English
Related papers

Related papers: Muon is Scalable for LLM Training

200 papers

The Mixture of Experts (MoE) models are an emerging class of sparsely activated deep learning models that have sublinear compute costs with respect to their parameters. In contrast with dense models, the sparse architecture of MoE offers…

Recent optimizers like Muon, Scion, and Gluon have pushed the frontier of large-scale deep learning by exploiting layer-wise linear minimization oracles (LMOs) over non-Euclidean norm balls, capturing neural network structure in ways…

Machine Learning · Computer Science 2025-10-02 Kaja Gruntkowska , Alexander Gaponov , Zhirayr Tovmasyan , Peter Richtárik

The optimization of large language models (LLMs) remains a critical challenge, particularly as model scaling exacerbates sensitivity to algorithmic imprecision and training instability. Recent advances in optimizers have improved…

Machine Learning · Computer Science 2025-11-26 Wei He , Kai Han , Hang Zhou , Hanting Chen , Zhicheng Liu , Xinghao Chen , Yunhe Wang

Orthonormalized updates accelerate training, improve stability, and enable robust hyperparameter transfer, but existing methods like Muon rely on dense matrix operations that clash with sharded weights in large-scale LLM training, causing…

Machine Learning · Computer Science 2025-09-16 Kwangjun Ahn , Byron Xu , Natalie Abreu , Ying Fan , Gagik Magakyan , Pratyusha Sharma , Zheng Zhan , John Langford

The recently introduced optimizer, Muon, has gained increasing attention due to its superior performance across a wide range of applications. However, its effectiveness in federated learning remains unexplored. To address this gap, this…

Machine Learning · Computer Science 2025-10-07 Xinwen Zhang , Hongchang Gao

The Muon optimizer has recently attracted considerable attention for its strong empirical performance and use of orthogonalized updates on matrix-shaped parameters, yet its underlying mechanisms and relationship to adaptive optimizers such…

Machine Learning · Computer Science 2026-02-05 Xianbiao Qi , Marco Chen , Jiaquan Ye , Yelin He , Rong Xiao

Modern optimizers, like Muon, impose matrix-wise geometry constraints on their updates. These matrix-wise constraints can be unified under Linear Minimization Oracle (LMO) theory. However, all current methods impose fixed LMO geometries for…

Artificial Intelligence · Computer Science 2026-05-20 Thomas Massena , Corentin Friedrich , Mathieu Serrurier

The large language model (LLM) is typically integrated into the mainstream optimization protocol. No work has questioned whether maintaining the model integrity is \textit{indispensable} for promising performance. In this work, we introduce…

Computation and Language · Computer Science 2026-03-17 Mingyuan Zhang , Yue Bai , Huan Wang , Yizhou Wang , Qihua Dong , Yitian Zhang , Yun Fu

Transferring the optimal learning rate from small to large neural networks can enable efficient training at scales where hyperparameter tuning is otherwise prohibitively expensive. To this end, the Maximal Update Parameterization (muP)…

Machine Learning · Computer Science 2026-02-16 Atli Kosson , Jeremy Welborn , Yang Liu , Martin Jaggi , Xi Chen

Mixture of Experts (MoE) has become a key architectural paradigm for efficiently scaling Large Language Models (LLMs) by selectively activating a subset of parameters for each input token. However, standard MoE architectures face…

Machine Learning · Computer Science 2025-05-27 Zehua Liu , Han Wu , Ruifeng She , Xiaojin Fu , Xiongwei Han , Tao Zhong , Mingxuan Yuan

Zeroth-order (ZO) optimization provides a gradient-free alternative to first-order (FO) methods by estimating gradients via finite differences of function evaluations, and has recently emerged as a memory-efficient paradigm for fine-tuning…

Machine Learning · Computer Science 2026-02-24 Yicheng Lang , Changsheng Wang , Yihua Zhang , Mingyi Hong , Zheng Zhang , Wotao Yin , Sijia Liu

The pursuit of faster optimization algorithms remains an active and important research direction in deep learning. Recently, the Muon optimizer [JJB+24] has demonstrated promising empirical performance, but its theoretical foundation…

Machine Learning · Computer Science 2025-09-30 Lizhang Chen , Jonathan Li , Qiang Liu

Recent advances in spectral optimization, notably Muon, have demonstrated that constraining update steps to the Stiefel manifold can significantly accelerate training and improve generalization. However, Muon implicitly assumes an isotropic…

Machine Learning · Computer Science 2026-04-02 Yechen Zhang , Shuhao Xing , Junhao Huang , Kai Lv , Yunhua Zhou , Xipeng Qiu , Qipeng Guo , Kai Chen

Matrix-based optimizers have demonstrated immense potential in training Large Language Models (LLMs), however, designing an ideal optimizer remains a formidable challenge. A superior optimizer must satisfy three core desiderata: efficiency,…

Machine Learning · Computer Science 2026-05-06 Jinghui Yuan , Jiaxuan Zou , Shuo Wang , Yong Liu , Feiping Nie

We propose AdaMuon, a novel optimizer that combines element-wise adaptivity with orthogonal updates for large-scale neural network training. AdaMuon incorporates two tightly coupled mechanisms: (1) an element-wise second momentum estimator…

Machine Learning · Computer Science 2025-12-25 Chongjie Si , Debing Zhang , Wei Shen

Efficient stochastic optimization typically integrates an update direction that performs well in the deterministic regime with a mechanism adapting to stochastic perturbations. While Adam uses adaptive moment estimates to promote stability,…

Machine Learning · Computer Science 2026-02-23 Minxin Zhang , Yuxuan Liu , Hayden Schaeffer

Large language models deliver strong reasoning and tool-use skills, yet their computational demands make them impractical for edge or cost-sensitive deployments. We present \textbf{Xmodel-2.5}, a 1.3-billion-parameter small language model…

Machine Learning · Computer Science 2025-11-26 Yang Liu , Xiaolong Zhong , Ling Jiang

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

Training and fine-tuning large language models (LLMs) with hundreds of billions to trillions of parameters requires tens of thousands of GPUs, and a highly scalable software stack. In this work, we present a novel four-dimensional hybrid…

Muon-style optimizers take a matrix-valued momentum or preconditioned update $B = U \operatorname{diag}(\sigma_1,\ldots,\sigma_r) V^\top$ and replace it with its canonical partial polar factor $\operatorname{Pol}(B) = U V^\top$. This maps…

Machine Learning · Computer Science 2026-05-27 Albert Yi
‹ Prev 1 3 4 5 6 7 10 Next ›