Stochastic Fixed-Point Iterations for Nonexpansive Maps: Convergence and Error Bounds

From MaRDI portal
Publication:6180255

DOI10.1137/22M1515550arXiv2208.04193OpenAlexW4390977426MaRDI QIDQ6180255FDOQ6180255

Roberto Cominetti, Mario Bravo

Publication date: 19 January 2024

Published in: SIAM Journal on Control and Optimization (Search for Journal in Brave)

Abstract: We study a stochastically perturbed version of the well-known Krasnoselski--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 non-asymptotic 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.


Full work available at URL: https://arxiv.org/abs/2208.04193







Cites Work






This page was built for publication: Stochastic Fixed-Point Iterations for Nonexpansive Maps: Convergence and Error Bounds

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6180255)