A Concise Lyapunov Analysis of Nesterov's Accelerated Gradient Method

Fuente: arXiv
Saved in:
Bibliographic Details
Main Author: Liu, Jun
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866913929092923392
author Liu, Jun
author_facet Liu, Jun
contents Convergence analysis of Nesterov's accelerated gradient method has attracted significant attention over the past decades. While extensive work has explored its theoretical properties and elucidated the intuition behind its acceleration, a simple and direct proof of its convergence rates is still lacking. We provide a concise Lyapunov analysis of the convergence rates of Nesterov's accelerated gradient method for both general convex and strongly convex functions.
format Preprint
id arxiv_https___arxiv_org_abs_2502_17373
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle A Concise Lyapunov Analysis of Nesterov's Accelerated Gradient Method
Liu, Jun
Optimization and Control
Machine Learning
Systems and Control
Convergence analysis of Nesterov's accelerated gradient method has attracted significant attention over the past decades. While extensive work has explored its theoretical properties and elucidated the intuition behind its acceleration, a simple and direct proof of its convergence rates is still lacking. We provide a concise Lyapunov analysis of the convergence rates of Nesterov's accelerated gradient method for both general convex and strongly convex functions.
title A Concise Lyapunov Analysis of Nesterov's Accelerated Gradient Method
topic Optimization and Control
Machine Learning
Systems and Control
url https://arxiv.org/abs/2502.17373