Exact convergence of gradient-free distributed optimization method in a multi-agent system

© 2018 IEEE. In this paper, a gradient-free algorithm is proposed for a set constrained distributed optimization problem in a multi-agent system under a directed communication network. For each agent, a pseudo-gradient is designed locally and utilized instead of the true gradient information to guid...

Full description

Saved in:

Bibliographic Details
Main Authors:	Pang, Yipeng, Hu, Guoqiang
Other Authors:	School of Electrical and Electronic Engineering
Format:	Conference or Workshop Item
Language:	English
Published:	2020
Subjects:	Engineering::Electrical and electronic engineering Distributed Optimization Multi-agent System
Online Access:	https://hdl.handle.net/10356/143537
Tags:	Add Tag No Tags, Be the first to tag this record!
Institution:	Nanyang Technological University
Language:	English

id	sg-ntu-dr.10356-143537
record_format	dspace
spelling	sg-ntu-dr.10356-1435372020-09-08T02:01:50Z Exact convergence of gradient-free distributed optimization method in a multi-agent system Pang, Yipeng Hu, Guoqiang School of Electrical and Electronic Engineering 2018 IEEE Conference on Decision and Control (CDC) Engineering::Electrical and electronic engineering Distributed Optimization Multi-agent System © 2018 IEEE. In this paper, a gradient-free algorithm is proposed for a set constrained distributed optimization problem in a multi-agent system under a directed communication network. For each agent, a pseudo-gradient is designed locally and utilized instead of the true gradient information to guide the decision variables update. Compared with most gradient-free optimization methods where a doubly-stochastic weighting matrix is usually employed, this algorithm uses a row-stochastic matrix plus a column-stochastic matrix, and is able to achieve exact asymptotic convergence to the optimal solution. National Research Foundation (NRF) Accepted version 2020-09-08T02:01:50Z 2020-09-08T02:01:50Z 2019 Conference Paper Pang, Y., & Hu, G. (2018). Exact convergence of gradient-free distributed optimization method in a multi-agent system. 2018 IEEE Conference on Decision and Control (CDC), 5728-5733. doi:10.1109/CDC.2018.8619028 9781538613955 https://hdl.handle.net/10356/143537 10.1109/CDC.2018.8619028 2-s2.0-85062187754 5728 5733 en © 2018 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other users, in any current or future media, including reprinting/republishing this material for adverstising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works. The published version is available at:https://doi.org/10.1109/CDC.2018.8619028 application/pdf
institution	Nanyang Technological University
building	NTU Library
country	Singapore
collection	DR-NTU
language	English
topic	Engineering::Electrical and electronic engineering Distributed Optimization Multi-agent System
spellingShingle	Engineering::Electrical and electronic engineering Distributed Optimization Multi-agent System Pang, Yipeng Hu, Guoqiang Exact convergence of gradient-free distributed optimization method in a multi-agent system
description	© 2018 IEEE. In this paper, a gradient-free algorithm is proposed for a set constrained distributed optimization problem in a multi-agent system under a directed communication network. For each agent, a pseudo-gradient is designed locally and utilized instead of the true gradient information to guide the decision variables update. Compared with most gradient-free optimization methods where a doubly-stochastic weighting matrix is usually employed, this algorithm uses a row-stochastic matrix plus a column-stochastic matrix, and is able to achieve exact asymptotic convergence to the optimal solution.
author2	School of Electrical and Electronic Engineering
author_facet	School of Electrical and Electronic Engineering Pang, Yipeng Hu, Guoqiang
format	Conference or Workshop Item
author	Pang, Yipeng Hu, Guoqiang
author_sort	Pang, Yipeng
title	Exact convergence of gradient-free distributed optimization method in a multi-agent system
title_short	Exact convergence of gradient-free distributed optimization method in a multi-agent system
title_full	Exact convergence of gradient-free distributed optimization method in a multi-agent system
title_fullStr	Exact convergence of gradient-free distributed optimization method in a multi-agent system
title_full_unstemmed	Exact convergence of gradient-free distributed optimization method in a multi-agent system
title_sort	exact convergence of gradient-free distributed optimization method in a multi-agent system
publishDate	2020
url	https://hdl.handle.net/10356/143537
_version_	1681057506965585920

Exact convergence of gradient-free distributed optimization method in a multi-agent system

Similar Items