Several Performance Bounds on Decentralized Online Optimization are Highly Conservative and Potentially Misleading

Fuente: arXiv
Enregistré dans:
Détails bibliographiques
Auteurs principaux: Meunier, Erwan, Hendrickx, Julien M.
Format: Preprint
Publié: 2025
Sujets:
Accès en ligne:
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866914027512266752
author Meunier, Erwan
Hendrickx, Julien M.
author_facet Meunier, Erwan
Hendrickx, Julien M.
contents We analyze Decentralized Online Optimization algorithms using the Performance Estimation Problem approach which allows, to automatically compute exact worst-case performance of optimization algorithms. Our analysis shows that several available performance guarantees are very conservative, sometimes by multiple orders of magnitude, and can lead to misguided choices of algorithm. Moreover, at least in terms of worst-case performance, some algorithms appear not to benefit from inter-agent communications for a significant period of time. We show how to improve classical methods by tuning their step-sizes, and find that we can save up to 20% on their actual worst-case performance regret.
format Preprint
id arxiv_https___arxiv_org_abs_2509_06466
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Several Performance Bounds on Decentralized Online Optimization are Highly Conservative and Potentially Misleading
Meunier, Erwan
Hendrickx, Julien M.
Optimization and Control
Artificial Intelligence
Distributed, Parallel, and Cluster Computing
Multiagent Systems
We analyze Decentralized Online Optimization algorithms using the Performance Estimation Problem approach which allows, to automatically compute exact worst-case performance of optimization algorithms. Our analysis shows that several available performance guarantees are very conservative, sometimes by multiple orders of magnitude, and can lead to misguided choices of algorithm. Moreover, at least in terms of worst-case performance, some algorithms appear not to benefit from inter-agent communications for a significant period of time. We show how to improve classical methods by tuning their step-sizes, and find that we can save up to 20% on their actual worst-case performance regret.
title Several Performance Bounds on Decentralized Online Optimization are Highly Conservative and Potentially Misleading
topic Optimization and Control
Artificial Intelligence
Distributed, Parallel, and Cluster Computing
Multiagent Systems
url https://arxiv.org/abs/2509.06466