Stability and Convergence of Distributed Stochastic Approximations with large Unbounded Stochastic Information Delays

We generalize the Borkar-Meyn stability Theorem (BMT) to distributed stochastic approximations (SAs) with information delays that possess an arbitrary moment bound. To model the delays, we introduce Age of Information Processes (AoIPs): stochastic processes on the non-negative integers with a unit g...

Full description

Saved in:
Bibliographic Details
Published inarXiv.org
Main Authors Redder, Adrian, Ramaswamy, Arunselvan, Karl, Holger
Format Paper
LanguageEnglish
Published Ithaca Cornell University Library, arXiv.org 11.05.2023
Subjects
Approximation
Errors
Optimization
Stability analysis
Stochastic processes
Online AccessGet full text

Cover

More Information
Summary:We generalize the Borkar-Meyn stability Theorem (BMT) to distributed stochastic approximations (SAs) with information delays that possess an arbitrary moment bound. To model the delays, we introduce Age of Information Processes (AoIPs): stochastic processes on the non-negative integers with a unit growth property. We show that AoIPs with an arbitrary moment bound cannot exceed any fraction of time infinitely often. In combination with a suitably chosen stepsize, this property turns out to be sufficient for the stability of distributed SAs. Compared to the BMT, our analysis requires crucial modifications and a new line of argument to handle the SA errors caused by AoI. In our analysis, we show that these SA errors satisfy a recursive inequality. To evaluate this recursion, we propose a new Gronwall-type inequality for time-varying lower limits of summations. As applications to our distributed BMT, we discuss distributed gradient-based optimization and a new approach to analyzing SAs with momentum.
ISSN:2331-8422