fine-tune Adam-Pretrained Models?

200 papers

Optimizers play an important role in both pretraining and finetuning stages when training large language models (LLMs). In this paper, we present an observation that full finetuning with the same optimizer as in pretraining achieves a…

Machine Learning · Computer Science 2026-05-08 Yuxing Liu , Jianyu Wang , Tong Zhang

For a long period of time, Adam has served as the ubiquitous default choice for training deep neural networks. Recently, many new optimizers have been introduced, out of which Muon has perhaps gained the highest popularity due to its…

Machine Learning · Computer Science 2026-03-03 Sara Dragutinović , Rajesh Ranganath

The choice of optimizer significantly impacts the training efficiency and computational costs of large language models (LLMs). Recently, the Muon optimizer has demonstrated promising results by orthogonalizing parameter updates, improving…

Machine Learning · Computer Science 2025-10-08 Zichong Li , Liming Liu , Chen Liang , Weizhu Chen , Tuo Zhao

Large Language Models (LLMs) achieve competitive performance across diverse natural language processing (NLP) tasks, yet pretraining is computationally demanding, making optimizer efficiency an important practical consideration. Muon…

Machine Learning · Computer Science 2026-01-22 Jingru Li , Yibo Fan , Huan Li

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

Muon optimizer has demonstrated robust results in pretraining of language models but its performance in finetuning of existing public pretrained models is not yet explored. Currently, Muon is used along with AdamW introducing a scope of…

Computation and Language · Computer Science 2025-11-11 Saurabh Page , Advait Joshi , S. S. Sonawane

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

Muon has emerged as a promising optimizer for large-scale foundation model pre-training by exploiting the matrix structure of neural network updates through iterative orthogonalization. However, its practical efficiency is limited by the…

Machine Learning · Computer Science 2026-04-14 Ziyue Liu , Ruijie Zhang , Zhengyang Wang , Yequan Zhao , Yupeng Su , Zi Yang , Zheng Zhang

Recently, the Muon optimizer based on matrix orthogonalization has demonstrated strong results in training small-scale language models, but the scalability to larger models has not been proven. We identify two crucial techniques for scaling…

We demonstrate that Muon, the simplest instantiation of a second-order optimizer, explicitly expands the Pareto frontier over AdamW on the compute-time tradeoff. We find that Muon is more effective than AdamW in retaining data efficiency at…

Muon has recently emerged as a strong optimizer for large language model pre-training, orthogonalizing the momentum matrix via Newton--Schulz polar iterations. A natural intuition is that polar iterations, by flattening the singular…

Machine Learning · Computer Science 2026-05-15 Ruijie Zhang , Yequan Zhao , Ziyue Liu , Zhengyang Wang , Yupeng Su , Liyan Tan , Zheng Zhang

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

Large language models (LLMs) have demonstrated impressive generalization and emergent capabilities, yet their pre-training remains computationally expensive and sensitive to optimization dynamics. While Adam-based optimizers offer fast…

Machine Learning · Computer Science 2025-10-01 Junjie Wang , Pan Zhou , Yiming Dong , Huan Li , Jia Li , Xun Zhou , Qicheng Lao , Cong Fang , Zhouchen Lin

The rapid scaling of large language models (LLMs) has made low-precision training essential for reducing memory, improving efficiency, and enabling larger models and datasets. Existing convergence theories for adaptive optimizers, however,…

Machine Learning · Computer Science 2026-03-03 Xuan Tang , Jichu Li , Difan Zou

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

The Muon optimizer has recently offered a promising alternative to AdamW for large language model training, leveraging matrix orthogonalization to produce geometry-aware updates. However, like all first-order methods, Muon can become…

Machine Learning · Computer Science 2026-05-27 Jiacheng Li , Jianchao Tan , Hongtao Xu , Jiaqi Zhang , Yifan Lu , Yerui Sun , Yuchen Xie , Xunliang Cai

We present a comprehensive theoretical and empirical study of the Muon optimizer for training transformers only with a small to medium decoder (30M - 200M parameters), with an emphasis on its mathematical foundations, convergence properties…

Machine Learning · Computer Science 2025-09-30 Sushant Mehta , Raj Dandekar , Rajat Dandekar , Sreedath Panat

In this note, we inspect the convergence of a new optimizer for pretraining LLMs, namely the Muon optimizer. Such an optimizer is closely related to a specialized steepest descent method where the update direction is the minimizer of the…

Optimization and Control · Mathematics 2025-06-03 Jiaxiang Li , Mingyi Hong

The rapid progress of large language models (LLMs) is increasingly constrained by memory and deployment costs, motivating compression methods for practical deployment. Many state-of-the-art compression pipelines leverage the low-rank…

AdamW has long been the dominant optimizer in language model pretraining, despite numerous claims that alternative optimizers offer 1.4 to 2x speedup. We posit that two methodological shortcomings have obscured fair comparisons and hindered…

Machine Learning · Computer Science 2025-09-08 Kaiyue Wen , David Hall , Tengyu Ma , Percy Liang
‹ Prev 1 2 3 10 Next ›