Low complexity convergence rate bounds for push-sum algorithms with homogeneous correlation structure
Abstract
The objective of this work is to establish an upper bound for the almost sure convergence rate for a class of push-sum algorithms. The current work extends the methods and results of the authors on a similar low-complexity bound on push-sum algorithms with some particular synchronous message passing schemes and complements the general approach of Gerencs\'er and Gerencs\'er from 2022 providing an exact, but often less accessible description. Furthermore, a parametric analysis is presented on the ``weight'' of the messages, which is found to be convex with an explicit expression for the gradient. This allows the fine-tuning of the algorithm used for improved efficiency. Numerical results confirm the speedup in evaluating the computable bounds without deteriorating their performance, for a graph on 120 vertices the runtime drops by more than 4 orders of magnitude.
Cite
@article{arxiv.2507.16601,
title = {Low complexity convergence rate bounds for push-sum algorithms with homogeneous correlation structure},
author = {Balázs Gerencsér and Miklós Kornyik},
journal= {arXiv preprint arXiv:2507.16601},
year = {2025}
}
Comments
15 pages, 3 figures