Salvato in:
Dettagli Bibliografici
Autori principali: Aujol, Jean-François, Dossal, Charles, Labarrière, Hippolyte, Rondepierre, Aude
Natura: Preprint
Pubblicazione: 2024
Soggetti:
Accesso online:https://arxiv.org/abs/2407.17063
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866929435032158208
author Aujol, Jean-François
Dossal, Charles
Labarrière, Hippolyte
Rondepierre, Aude
author_facet Aujol, Jean-François
Dossal, Charles
Labarrière, Hippolyte
Rondepierre, Aude
contents Introduced by Beck and Teboulle, FISTA (for Fast Iterative Shrinkage-Thresholding Algorithm) is a first-order method widely used in convex optimization. Adapted from Nesterov's accelerated gradient method for convex functions, the generated sequence guarantees a decay of the function values of $\mathcal{O}\left(n^{-2}\right)$ in the convex setting. We show that for coercive functions satisfying some local growth condition (namely a H\''olderian or quadratic growth condition), this sequence strongly converges to a minimizer. This property, which has never been proved without assuming the uniqueness of the minimizer, is associated with improved convergence rates for the function values. The proposed analysis is based on a preliminary study of the Asymptotic Vanishing Damping system introduced by Su et al. in to modelNesterov's accelerated gradient method in a continuous setting. Novel improved convergence results are also shown for the solutions of this dynamical system, including the finite length of the trajectory under the aforementioned geometry conditions.
format Preprint
id arxiv_https___arxiv_org_abs_2407_17063
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Strong Convergence of FISTA Iterates under H{ö}lderian and Quadratic Growth Conditions
Aujol, Jean-François
Dossal, Charles
Labarrière, Hippolyte
Rondepierre, Aude
Optimization and Control
Introduced by Beck and Teboulle, FISTA (for Fast Iterative Shrinkage-Thresholding Algorithm) is a first-order method widely used in convex optimization. Adapted from Nesterov's accelerated gradient method for convex functions, the generated sequence guarantees a decay of the function values of $\mathcal{O}\left(n^{-2}\right)$ in the convex setting. We show that for coercive functions satisfying some local growth condition (namely a H\''olderian or quadratic growth condition), this sequence strongly converges to a minimizer. This property, which has never been proved without assuming the uniqueness of the minimizer, is associated with improved convergence rates for the function values. The proposed analysis is based on a preliminary study of the Asymptotic Vanishing Damping system introduced by Su et al. in to modelNesterov's accelerated gradient method in a continuous setting. Novel improved convergence results are also shown for the solutions of this dynamical system, including the finite length of the trajectory under the aforementioned geometry conditions.
title Strong Convergence of FISTA Iterates under H{ö}lderian and Quadratic Growth Conditions
topic Optimization and Control
url https://arxiv.org/abs/2407.17063