Solving nonconvex optimization problems via a second order dynamical system with unbounded damping

Fuente: arXiv
Saved in:
Bibliographic Details
Main Author: László, Szilárd Csaba
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909856677494784
author László, Szilárd Csaba
author_facet László, Szilárd Csaba
contents In this paper we study a second order dynamical system with variable coefficients in connection to the minimization problem of a smooth nonconvex function. The convergence of the trajectories generated by the dynamical system to a critical point of the objective function is assured, provided a regularization of the objective function satisfies the Kurdyka-Łojasiewicz property. We also provide convergence rates for the trajectories generated by the dynamical system, formulated in terms of the Łojasiewicz exponent, and we show that the unbounded damping considered in our dynamical system significantly improves the convergence rates known so far in the literature, that is, instead of linear rates we obtain superlinear rates.
format Preprint
id arxiv_https___arxiv_org_abs_2510_16864
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Solving nonconvex optimization problems via a second order dynamical system with unbounded damping
László, Szilárd Csaba
Optimization and Control
90C26, 90C30, 65K10
In this paper we study a second order dynamical system with variable coefficients in connection to the minimization problem of a smooth nonconvex function. The convergence of the trajectories generated by the dynamical system to a critical point of the objective function is assured, provided a regularization of the objective function satisfies the Kurdyka-Łojasiewicz property. We also provide convergence rates for the trajectories generated by the dynamical system, formulated in terms of the Łojasiewicz exponent, and we show that the unbounded damping considered in our dynamical system significantly improves the convergence rates known so far in the literature, that is, instead of linear rates we obtain superlinear rates.
title Solving nonconvex optimization problems via a second order dynamical system with unbounded damping
topic Optimization and Control
90C26, 90C30, 65K10
url https://arxiv.org/abs/2510.16864