English
Related papers

Related papers: A Convergence Analysis of Nesterov's Accelerated G…

200 papers

In this paper, we generalize the well-known Nesterov's accelerated gradient (AG) method, originally designed for convex smooth optimization, to solve nonconvex and possibly stochastic optimization problems. We demonstrate that by properly…

Optimization and Control · Mathematics 2013-10-15 Saeed Ghadimi , Guanghui Lan

Two major momentum-based techniques that have achieved tremendous success in optimization are Polyak's heavy ball method and Nesterov's accelerated gradient. A crucial step in all momentum-based methods is the choice of the momentum…

Machine Learning · Statistics 2017-12-21 Vishwak Srinivasan , Adepu Ravi Sankar , Vineeth N Balasubramanian

Gradient restarting has been shown to improve the numerical performance of accelerated gradient methods. This paper provides a mathematical analysis to understand these advantages. First, we establish global linear convergence guarantees…

Optimization and Control · Mathematics 2025-05-28 Chenglong Bao , Liang Chen , Jiahong Li , Zuowei Shen

We propose AdaNAG, an adaptive accelerated gradient method based on Nesterov's accelerated gradient method. AdaNAG is line-search-free, parameter-free, and achieves the accelerated convergence rates $f(x_k) - f_\star =…

Optimization and Control · Mathematics 2025-05-20 Jaewook J. Suh , Shiqian Ma

We present a totally asynchronous algorithm for convex optimization that is based on a novel generalization of Nesterov's accelerated gradient method. This algorithm is developed for fast convergence under "total asynchrony," i.e., allowing…

Optimization and Control · Mathematics 2024-06-17 Ellie Pond , April Sebok , Zachary Bell , Matthew Hale

The Nesterov's accelerated quasi-Newton (L)NAQ method has shown to accelerate the conventional (L)BFGS quasi-Newton method using the Nesterov's accelerated gradient in several neural network (NN) applications. However, the calculation of…

Optimization and Control · Mathematics 2021-12-03 S. Indrapriyadarsini , Shahrzad Mahboubi , Hiroshi Ninomiya , Takeshi Kamio , Hideki Asai

Modern machine learning focuses on highly expressive models that are able to fit or interpolate the data completely, resulting in zero training loss. For such models, we show that the stochastic gradients of common loss functions satisfy a…

Machine Learning · Computer Science 2019-04-09 Sharan Vaswani , Francis Bach , Mark Schmidt

The stochastic momentum method is a commonly used acceleration technique for solving large-scale stochastic optimization problems in artificial neural networks. Current convergence results of stochastic momentum methods under non-convex…

Optimization and Control · Mathematics 2023-01-26 Dongpo Xu , Jinlan Liu , Yinghua Lu , Jun Kong , Danilo Mandic

Machine learning and deep learning are widely researched fields that provide solutions to many modern problems. Due to the complexity of new problems related to the size of datasets, efficient approaches are obligatory. In optimization…

Optimization and Control · Mathematics 2025-10-01 Stepan Trifonov , Leonid Levin , Savelii Chezhegov , Aleksandr Beznosikov

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

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

Adaptive gradient methods like AdaGrad are widely used in optimizing neural networks. Yet, existing convergence guarantees for adaptive gradient methods require either convexity or smoothness, and, in the smooth setting, only guarantee…

Machine Learning · Computer Science 2019-10-22 Xiaoxia Wu , Simon S. Du , Rachel Ward

Neural-ODE parameterize a differential equation using continuous depth neural network and solve it using numerical ODE-integrator. These models offer a constant memory cost compared to models with discrete sequence of hidden layers in which…

Machine Learning · Computer Science 2025-03-27 Sheikh Waqas Akhtar

The vast majority of convergence rates analysis for stochastic gradient methods in the literature focus on convergence in expectation, whereas trajectory-wise almost sure convergence is clearly important to ensure that any instantiation of…

Machine Learning · Computer Science 2022-07-12 Jun Liu , Ye Yuan

We present a coupled system of ODEs which, when discretized with a constant time step/learning rate, recovers Nesterov's accelerated gradient descent algorithm. The same ODEs, when discretized with a decreasing learning rate, leads to novel…

Optimization and Control · Mathematics 2020-09-02 Maxime Laborde , Adam M. Oberman

Communication overhead is a major bottleneck hampering the scalability of distributed machine learning systems. Recently, there has been a surge of interest in using gradient compression to improve the communication efficiency of…

Machine Learning · Computer Science 2019-10-29 Shuai Zheng , Ziyue Huang , James T. Kwok

Nesterov's accelerated gradient method for minimizing a smooth strongly convex function $f$ is known to reduce $f(\x_k)-f(\x^*)$ by a factor of $\eps\in(0,1)$ after $k\ge O(\sqrt{L/\ell}\log(1/\eps))$ iterations, where $\ell,L$ are the two…

Optimization and Control · Mathematics 2016-05-03 Sahar Karimi , Stephen A. Vavasis

A common problem in training neural networks is the vanishing and/or exploding gradient problem which is more prominently seen in training of Recurrent Neural Networks (RNNs). Thus several algorithms have been proposed for training RNNs.…

Machine Learning · Computer Science 2019-09-10 S. Indrapriyadarsini , Shahrzad Mahboubi , Hiroshi Ninomiya , Hideki Asai

Several variants of stochastic gradient descent (SGD) have been proposed to improve the learning effectiveness and efficiency when training deep neural networks, among which some recent influential attempts would like to adaptively control…

Machine Learning · Computer Science 2020-10-22 Jie Liu , Chen Lin , Chuming Li , Lu Sheng , Ming Sun , Junjie Yan , Wanli Ouyang

Adaptive gradient methods such as Adam have been shown to be very effective for training deep neural networks (DNNs) by tracking the second moment of gradients to compute the individual learning rates. Differently from existing methods, we…

Machine Learning · Computer Science 2019-02-26 Guoqiang Zhang , Kenta Niwa , W. Bastiaan Kleijn