Saved in:
Bibliographic Details
Main Authors: Karakai, Aron, Eising, Jaap, Martinelli, Andrea, Dörfler, Florian
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2510.27645
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915930760544256
author Karakai, Aron
Eising, Jaap
Martinelli, Andrea
Dörfler, Florian
author_facet Karakai, Aron
Eising, Jaap
Martinelli, Andrea
Dörfler, Florian
contents We develop a system-theoretic framework for the structured analysis of distributed optimization algorithms with decomposable cost functions. We model such algorithms as a network of interacting dynamical systems and derive tests for convergence based on incremental dissipativity and contraction theory. This approach yields a step-by-step analysis pipeline suitable for any network structure, with conditions expressed as linear matrix inequalities. In addition, a numerical comparison with traditional analysis methods is presented, in the context of distributed gradient descent.
format Preprint
id arxiv_https___arxiv_org_abs_2510_27645
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Convergence Analysis of Distributed Optimization: A Dissipativity Framework
Karakai, Aron
Eising, Jaap
Martinelli, Andrea
Dörfler, Florian
Optimization and Control
We develop a system-theoretic framework for the structured analysis of distributed optimization algorithms with decomposable cost functions. We model such algorithms as a network of interacting dynamical systems and derive tests for convergence based on incremental dissipativity and contraction theory. This approach yields a step-by-step analysis pipeline suitable for any network structure, with conditions expressed as linear matrix inequalities. In addition, a numerical comparison with traditional analysis methods is presented, in the context of distributed gradient descent.
title Convergence Analysis of Distributed Optimization: A Dissipativity Framework
topic Optimization and Control
url https://arxiv.org/abs/2510.27645