English
Related papers

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

200 papers

Muon has recently emerged as a strong alternative to AdamW for training neural networks, with encouraging large-scale pretraining results and growing evidence that matrix-structured updates can be faster in practice. Yet Muon, and more…

Machine Learning · Computer Science 2026-05-19 Abdurakhmon Sadiev , Artavazd Maranjyan , Ivan Ilin , Peter Richtárik

Incorporating stochasticity into the training process of deep convolutional networks is a widely used technique to reduce overfitting and improve regularization. Existing techniques often require modifying the architecture of the network by…

Computer Vision and Pattern Recognition · Computer Science 2024-11-26 Evgeny Hershkovitch Neiterman , Gil Ben-Artzi

Deep Neural Network (DNN) models are usually trained sequentially from one layer to another, which causes forward, backward and update locking's problems, leading to poor performance in terms of training time. The existing parallel…

Distributed, Parallel, and Cluster Computing · Computer Science 2022-07-25 Samson B. Akintoye , Liangxiu Han , Huw Lloyd , Xin Zhang , Darren Dancey , Haoming Chen , Daoqiang Zhang

Recent empirical research has demonstrated that deep learning optimizers based on the linear minimization oracle (LMO) over specifically chosen Non-Euclidean norm balls, such as Muon and Scion, outperform Adam-type methods in the training…

Optimization and Control · Mathematics 2025-12-19 Xun Qian , Hussein Rammal , Dmitry Kovalev , Peter Richtárik

Adversarial training has been proven to be a powerful regularization method to improve the generalization of models. However, current adversarial training methods only attack the original input sample or the embedding vectors, and their…

Machine Learning · Computer Science 2021-08-31 Shiwen Ni , Jiawen Li , Hung-Yu Kao

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

Asynchronous distributed algorithms are a popular way to reduce synchronization costs in large-scale optimization, and in particular for neural network training. However, for nonsmooth and nonconvex objectives, few convergence guarantees…

Optimization and Control · Mathematics 2020-07-14 Vyacheslav Kungurtsev , Malcolm Egan , Bapi Chatterjee , Dan Alistarh

The past few years have witnessed the fast development of different regularization methods for deep learning models such as fully-connected deep neural networks (DNNs) and Convolutional Neural Networks (CNNs). Most of previous methods…

Machine Learning · Computer Science 2018-11-20 Hengyue Pan , Hui Jiang , Xin Niu , Yong Dou

Structured pruning is an effective approach for compressing large pre-trained neural networks without significantly affecting their performance. However, most current structured pruning methods do not provide any performance guarantees, and…

Machine Learning · Computer Science 2023-02-14 Marwa El Halabi , Suraj Srinivas , Simon Lacoste-Julien

Preconditioned adaptive methods have gained significant attention for training deep neural networks, as they capture rich curvature information of the loss landscape. The central challenge in this field lies in balancing preconditioning…

Machine Learning · Computer Science 2026-05-14 Shenyang Deng , Zhuoli Ouyang , Tianyu Pang , Zihang Liu , Ruochen Jin , Shuhua Yu , Yaoqing Yang

This paper proposes a new method to improve the training efficiency of deep convolutional neural networks. During training, the method evaluates scores to measure how much each layer's parameters change and whether the layer will continue…

Computer Vision and Pattern Recognition · Computer Science 2026-04-28 Giorgio Cruciata , Luca Cruciata , Liliana Lo Presti , Jan Van Gemert , Marco La Cascia

It has been shown that deep neural networks are prone to overfitting on biased training data. Towards addressing this issue, meta-learning employs a meta model for correcting the training bias. Despite the promising performances, super slow…

Machine Learning · Computer Science 2021-05-03 Youjiang Xu , Linchao Zhu , Lu Jiang , Yi Yang

Despite dropout's ubiquity in machine learning, its effectiveness as a form of data augmentation remains under-explored. We address two key questions: (i) When is dropout effective as an augmentation strategy? (ii) Is dropout uniquely…

Machine Learning · Computer Science 2025-06-02 Rickard Brüel-Gabrielsson , Tongzhou Wang , Manel Baradad , Justin Solomon

Most uses of machine learning today involve training a model from scratch for a particular task, or sometimes starting with a model pretrained on a related task and then fine-tuning on a downstream task. Both approaches offer limited…

Machine Learning · Computer Science 2022-05-26 Andrea Gesmundo , Jeff Dean

Geometry-aware optimization algorithms, such as Muon, have achieved remarkable success in training deep neural networks (DNNs). These methods leverage the underlying geometry of DNNs by selecting appropriate norms for different layers and…

Machine Learning · Computer Science 2026-02-04 Jie Hao , Xiaochuan Gong , Jie Xu , Zhengdao Wang , Mingrui Liu

The training of deep neural networks is inherently a nonconvex optimization problem, yet standard approaches such as stochastic gradient descent (SGD) require simultaneous updates to all parameters, often leading to unstable convergence and…

Machine Learning · Computer Science 2025-08-07 Chengcheng Yan , Jiawei Xu , Zheng Peng , Qingsong Wang

While traditional Deep Learning (DL) optimization methods treat all training samples equally, Distributionally Robust Optimization (DRO) adaptively assigns importance weights to different samples. However, a significant gap exists between…

Due to lack of data, overfitting ubiquitously exists in real-world applications of deep neural networks (DNNs). We propose advanced dropout, a model-free methodology, to mitigate overfitting and improve the performance of DNNs. The advanced…

Machine Learning · Computer Science 2021-08-11 Jiyang Xie , Zhanyu Ma , and Jianjun Lei , Guoqiang Zhang , Jing-Hao Xue , Zheng-Hua Tan , Jun Guo

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

Dropout is a simple but efficient regularization technique for achieving better generalization of deep neural networks (DNNs); hence it is widely used in tasks based on DNNs. During training, dropout randomly discards a portion of the…

Neural and Evolutionary Computing · Computer Science 2020-10-22 Hiroshi Inoue