Saved in:
Bibliographic Details
Main Authors: Xu, Zeyi, Chen, Long
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2601.19013
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910015155077120
author Xu, Zeyi
Chen, Long
author_facet Xu, Zeyi
Chen, Long
contents This work proposes A$^2$GD, a novel adaptive accelerated gradient descent method for convex and composite optimization. Smoothness and convexity constants are updated via Lyapunov analysis. Inspired by stability analysis in ODE solvers, the method triggers line search only when accumulated perturbations become positive, thereby reducing gradient evaluations while preserving strong convergence guarantees. By integrating adaptive step size and momentum acceleration, A$^2$GD outperforms existing first-order methods across a range of problem settings.
format Preprint
id arxiv_https___arxiv_org_abs_2601_19013
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Adaptive Accelerated Gradient Descent Methods for Convex Optimization
Xu, Zeyi
Chen, Long
Optimization and Control
This work proposes A$^2$GD, a novel adaptive accelerated gradient descent method for convex and composite optimization. Smoothness and convexity constants are updated via Lyapunov analysis. Inspired by stability analysis in ODE solvers, the method triggers line search only when accumulated perturbations become positive, thereby reducing gradient evaluations while preserving strong convergence guarantees. By integrating adaptive step size and momentum acceleration, A$^2$GD outperforms existing first-order methods across a range of problem settings.
title Adaptive Accelerated Gradient Descent Methods for Convex Optimization
topic Optimization and Control
url https://arxiv.org/abs/2601.19013