Salvato in:
Dettagli Bibliografici
Autori principali: van Treek, Kira, Peña, Javier F., Vera, Juan C., Zuluaga, Luis F.
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:https://arxiv.org/abs/2510.27540
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866909880531550208
author van Treek, Kira
Peña, Javier F.
Vera, Juan C.
Zuluaga, Luis F.
author_facet van Treek, Kira
Peña, Javier F.
Vera, Juan C.
Zuluaga, Luis F.
contents Many optimization algorithms$\unicode{x2013}$including gradient descent, proximal methods, and operator splitting techniques$\unicode{x2013}$can be formulated as fixed-point iterations (FPI) of continuous operators. When these operators are averaged, convergence to a fixed point is guaranteed when one exists, but the convergence is generally sublinear. Recent results establish linear convergence of FPI for averaged operators under certain conditions. However, such conditions do not apply to common classes of operators, such as those arising in piecewise linear and quadratic optimization problems. In this work, we prove that a local error-bound condition is both necessary and sufficient for the linear convergence of FPI applied to averaged operators. We provide explicit bounds on the convergence rate and show how these relate to the constants in the error-bound condition. Our main result demonstrates that piecewise linear operators satisfy local error bounds, ensuring linear convergence of the associated optimization algorithms. This leads to a general and practical framework for analyzing convergence behavior in algorithms such as ADMM and Douglas-Rachford in the absence of strong convexity. In particular, we obtain convergence rates that are independent of problem data for linear optimization, and depend only on the condition number of the objective for quadratic optimization.
format Preprint
id arxiv_https___arxiv_org_abs_2510_27540
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Linear Convergence and Error Bounds for Optimization Without Strong Convexity
van Treek, Kira
Peña, Javier F.
Vera, Juan C.
Zuluaga, Luis F.
Optimization and Control
90C25, 90C20, 90C05
Many optimization algorithms$\unicode{x2013}$including gradient descent, proximal methods, and operator splitting techniques$\unicode{x2013}$can be formulated as fixed-point iterations (FPI) of continuous operators. When these operators are averaged, convergence to a fixed point is guaranteed when one exists, but the convergence is generally sublinear. Recent results establish linear convergence of FPI for averaged operators under certain conditions. However, such conditions do not apply to common classes of operators, such as those arising in piecewise linear and quadratic optimization problems. In this work, we prove that a local error-bound condition is both necessary and sufficient for the linear convergence of FPI applied to averaged operators. We provide explicit bounds on the convergence rate and show how these relate to the constants in the error-bound condition. Our main result demonstrates that piecewise linear operators satisfy local error bounds, ensuring linear convergence of the associated optimization algorithms. This leads to a general and practical framework for analyzing convergence behavior in algorithms such as ADMM and Douglas-Rachford in the absence of strong convexity. In particular, we obtain convergence rates that are independent of problem data for linear optimization, and depend only on the condition number of the objective for quadratic optimization.
title Linear Convergence and Error Bounds for Optimization Without Strong Convexity
topic Optimization and Control
90C25, 90C20, 90C05
url https://arxiv.org/abs/2510.27540