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

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 ar...

Full description

Saved in:
Bibliographic Details
Published inProceedings of the American Control Conference pp. 3658 - 3665
Main Authors Duan, Yingpeng, Tang, Yujie
Format Conference Proceeding
LanguageEnglish
Published AACC 08.07.2025
Subjects
Complexity theory
Computational efficiency
Convergence
Cost function
Estimation
Extrapolation
Multi-agent systems
Scalability
Vectors
Online AccessGet full text
ISSN2378-5861
DOI10.23919/ACC63710.2025.11107733

Cover

More Information
Summary: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.
ISSN:2378-5861
DOI:10.23919/ACC63710.2025.11107733