English
Related papers

Related papers: A Differential Equation for Modeling Nesterov's Ac…

200 papers

We develop a theory of accelerated first-order optimization from the viewpoint of differential equations and Lyapunov functions. Building upon the previous work of many researchers, we consider differential equations which model the…

Optimization and Control · Mathematics 2021-04-02 Jonathan W. Siegel

Following the seminal work of Nesterov, accelerated optimization methods have been used to powerfully boost the performance of first-order, gradient-based parameter estimation in scenarios where second-order optimization strategies are…

Numerical Analysis · Computer Science 2017-11-28 Anthony Yezzi , Ganesh Sundaramoorthi

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

First order optimization algorithms play a major role in large scale machine learning. A new class of methods, called adaptive algorithms, were recently introduced to adjust iteratively the learning rate for each coordinate. Despite great…

Machine Learning · Computer Science 2019-10-01 André Belotto da Silva , Maxime Gazeau

Many important machine learning applications involve regularized nonconvex bi-level optimization. However, the existing gradient-based bi-level optimization algorithms cannot handle nonconvex or nonsmooth regularizers, and they suffer from…

Machine Learning · Computer Science 2022-06-06 Ziyi Chen , Bhavya Kailkhura , Yi Zhou

This paper studies the Nesterov-Spokoiny Acceleration (NSA), a variant of the accelerated gradient method by Nesterov and Spokoiny. For smooth convex optimization, NSA achieves a strict $o(1/k^2)$ convergence rate in function value and an…

Optimization and Control · Mathematics 2025-11-13 Weibin Peng , Yu Liu , Tianyu Wang

We analyze the convergence rate of a family of inertial algorithms, which can be obtained by discretization of an inertial system with Hessian-driven damping. We recover a convergence rate, up to a factor of 2 speedup upon Nesterov's…

Optimization and Control · Mathematics 2025-02-25 Zepeng Wang , Juan Peypouquet

We present two classes of differentially private optimization algorithms derived from the well-known accelerated first-order methods. The first algorithm is inspired by Polyak's heavy ball method and employs a smoothing approach to decrease…

Machine Learning · Computer Science 2022-05-17 Nurdan Kuru , Ş. İlker Birbil , Mert Gurbuzbalaban , Sinan Yildirim

Nesterov's accelerated gradient method (NAG) is widely used in problems with machine learning background including deep learning, and is corresponding to a continuous-time differential equation. From this connection, the property of the…

Optimization and Control · Mathematics 2022-04-05 Yasong Feng , Weiguo Gao

A key appeal of the recently proposed Neural Ordinary Differential Equation (ODE) framework is that it seems to provide a continuous-time extension of discrete residual neural networks. As we show herein, though, trained Neural ODE models…

Machine Learning · Computer Science 2023-09-12 Katharina Ott , Prateek Katiyar , Philipp Hennig , Michael Tiemann

Mirror descent plays a crucial role in constrained optimization and acceleration schemes, along with its corresponding low-resolution ordinary differential equations (ODEs) framework have been proposed. However, the low-resolution ODEs are…

Optimization and Control · Mathematics 2023-08-11 Ya-xiang Yuan , Yi Zhang

In this paper, we propose a unified view of gradient-based algorithms for stochastic convex composite optimization by extending the concept of estimate sequence introduced by Nesterov. This point of view covers the stochastic gradient…

Machine Learning · Statistics 2019-05-08 Andrei Kulunchakov , Julien Mairal

Accelerated gradient descent iterations are widely used in optimization. It is known that, in the continuous-time limit, these iterations converge to a second-order differential equation which we refer to as the accelerated gradient flow.…

Optimization and Control · Mathematics 2020-06-16 Mohammad Farazmand

Alternating minimization (AM) procedures are practically efficient in many applications for solving convex and non-convex optimization problems. On the other hand, Nesterov's accelerated gradient is theoretically optimal first-order method…

Optimization and Control · Mathematics 2021-09-16 Sergey Guminov , Pavel Dvurechensky , Nazarii Tupitsa , Alexander Gasnikov

We develop an accelerated gradient descent algorithm on the Grassmann manifold to compute the subspace spanned by a number of leading eigenvectors of a symmetric positive semi-definite matrix. This has a constant cost per iteration and a…

Optimization and Control · Mathematics 2024-06-27 Foivos Alimisis , Simon Vary , Bart Vandereycken

We present a simple transformation of any linear program or semidefinite program into an equivalent convex optimization problem whose only constraints are linear equations. The objective function is defined on the whole space, making…

Optimization and Control · Mathematics 2014-10-07 James Renegar

In the history of first-order algorithms, Nesterov's accelerated gradient descent (NAG) is one of the milestones. However, the cause of the acceleration has been a mystery for a long time. It has not been revealed with the existence of…

Optimization and Control · Mathematics 2022-09-20 Shuo Chen , Bin Shi , Ya-xiang Yuan

We provide a novel accelerated first-order method that achieves the asymptotically optimal convergence rate for smooth functions in the first-order oracle model. To this day, Nesterov's Accelerated Gradient Descent (AGD) and variations…

Optimization and Control · Mathematics 2018-02-13 Jelena Diakonikolas , Lorenzo Orecchia

In this paper, we try to uncover the second-order essence of several first-order optimization methods. For Nesterov Accelerated Gradient, we rigorously prove that the algorithm makes use of the difference between past and current gradients,…

Machine Learning · Computer Science 2019-12-23 Yuzheng Hu , Licong Lin , Shange Tang

Recently, the high-resolution ordinary differential equation (ODE) framework, which retains higher-order terms, has been proposed to analyze gradient-based optimization algorithms. Through this framework, the term $\nabla^2…

Optimization and Control · Mathematics 2026-02-05 Xudong Li , Lei Shi , Mingqi Song