English
Related papers

Related papers: Accelerating SGD with momentum for over-parameteri…

200 papers

Stochastic gradient descent~(SGD) and its variants have been the dominating optimization methods in machine learning. Compared to SGD with small-batch training, SGD with large-batch training can better utilize the computational power of…

Machine Learning · Statistics 2024-04-16 Shen-Yi Zhao , Chang-Wei Shi , Yin-Peng Xie , Wu-Jun Li

In this paper, we study the stochastic gradient descent (SGD) method for the nonconvex nonsmooth optimization, and propose an accelerated SGD method by combining the variance reduction technique with Nesterov's extrapolation technique.…

Optimization and Control · Mathematics 2019-02-18 Feihu Huang , Songcan Chen

We prove new convergence rates for a generalized version of stochastic Nesterov acceleration under interpolation conditions. Unlike previous analyses, our approach accelerates any stochastic gradient method which makes sufficient progress…

Optimization and Control · Mathematics 2025-01-27 Aaron Mishkin , Mert Pilanci , Mark Schmidt

We analyze a class of stochastic gradient algorithms with momentum on a high-dimensional random least squares problem. Our framework, inspired by random matrix theory, provides an exact (deterministic) characterization for the sequence of…

Optimization and Control · Mathematics 2021-10-27 Courtney Paquette , Elliot Paquette

Nesterov's well-known scheme for accelerating gradient descent in convex optimization problems is adapted to accelerating stationary iterative solvers for linear systems. Compared with classical Krylov subspace acceleration methods, the…

Optimization and Control · Mathematics 2021-08-10 Tao Hong , Irad Yavneh

The training of modern deep learning neural network calls for large amounts of computation, which is often provided by GPUs or other specific accelerators. To scale out to achieve faster training speed, two update algorithms are mainly…

Machine Learning · Computer Science 2020-05-15 Yemao Xu , Dezun Dong , Weixia Xu , Xiangke Liao

Nesterov's accelerated gradient descent method (AGD) is a seminal deterministic first-order method known to achieve the optimal order of iteration complexity for solving convex smooth optimization problems. Two distinct sequences of…

Optimization and Control · Mathematics 2026-03-10 Yan Wu , Yipeng Zhang , Lu Liu , Yuyuan Ouyang

In recent years, even though Stochastic Gradient Descent (SGD) and its variants are well-known for training neural networks, it suffers from limitations such as the lack of theoretical guarantees, vanishing gradients, and excessive…

Optimization and Control · Mathematics 2022-02-17 Junxiang Wang , Hongyi Li , Liang Zhao

Commonly used optimization algorithms often show a trade-off between good generalization and fast training times. For instance, stochastic gradient descent (SGD) tends to have good generalization; however, adaptive gradient methods have…

Machine Learning · Computer Science 2023-06-14 Aditya Cowsik , Tankut Can , Paolo Glorioso

Stochastic gradient descent (SGD) is the main approach for training deep networks: it moves towards the optimum of the cost function by iteratively updating the parameters of a model in the direction of the gradient of the loss evaluated on…

Machine Learning · Computer Science 2021-03-30 Loris Nanni , Gianluca Maguolo , Alessandra Lumini

Classical machine learning models such as deep neural networks are usually trained by using Stochastic Gradient Descent-based (SGD) algorithms. The classical SGD can be interpreted as a discretization of the stochastic gradient flow. In…

Optimization and Control · Mathematics 2023-10-03 Valentin Leplat , Daniil Merkulov , Aleksandr Katrutsa , Daniel Bershatsky , Olga Tsymboi , Ivan Oseledets

Nesterov's accelerated gradient descent (AGD), an instance of the general family of "momentum methods", provably achieves faster convergence rate than gradient descent (GD) in the convex setting. However, whether these methods are superior…

Machine Learning · Computer Science 2017-11-29 Chi Jin , Praneeth Netrapalli , Michael I. Jordan

Accelerated stochastic gradient descent (ASGD) is a workhorse in deep learning and often achieves better generalization performance than SGD. However, existing optimization theory can only explain the faster convergence of ASGD, but cannot…

Machine Learning · Computer Science 2023-11-27 Xuheng Li , Yihe Deng , Jingfeng Wu , Dongruo Zhou , Quanquan Gu

Over the last decades, Stochastic Gradient Descent (SGD) has been intensively studied by the Machine Learning community. Despite its versatility and excellent performance, the optimization of large models via SGD still is a time-consuming…

Machine Learning · Computer Science 2025-12-01 Mauro DL Tosi , Martin Theobald

As the size of models and datasets grows, it has become increasingly common to train models in parallel. However, existing distributed stochastic gradient descent (SGD) algorithms suffer from insufficient utilization of computational…

Machine Learning · Computer Science 2023-08-30 Xin Zhou , Ling Chen , Houming Wu

The extrapolation strategy raised by Nesterov, which can accelerate the convergence rate of gradient descent methods by orders of magnitude when dealing with smooth convex objective, has led to tremendous success in training machine…

Machine Learning · Computer Science 2020-06-18 W. Tao , Z. Pan , G. Wu , Q. Tao

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

We present a generalization of Nesterov's accelerated gradient descent algorithm. Our algorithm (AGNES) provably achieves acceleration for smooth convex and strongly convex minimization tasks with noisy gradient estimates if the noise…

Machine Learning · Statistics 2024-11-04 Kanan Gupta , Jonathan W. Siegel , Stephan Wojtowytsch

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

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