On the Convergence of Decentralized Stochastic Gradient-Tracking with Finite-Time Consensus

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Fainman, Aaron, Vlaski, Stefan
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912905107079168
author Fainman, Aaron
Vlaski, Stefan
author_facet Fainman, Aaron
Vlaski, Stefan
contents Algorithms for decentralized optimization and learning rely on local optimization steps coupled with combination steps over a graph. Recent works have demonstrated that using a time-varying sequence of matrices that achieves finite-time consensus can improve the communication and iteration complexity of decentralized optimization algorithms based on gradient tracking. In practice, a sequence of matrices satisfying the exact finite-time consensus property may not be available due to imperfect knowledge of the network topology, a limit on the length of the sequence, or numerical instabilities. In this work, we quantify the impact of approximate finite-time consensus sequences on the convergence of a gradient-tracking based decentralized optimization algorithm. Our results hold for any periodic sequence of combination matrices. We clarify the interplay between approximation error of the finite-time consensus sequence and the length of the sequence as well as typical problem parameters such as smoothness and gradient noise.
format Preprint
id arxiv_https___arxiv_org_abs_2505_23577
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle On the Convergence of Decentralized Stochastic Gradient-Tracking with Finite-Time Consensus
Fainman, Aaron
Vlaski, Stefan
Optimization and Control
Signal Processing
Algorithms for decentralized optimization and learning rely on local optimization steps coupled with combination steps over a graph. Recent works have demonstrated that using a time-varying sequence of matrices that achieves finite-time consensus can improve the communication and iteration complexity of decentralized optimization algorithms based on gradient tracking. In practice, a sequence of matrices satisfying the exact finite-time consensus property may not be available due to imperfect knowledge of the network topology, a limit on the length of the sequence, or numerical instabilities. In this work, we quantify the impact of approximate finite-time consensus sequences on the convergence of a gradient-tracking based decentralized optimization algorithm. Our results hold for any periodic sequence of combination matrices. We clarify the interplay between approximation error of the finite-time consensus sequence and the length of the sequence as well as typical problem parameters such as smoothness and gradient noise.
title On the Convergence of Decentralized Stochastic Gradient-Tracking with Finite-Time Consensus
topic Optimization and Control
Signal Processing
url https://arxiv.org/abs/2505.23577