Local Conditions for Global Convergence of Gradient Flows and Proximal Point Sequences in Metric Spaces

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Schiavo, Lorenzo Dello, Maas, Jan, Pedrotti, Francesco
Format: Preprint
Published: 2023
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866913334682451968
author Schiavo, Lorenzo Dello
Maas, Jan
Pedrotti, Francesco
author_facet Schiavo, Lorenzo Dello
Maas, Jan
Pedrotti, Francesco
contents This paper deals with local criteria for the convergence to a global minimiser for gradient flow trajectories and their discretisations. To obtain quantitative estimates on the speed of convergence, we consider variations on the classical Kurdyka--Łojasiewicz inequality for a large class of parameter functions. Our assumptions are given in terms of the initial data, without any reference to an equilibrium point. The main results are convergence statements for gradient flow curves and proximal point sequences to a global minimiser, together with sharp quantitative estimates on the speed of convergence. These convergence results apply in the general setting of lower semicontinuous functionals on complete metric spaces, generalising recent results for smooth functionals on $\mathbb{R}^n$. While the non-smooth setting covers very general spaces, it is also useful for (non)-smooth functionals on $\mathbb{R}^n$.
format Preprint
id arxiv_https___arxiv_org_abs_2304_05239
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle Local Conditions for Global Convergence of Gradient Flows and Proximal Point Sequences in Metric Spaces
Schiavo, Lorenzo Dello
Maas, Jan
Pedrotti, Francesco
Optimization and Control
45J05, 49Q20 (Primary) 39B62, 37N40, 49J52, 65K10 (Secondary)
This paper deals with local criteria for the convergence to a global minimiser for gradient flow trajectories and their discretisations. To obtain quantitative estimates on the speed of convergence, we consider variations on the classical Kurdyka--Łojasiewicz inequality for a large class of parameter functions. Our assumptions are given in terms of the initial data, without any reference to an equilibrium point. The main results are convergence statements for gradient flow curves and proximal point sequences to a global minimiser, together with sharp quantitative estimates on the speed of convergence. These convergence results apply in the general setting of lower semicontinuous functionals on complete metric spaces, generalising recent results for smooth functionals on $\mathbb{R}^n$. While the non-smooth setting covers very general spaces, it is also useful for (non)-smooth functionals on $\mathbb{R}^n$.
title Local Conditions for Global Convergence of Gradient Flows and Proximal Point Sequences in Metric Spaces
topic Optimization and Control
45J05, 49Q20 (Primary) 39B62, 37N40, 49J52, 65K10 (Secondary)
url https://arxiv.org/abs/2304.05239