English
Related papers

Related papers: Momentum Improves Normalized SGD

200 papers

While momentum-based methods, in conjunction with stochastic gradient descent (SGD), are widely used when training machine learning models, there is little theoretical understanding on the generalization error of such methods. In this work,…

Machine Learning · Computer Science 2021-09-27 Ali Ramezani-Kebrya , Ashish Khisti , Ben Liang

Heavy-ball momentum with decaying learning rates is widely used with SGD for optimizing deep learning models. In contrast to its empirical popularity, the understanding of its theoretical property is still quite limited, especially under…

Machine Learning · Computer Science 2024-03-19 Rui Pan , Yuxing Liu , Xiaoyu Wang , Tong Zhang

Stochastic gradient descent (SGD) is a standard optimization method to minimize a training error with respect to network parameters in modern neural network learning. However, it typically suffers from proliferation of saddle points in the…

Machine Learning · Computer Science 2017-11-23 Haiping Huang , Taro Toyoizumi

We suggest a simple adaptive step-size procedure, which does not require any line-search, for a general class of nonlinear optimization methods and prove convergence of a general method under mild assumptions. In particular, the goal…

Optimization and Control · Mathematics 2018-03-05 Igor Konnov

The momentum acceleration technique is widely adopted in many optimization algorithms. However, there is no theoretical answer on how the momentum affects the generalization performance of the optimization algorithms. This paper studies…

Machine Learning · Computer Science 2022-05-30 Bohan Wang , Qi Meng , Huishuai Zhang , Ruoyu Sun , Wei Chen , Zhi-Ming Ma , Tie-Yan Liu

We combine two advanced ideas widely used in optimization for machine learning: shuffling strategy and momentum technique to develop a novel shuffling gradient-based method with momentum, coined Shuffling Momentum Gradient (SMG), for…

Optimization and Control · Mathematics 2021-06-10 Trang H. Tran , Lam M. Nguyen , Quoc Tran-Dinh

In this paper, we suggest a new framework for analyzing primal subgradient methods for nonsmooth convex optimization problems. We show that the classical step-size rules, based on normalization of subgradient, or on the knowledge of optimal…

Optimization and Control · Mathematics 2023-11-27 Yurii Nesterov

The scale of deep learning nowadays calls for efficient distributed training algorithms. Decentralized momentum SGD (DmSGD), in which each node averages only with its neighbors, is more communication efficient than vanilla Parallel momentum…

Machine Learning · Computer Science 2021-04-27 Kun Yuan , Yiming Chen , Xinmeng Huang , Yingya Zhang , Pan Pan , Yinghui Xu , Wotao Yin

Stochastic gradient descent (SGD) has been widely studied in the literature from different angles, and is commonly employed for solving many big data machine learning problems. However, the averaging technique, which combines all iterative…

Machine Learning · Computer Science 2020-05-28 Zhishuai Guo , Yan Yan , Tianbao Yang

Heavy ball momentum is crucial in accelerating (stochastic) gradient-based optimization algorithms for machine learning. Existing heavy ball momentum is usually weighted by a uniform hyperparameter, which relies on excessive tuning.…

Machine Learning · Computer Science 2021-10-19 Tao Sun , Huaming Ling , Zuoqiang Shi , Dongsheng Li , Bao Wang

Following the same routine as [SSJ20], we continue to present the theoretical analysis for stochastic gradient descent with momentum (SGD with momentum) in this paper. Differently, for SGD with momentum, we demonstrate it is the two…

Machine Learning · Computer Science 2022-09-13 Bin Shi

When training neural networks, it has been widely observed that a large step size is essential in stochastic gradient descent (SGD) for obtaining superior models. However, the effect of large step sizes on the success of SGD is not well…

Machine Learning · Computer Science 2023-02-17 Amirkeivan Mohtashami , Martin Jaggi , Sebastian Stich

Various gradient compression schemes have been proposed to mitigate the communication cost in distributed training of large scale machine learning models. Sign-based methods, such as signSGD, have recently been gaining popularity because of…

Optimization and Control · Mathematics 2021-06-25 Mher Safaryan , Peter Richtárik

For SGD based distributed stochastic optimization, computation complexity, measured by the convergence rate in terms of the number of stochastic gradient calls, and communication complexity, measured by the number of inter-node…

Optimization and Control · Mathematics 2019-05-14 Hao Yu , Rong Jin

Empirically, it has been observed that adding momentum to Stochastic Gradient Descent (SGD) accelerates the convergence of the algorithm. However, the literature has been rather pessimistic, even in the case of convex functions, about the…

Optimization and Control · Mathematics 2025-01-27 Julien Hermant , Marien Renaud , Jean-François Aujol , Charles Dossal , Aude Rondepierre

Momentum has become a crucial component in deep learning optimizers, necessitating a comprehensive understanding of when and why it accelerates stochastic gradient descent (SGD). To address the question of ''when'', we establish a…

Machine Learning · Computer Science 2023-06-16 Jingwen Fu , Bohan Wang , Huishuai Zhang , Zhizheng Zhang , Wei Chen , Nanning Zheng

In this paper, we propose and analyze SQuARM-SGD, a communication-efficient algorithm for decentralized training of large-scale machine learning models over a network. In SQuARM-SGD, each node performs a fixed number of local SGD steps…

Machine Learning · Computer Science 2021-10-12 Navjot Singh , Deepesh Data , Jemin George , Suhas Diggavi

Under mild assumptions stochastic gradient methods asymptotically achieve an optimal rate of convergence if the arithmetic mean of all iterates is returned as an approximate optimal solution. However, in the absence of stochastic noise, the…

Optimization and Control · Mathematics 2022-10-06 Melinda Hagedorn , Florian Jarre

In machine learning, stochastic gradient descent (SGD) is widely deployed to train models using highly non-convex objectives with equally complex noise models. Unfortunately, SGD theory often makes restrictive assumptions that fail to…

Machine Learning · Computer Science 2022-10-11 Vivak Patel , Shushu Zhang , Bowen Tian

Asynchronous optimization algorithms often require delay bounds to prove their convergence, though these bounds can be difficult to obtain in practice. Existing algorithms that do not require delay bounds often converge slowly. Therefore,…

Optimization and Control · Mathematics 2025-08-12 Ellie Pond , Yichen Zhao , Matthew Hale