A Concise Lyapunov Analysis of Nesterov's Accelerated Gradient Method

Jun Liu
2/24/2025
math.OCcs.LGeess.SY

No confident code implementation found for this paper.

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.

View on arXivView PDF

Code Implementations

No confident code match yet

We couldn't find an author-owned or strongly-evidenced community implementation for this paper. Any repos shown below are weak matches — verify before relying on them.

No code implementations found yet.

Know of an implementation? Let us know in the comments below!

Similar Papers

On Underdamped Nesterov's Acceleration

84% match2023

Linear convergence of forward-backward accelerated algorithms without knowledge of the modulus of strong convexity

83% match2023

Nesterov acceleration despite very noisy gradients

81% match2023

Accelerated Gradient Methods for Nonconvex Optimization: Escape Trajectories From Strict Saddle Points and Convergence to Local Minima

81% match2023

Provable Accelerated Convergence of Nesterov's Momentum for Deep ReLU Neural Networks

80% match2023

Generalized Continuous-Time Models for Nesterov's Accelerated Gradient Methods

80% match2024

Cite this paper

@article{liu2025concise,
  title  = {A Concise Lyapunov Analysis of Nesterov's Accelerated Gradient Method},
  author = {Jun Liu},
  year   = {2025},
  eprint = {2502.17373},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2502.17373v3}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2502.17373.svg)](https://codeofpaper.com/paper/2502.17373)

Discussion