English
Related papers

Related papers: Provable Convergence of Nesterov's Accelerated Gra…

200 papers

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

Recently, {\it stochastic momentum} methods have been widely adopted in training deep neural networks. However, their convergence analysis is still underexplored at the moment, in particular for non-convex optimization. This paper fills the…

Optimization and Control · Mathematics 2016-05-06 Tianbao Yang , Qihang Lin , Zhe Li

Pipeline Parallelism (PP) enables large neural network training on small, interconnected devices by splitting the model into multiple stages. To maximize pipeline utilization, asynchronous optimization is appealing as it offers 100%…

Machine Learning · Computer Science 2025-05-05 Thalaiyasingam Ajanthan , Sameera Ramasinghe , Yan Zuo , Gil Avraham , Alexander Long

Current state-of-the-art analyses on the convergence of gradient descent for training neural networks focus on characterizing properties of the loss landscape, such as the Polyak-Lojaciewicz (PL) condition and the restricted strong…

Machine Learning · Computer Science 2024-01-08 Fangshuo Liao , Anastasios Kyrillidis

Nesterov's accelerated gradient methods (AGM) have been successfully applied in many machine learning areas. However, their empirical performance on training max-margin models has been inferior to existing specialized solvers. In this…

Machine Learning · Computer Science 2010-11-03 Xinhua Zhang , Ankan Saha , S. V. N. Vishwanathan

Nesterov's accelerated gradient method (NAG) marks a pivotal advancement in gradient-based optimization, achieving faster convergence compared to the vanilla gradient descent method for convex functions. However, its algorithmic complexity…

Optimization and Control · Mathematics 2025-01-21 Mingwei Fu , Bin Shi

A significant milestone in modern gradient-based optimization was achieved with the development of Nesterov's accelerated gradient descent (NAG) method. This forward-backward technique has been further advanced with the introduction of its…

Optimization and Control · Mathematics 2024-04-10 Bowen Li , Bin Shi , Ya-xiang Yuan

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

Recent studies have shown that proximal gradient (PG) method and accelerated gradient method (APG) with restarting can enjoy a linear convergence under a weaker condition than strong convexity, namely a quadratic growth condition (QGC).…

Optimization and Control · Mathematics 2017-05-16 Mingrui Liu , Tianbao Yang

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

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

We consider the problem of minimizing a strongly convex smooth function where the gradients are subject to additive worst-case deterministic errors that are square-summable. We study the trade-offs between the convergence rate and…

Optimization and Control · Mathematics 2023-10-23 Mert Gurbuzbalaban

As a representative continuous-depth neural network approach, stochastic differential equation (SDE)-based Bayesian neural networks (BNNs) have attracted considerable attention due to their solid theoretical foundations and strong potential…

Machine Learning · Statistics 2026-03-27 Chenxu Yu , Wenqi Fang

Nesterov's accelerated gradient method (NAG) achieves faster convergence than gradient descent for convex optimization but lacks monotonicity in function values. To address this, Beck and Teboulle [2009b] proposed a monotonic variant,…

Optimization and Control · Mathematics 2025-08-06 Mingwei Fu , 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

Momentum methods such as Polyak's heavy ball (HB) method, Nesterov's accelerated gradient (AG) as well as accelerated projected gradient (APG) method have been commonly used in machine learning practice, but their performance is quite…

Machine Learning · Statistics 2019-08-20 Bugra Can , Mert Gurbuzbalaban , Lingjiong Zhu

We propose computationally tractable accelerated first-order methods for Riemannian optimization, extending the Nesterov accelerated gradient (NAG) method. For both geodesically convex and geodesically strongly convex objective functions,…

Optimization and Control · Mathematics 2025-08-12 Jungbin Kim , Insoon Yang

The use of momentum in stochastic gradient methods has become a widespread practice in machine learning. Different variants of momentum, including heavy-ball momentum, Nesterov's accelerated gradient (NAG), and quasi-hyperbolic momentum…

Machine Learning · Computer Science 2019-10-31 Igor Gitman , Hunter Lang , Pengchuan Zhang , Lin Xiao

We study the convergence of accelerated stochastic gradient descent for strongly convex objectives under the growth condition, which states that the variance of stochastic gradient is bounded by a multiplicative part that grows with the…

Optimization and Control · Mathematics 2023-11-01 You-Lin Chen , Sen Na , Mladen Kolar

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