Fast convex optimization via inertial systems with asymptotically vanishing viscosity and Hessian-driven damping

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Wang, Zepeng, Peypouquet, Juan
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916847375351808
author Wang, Zepeng
Peypouquet, Juan
author_facet Wang, Zepeng
Peypouquet, Juan
contents We study the convergence rate of a family of inertial algorithms, which can be obtained by discretization of an inertial system combining asymptotic vanishing viscous and Hessian-driven damping. We establish a fast sublinear convergence rate in case the objective function is convex and satisfies Polyak-Łojasiewicz inequality. We also establish a linear convergence rate for strongly convex functions. The results can provide more insights into the convergence property of Nesterov's accelerated gradient method.
format Preprint
id arxiv_https___arxiv_org_abs_2506_21730
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Fast convex optimization via inertial systems with asymptotically vanishing viscosity and Hessian-driven damping
Wang, Zepeng
Peypouquet, Juan
Optimization and Control
We study the convergence rate of a family of inertial algorithms, which can be obtained by discretization of an inertial system combining asymptotic vanishing viscous and Hessian-driven damping. We establish a fast sublinear convergence rate in case the objective function is convex and satisfies Polyak-Łojasiewicz inequality. We also establish a linear convergence rate for strongly convex functions. The results can provide more insights into the convergence property of Nesterov's accelerated gradient method.
title Fast convex optimization via inertial systems with asymptotically vanishing viscosity and Hessian-driven damping
topic Optimization and Control
url https://arxiv.org/abs/2506.21730