A Concise Lyapunov Analysis of Nesterov's Accelerated Gradient Method
Optimization and Control
2025-07-08 v3 Machine Learning
Systems and Control
Systems and Control
Abstract
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.
Keywords
Cite
@article{arxiv.2502.17373,
title = {A Concise Lyapunov Analysis of Nesterov's Accelerated Gradient Method},
author = {Jun Liu},
journal= {arXiv preprint arXiv:2502.17373},
year = {2025}
}
Comments
This update adds a few references to related work