English
Related papers

Related papers: Drop-Muon: Update Less, Converge Faster

200 papers

In large-scale optimization, the cheapness and effectiveness of update steps are the most crucial factors for a successful optimizer. Sign-based optimizers like Lion or Signum produce cheap per-step updates, whereas Muon's spectral…

Large models recently are widely applied in artificial intelligence, so efficient training of large models has received widespread attention. More recently, a useful Muon optimizer is specifically designed for matrix-structured parameters…

Machine Learning · Computer Science 2025-09-22 Feihu Huang , Yuning Luo , Songcan Chen

The majority of parameters in neural networks are naturally represented as matrices. However, most commonly used optimizers treat these matrix parameters as flattened vectors during optimization, potentially overlooking their inherent…

Machine Learning · Statistics 2026-04-15 Wei Shen , Ruichuan Huang , Minhui Huang , Cong Shen , Jiawei Zhang

Muon improves neural-network training by orthogonalizing matrix-valued updates, but it leaves each layer's update magnitude controlled mostly by a global learning rate. We introduce OrScale, a trust-ratio extension of Muon built on a simple…

Machine Learning · Computer Science 2026-05-11 Yuxuan Lou , Yang You

In this paper, we propose DeMuon, a method for decentralized matrix optimization over a given communication topology. DeMuon incorporates matrix orthogonalization via Newton-Schulz iterations-a technique inherited from its centralized…

Optimization and Control · Mathematics 2025-10-03 Chuan He , Shuyi Ren , Jingwei Mao , Erik G. Larsson

Deep neural networks achieve state-of-the-art and sometimes super-human performance across various domains. However, when learning tasks sequentially, the networks easily forget the knowledge of previous tasks, known as "catastrophic…

Computer Vision and Pattern Recognition · Computer Science 2021-05-18 Shixiang Tang , Dapeng Chen , Jinguo Zhu , Shijie Yu , Wanli Ouyang

Deep Learning (DL) model-based AI services are increasingly offered in a variety of predictive analytics services such as computer vision, natural language processing, speech recognition. However, the quality of the DL models can degrade…

Distributed, Parallel, and Cluster Computing · Computer Science 2020-11-04 Anirban Bhattacharjee , Ajay Dev Chhokra , Hongyang Sun , Shashank Shekhar , Aniruddha Gokhale , Gabor Karsai , Abhishek Dubey

Deep learning's success has been attributed to the training of large, overparameterized models on massive amounts of data. As this trend continues, model training has become prohibitively costly, requiring access to powerful computing…

Machine Learning · Computer Science 2021-11-25 Ravi S Raju , Kyle Daruwalla , Mikko Lipasti

We consider distributed optimization under communication constraints for training deep learning models. We propose a new algorithm, whose parameter updates rely on two forces: a regular gradient step, and a corrective direction dictated by…

Machine Learning · Computer Science 2022-04-29 Yunfei Teng , Wenbo Gao , Francois Chalus , Anna Choromanska , Donald Goldfarb , Adrian Weller

Pretrained language models have achieved remarkable success in natural language understanding. However, fine-tuning pretrained models on limited training data tends to overfit and thus diminish performance. This paper presents Bi-Drop, a…

Computation and Language · Computer Science 2023-10-24 Shoujie Tong , Heming Xia , Damai Dai , Runxin Xu , Tianyu Liu , Binghuai Lin , Yunbo Cao , Zhifang Sui

Finetuning a pretrained model has become a standard approach for training neural networks on novel tasks, resulting in fast convergence and improved performance. In this work, we study an alternative finetuning method, where instead of…

Machine Learning · Computer Science 2023-07-04 Gal Kaplun , Andrey Gurevich , Tal Swisa , Mazor David , Shai Shalev-Shwartz , Eran Malach

Existing deep learning-based depth completion methods generally employ massive stacked layers to predict the dense depth map from sparse input data. Although such approaches greatly advance this task, their accompanied huge computational…

Computer Vision and Pattern Recognition · Computer Science 2023-10-16 Yufei Wang , Bo Li , Ge Zhang , Qi Liu , Tao Gao , Yuchao Dai

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

Muon-style optimizers leverage Newton-Schulz (NS) iterations to orthogonalize updates, yielding update geometries that often outperform Adam-series methods. However, this orthogonalization discards magnitude information, rendering training…

Machine Learning · Computer Science 2026-03-10 Peng Cheng , Jiucheng Zang , Qingnan Li , Liheng Ma , Yufei Cui , Yingxue Zhang , Boxing Chen , Ming Jian , Wen Tong

We introduce dropout compaction, a novel method for training feed-forward neural networks which realizes the performance gains of training a large model with dropout regularization, yet extracts a compact neural network for run-time…

Machine Learning · Statistics 2017-05-25 Yotaro Kubo , George Tucker , Simon Wiesler

Training of deep neural networks (DNNs) frequently involves optimizing several millions or even billions of parameters. Even with modern computing architectures, the computational expense of DNN training can inhibit, for instance, network…

Machine Learning · Computer Science 2020-06-26 Mauricio E. Tano , Gavin D. Portwood , Jean C. Ragusa

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

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

Muon and related normalized optimizers decouple the choice of update direction from the choice of step scale, but their practical performance remains sensitive to the scale of the normalized step. We study adaptive scaling rules for Muon in…

Machine Learning · Computer Science 2026-05-20 Yury Demidovich , Abhishek Chakraborty , Grigory Malinovsky , Angelia Nedić , Peter Richtárik

Understanding whether deep neural networks are effectively optimized remains challenging, as training occurs in highly nonconvex landscapes and standard metrics provide limited visibility into layer-wise learning quality. This challenge is…

Machine Learning · Computer Science 2026-05-05 Arian Eamaz , Farhang Yeganegi , Mojtaba Soltanalian