English
Related papers

Related papers: Optimal convergence rates for Nesterov acceleratio…

200 papers

An adaptive regularization algorithm for unconstrained nonconvex optimization is presented in which the objective function is never evaluated, but only derivatives are used. This algorithm belongs to the class of adaptive regularization…

Optimization and Control · Mathematics 2022-05-05 S. Gratton , S. Jerad , Ph. L. Toint

We present a new accelerated stochastic second-order method that is robust to both gradient and Hessian inexactness, which occurs typically in machine learning. We establish theoretical lower bounds and prove that our algorithm achieves…

Optimization and Control · Mathematics 2024-05-28 Artem Agafonov , Dmitry Kamzolov , Alexander Gasnikov , Ali Kavis , Kimon Antonakopoulos , Volkan Cevher , Martin Takáč

In machine learning research, the proximal gradient methods are popular for solving various optimization problems with non-smooth regularization. Inexact proximal gradient methods are extremely important when exactly solving the proximal…

Machine Learning · Computer Science 2018-09-11 Bin Gu , De Wang , Zhouyuan Huo , Heng Huang

Motivated, in particular, by the entropy-regularized optimal transport problem, we consider convex optimization problems with linear equality constraints, where the dual objective has Lipschitz $p$-th order derivatives, and develop two…

Optimization and Control · Mathematics 2023-08-11 Pavel Dvurechensky , Petr Ostroukhov , Alexander Gasnikov , César A. Uribe , Anastasiya Ivanova

Stochastic approximation is a foundation for many algorithms found in machine learning and optimization. It is in general slow to converge: the mean square error vanishes as $O(n^{-1})$. A deterministic counterpart known as quasi-stochastic…

Optimization and Control · Mathematics 2024-03-26 Caio Kalil Lauand , Sean Meyn

We consider gradient descent with `momentum', a widely used method for loss function minimization in machine learning. This method is often used with `Nesterov acceleration', meaning that the gradient is evaluated not at the current…

Machine Learning · Computer Science 2020-01-20 Goran Nakerst , John Brennan , Masudul Haque

Recent work has established that the trajectory of the Nesterov ODE, a the continuous-time model of Nesterov's accelerated gradient method, exhibits point convergence towards a minimizer of a convex potential. A natural next question is…

Optimization and Control · Mathematics 2026-04-09 Ernest K. Ryu

Gradient descent is slow to converge for ill-conditioned problems and non-convex problems. An important technique for acceleration is step-size adaptation. The first part of this paper contains a detailed review of step-size adaptation…

Machine Learning · Computer Science 2022-05-27 Hengshuai Yao

In this short note, we provide a simple version of an accelerated forward-backward method (a.k.a. Nesterov's accelerated proximal gradient method) possibly relying on approximate proximal operators and allowing to exploit strong convexity…

Optimization and Control · Mathematics 2022-01-24 Mathieu Barré , Adrien Taylor , Francis Bach

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

The subgradient method is one of the most fundamental algorithmic schemes for nonsmooth optimization. The existing complexity and convergence results for this method are mainly derived for Lipschitz continuous objective functions. In this…

Optimization and Control · Mathematics 2024-11-01 Xiao Li , Lei Zhao , Daoli Zhu , Anthony Man-Cho So

Incorporating second order curvature information in gradient based methods have shown to improve convergence drastically despite its computational intensity. In this paper, we propose a stochastic (online) quasi-Newton method with…

Machine Learning · Computer Science 2020-10-16 S. Indrapriyadarsini , Shahrzad Mahboubi , Hiroshi Ninomiya , Hideki Asai

We revisit the Ravine method of Gelfand and Tsetlin from a dynamical system perspective, study its convergence properties, and highlight its similarities and differences with the Nesterov accelerated gradient method. The two methods are…

Optimization and Control · Mathematics 2022-02-02 H. Attouch , J. Fadili

We study the convergence rate of a family of inertial algorithms, which can be obtained by discretization of an inertial system combining asymptotic vanishing viscous and Hessian-driven damping. We establish a fast sublinear convergence…

Optimization and Control · Mathematics 2025-07-18 Zepeng Wang , Juan Peypouquet

For first-order smooth optimization, the research on the acceleration phenomenon has a long-time history. Until recently, the mechanism leading to acceleration was not successfully uncovered by the gradient correction term and its…

Optimization and Control · Mathematics 2022-11-04 Bowen Li , Bin Shi , Ya-xiang Yuan

Motivated by the fact that the gradient-based optimization algorithms can be studied from the perspective of limiting ordinary differential equations (ODEs), here we derive an ODE representation of the accelerated triple momentum (TM)…

Optimization and Control · Mathematics 2020-08-26 Boya Sun , Jemin George , Solmaz Kia

We give a novel proof of the $O(1/k)$ and $O(1/k^2)$ convergence rates of the proximal gradient and accelerated proximal gradient methods for composite convex minimization. The crux of the new proof is an upper bound constructed via the…

Optimization and Control · Mathematics 2018-01-10 David H. Gutman , Javier F. Pena

We consider optimizing a function smooth convex function $f$ that is the average of a set of differentiable functions $f_i$, under the assumption considered by Solodov [1998] and Tseng [1998] that the norm of each gradient $f_i'$ is bounded…

Optimization and Control · Mathematics 2013-08-30 Mark Schmidt , Nicolas Le Roux

Asynchronous algorithms have attracted much attention recently due to the crucial demands on solving large-scale optimization problems. However, the accelerated versions of asynchronous algorithms are rarely studied. In this paper, we…

Optimization and Control · Mathematics 2018-02-28 Cong Fang , Yameng Huang , Zhouchen Lin

This paper presents a sufficient condition for stochastic gradients not to slow down the convergence of Nesterov's accelerated gradient method. The new condition has the strong-growth condition by Schmidt \& Roux as a special case, and it…

Optimization and Control · Mathematics 2022-07-26 Víctor Valls , Shiqiang Wang , Yuang Jiang , Leandros Tassiulas