Zeroth-Order Feedback Optimization in Multi-Agent Systems: Tackling Coupled Constraints

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Duan, Yingpeng, Tang, Yujie
Format: Preprint
Veröffentlicht: 2024
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866916442069270528
author Duan, Yingpeng
Tang, Yujie
author_facet Duan, Yingpeng
Tang, Yujie
contents This paper investigates distributed zeroth-order feedback optimization in multi-agent systems with coupled constraints, where each agent operates its local action vector and observes only zeroth-order information to minimize a global cost function subject to constraints in which the local actions are coupled. Specifically, we employ two-point zeroth-order gradient estimation with delayed information to construct stochastic gradients, and leverage the constraint extrapolation technique and the averaging consensus framework to effectively handle the coupled constraints. We also provide convergence rate and oracle complexity results for our algorithm, characterizing its computational efficiency and scalability by rigorous theoretical analysis. Numerical experiments are conducted to validate the algorithm's effectiveness.
format Preprint
id arxiv_https___arxiv_org_abs_2410_12647
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Zeroth-Order Feedback Optimization in Multi-Agent Systems: Tackling Coupled Constraints
Duan, Yingpeng
Tang, Yujie
Optimization and Control
Systems and Control
This paper investigates distributed zeroth-order feedback optimization in multi-agent systems with coupled constraints, where each agent operates its local action vector and observes only zeroth-order information to minimize a global cost function subject to constraints in which the local actions are coupled. Specifically, we employ two-point zeroth-order gradient estimation with delayed information to construct stochastic gradients, and leverage the constraint extrapolation technique and the averaging consensus framework to effectively handle the coupled constraints. We also provide convergence rate and oracle complexity results for our algorithm, characterizing its computational efficiency and scalability by rigorous theoretical analysis. Numerical experiments are conducted to validate the algorithm's effectiveness.
title Zeroth-Order Feedback Optimization in Multi-Agent Systems: Tackling Coupled Constraints
topic Optimization and Control
Systems and Control
url https://arxiv.org/abs/2410.12647