English
Related papers

Related papers: When and Why Momentum Accelerates SGD:An Empirical…

200 papers

Learning rate scheduling plays a critical role in the optimization of deep neural networks, directly influencing convergence speed, stability, and generalization. While existing schedulers such as cosine annealing, cyclical learning rates,…

Machine Learning · Computer Science 2026-03-05 Ayush K. Varshney , Šarūnas Girdzijauskas , Konstantinos Vandikas , Aneta Vulgarakis Feljan

Based on SGD, previous works have proposed many algorithms that have improved convergence speed and generalization in stochastic optimization, such as SGDm, AdaGrad, Adam, etc. However, their convergence analysis under non-convex conditions…

Machine Learning · Computer Science 2024-02-05 Yichuan Deng , Zhao Song , Chiwun Yang

Recently, Stochastic Gradient Descent (SGD) and its variants have become the dominant methods in the large-scale optimization of machine learning (ML) problems. A variety of strategies have been proposed for tuning the step sizes, ranging…

Machine Learning · Computer Science 2022-08-02 Xiaoyu Li

Stochastic momentum methods have been widely adopted in training deep neural networks. However, their theoretical analysis of convergence of the training objective and the generalization error for prediction is still under-explored. This…

Machine Learning · Computer Science 2018-08-31 Yan Yan , Tianbao Yang , Zhe Li , Qihang Lin , Yi Yang

In this paper, we consider a general stochastic optimization problem which is often at the core of supervised learning, such as deep learning and linear classification. We consider a standard stochastic gradient descent (SGD) method with a…

Machine Learning · Statistics 2018-12-27 Lam M. Nguyen , Nam H. Nguyen , Dzung T. Phan , Jayant R. Kalagnanam , Katya Scheinberg

Stochastic gradient descent (SGD) is a workhorse algorithm for solving large-scale optimization problems in data science and machine learning. Understanding the convergence of SGD is hence of fundamental importance. In this work we examine…

Numerical Analysis · Mathematics 2024-12-11 Lehan Chen , Yuji Nakatsukasa

Stochastic gradient descent (\textsc{Sgd}) methods are the most powerful optimization tools in training machine learning and deep learning models. Moreover, acceleration (a.k.a. momentum) methods and diagonal scaling (a.k.a. adaptive…

Machine Learning · Statistics 2018-10-02 Qi Deng , Yi Cheng , Guanghui Lan

Asynchronous stochastic gradient descent (SGD) is attractive from a speed perspective because workers do not wait for synchronization. However, the Transformer model converges poorly with asynchronous SGD, resulting in substantially lower…

Computation and Language · Computer Science 2021-11-30 Alham Fikri Aji , Kenneth Heafield

Stochastic gradient descent (SGD) is of fundamental importance in deep learning. Despite its simplicity, elucidating its efficacy remains challenging. Conventionally, the success of SGD is ascribed to the stochastic gradient noise (SGN)…

Machine Learning · Computer Science 2023-02-21 Chengli Tan , Jiangshe Zhang , Junmin Liu

It has long been argued that minibatch stochastic gradient descent can generalize better than large batch gradient descent in deep neural networks. However recent papers have questioned this claim, arguing that this effect is simply a…

Machine Learning · Computer Science 2020-06-29 Samuel L. Smith , Erich Elsen , Soham De

Gradient descent-based optimization methods underpin the parameter training of neural networks, and hence comprise a significant component in the impressive test results found in a number of applications. Introducing stochasticity is key to…

Machine Learning · Computer Science 2021-06-01 Nikola B. Kovachki , Andrew M. Stuart

A variety of widely used optimization methods like SignSGD and Muon can be interpreted as instances of steepest descent under different norm-induced geometries. In this work, we study the implicit bias of mini-batch stochastic steepest…

Machine Learning · Computer Science 2026-02-13 Jichu Li , Xuan Tang , Difan Zou

Training neural networks requires optimizing a loss function that may be highly irregular, and in particular neither convex nor smooth. Popular training algorithms are based on stochastic gradient descent with momentum (SGDM), for which…

Machine Learning · Computer Science 2026-03-17 Qinzi Zhang , Ashok Cutkosky

Stochastic gradient descent with momentum (SGDM) is the dominant algorithm in many optimization scenarios, including convex optimization instances and non-convex neural network training. Yet, in the stochastic setting, momentum interferes…

Optimization and Control · Mathematics 2023-06-28 Junhyung Lyle Kim , Panos Toulis , Anastasios Kyrillidis

Momentum-based optimizers are widely adopted for training neural networks. However, the optimal selection of momentum coefficients remains elusive. This uncertainty impedes a clear understanding of the role of momentum in stochastic…

Machine Learning · Computer Science 2025-05-22 Xianliang Li , Jun Luo , Zhiwei Zheng , Hanxiao Wang , Li Luo , Lingkun Wen , Linlong Wu , Sheng Xu

Asynchronous stochastic gradient descent (SGD) enables scalable distributed training but suffers from gradient staleness. Existing mitigation strategies, such as delay-adaptive learning rates and staleness-aware filtering, typically…

Machine Learning · Computer Science 2026-05-15 Tehila Dahan , Roie Reshef , Sharon Goldstein , Kfir Y. Levy

Recent works have explored the use of momentum in local methods to enhance distributed SGD. This is particularly appealing in Federated Learning (FL), where momentum intuitively appears as a solution to mitigate the effects of statistical…

Machine Learning · Computer Science 2025-11-26 Riccardo Zaccone , Sai Praneeth Karimireddy , Carlo Masone

Stochastic Gradient Descent (SGD) and its variants are the most used algorithms in machine learning applications. In particular, SGD with adaptive learning rates and momentum is the industry standard to train deep networks. Despite the…

Machine Learning · Statistics 2020-07-29 Xiaoyu Li , Francesco Orabona

In order to extract the best possible performance from asynchronous stochastic gradient descent one must increase the mini-batch size and scale the learning rate accordingly. In order to achieve further speedup we introduce a technique that…

Computation and Language · Computer Science 2018-09-17 Nikolay Bogoychev , Marcin Junczys-Dowmunt , Kenneth Heafield , Alham Fikri Aji

Recent findings by Cohen et al., 2021, demonstrate that when training neural networks using full-batch gradient descent with a step size of $\eta$, the largest eigenvalue $\lambda_{\max}$ of the full-batch Hessian consistently stabilizes…

Machine Learning · Computer Science 2025-12-30 Arseniy Andreyev , Pierfrancesco Beneventano