Stochastic Fixed-Point Iterations for Nonexpansive Maps: Convergence and Error Bounds
SIAM Journal on Control and Optimization · 29.02.2024 · 62 (1) · 191-219
DOI: 10.1137/22m1515550 ↗Kurz gefasst
Fachartikel in der Zeitschrift SIAM Journal on Control and Optimization, online erschienen am 18.01.2024. Verfasst von Mario Bravo und 1 weiteren Autor:innen. Die Arbeit wurde bisher 11-mal zitiert (Crossref) und nennt 29 Literaturangaben. Gefördert von: Fondo Nacional de Desarrollo Científico, Tecnológico y de Innovación Tecnológica.
Abstract (Originalsprache)
We study a stochastically perturbed version of the well-known Krasnoselskii–Mann iteration for computing fixed points of nonexpansive maps in finite dimensional normed spaces. We discuss sufficient conditions on the stochastic noise and stepsizes that guarantee almost sure convergence of the iterates towards a fixed point and derive nonasymptotic error bounds and convergence rates for the fixed-point residuals. Our main results concern the case of a martingale difference noise with variances that can possibly grow unbounded. This supports an application to reinforcement learning for average reward Markov decision processes, for which we establish convergence and asymptotic rates. We also analyze in depth the case where the noise has uniformly bounded variance, obtaining error bounds with explicit computable constants.
Förderung
- Fondo Nacional de Desarrollo Científico, Tecnológico y de Innovación Tecnológica
Zitieren
APA
Bravo, M., & Cominetti, R. (2024). Stochastic Fixed-Point Iterations for Nonexpansive Maps: Convergence and Error Bounds. SIAM Journal on Control and Optimization, 62(1), 191-219. https://doi.org/10.1137/22m1515550
Vancouver
Bravo M, Cominetti R. Stochastic Fixed-Point Iterations for Nonexpansive Maps: Convergence and Error Bounds. SIAM Journal on Control and Optimization. 2024;62(1):191-219. doi:10.1137/22m1515550
BibTeX
@article{Bravo2024,
author = {Bravo, Mario and Cominetti, Roberto},
title = {Stochastic Fixed-Point Iterations for Nonexpansive Maps: Convergence and Error Bounds},
journal = {SIAM Journal on Control and Optimization},
year = {2024},
volume = {62},
number = {1},
pages = {191--219},
doi = {10.1137/22m1515550}
}
EUVIMED