ZONE: Zeroth-order nonconvex multiagent optimization over networks

Davood Hajinezhad; Mingyi Hong; Alfredo Garcia

doi:10.1109/TAC.2019.2896025

ZONE: Zeroth-order nonconvex multiagent optimization over networks

Davood Hajinezhad, Mingyi Hong, Alfredo Garcia

Electrical and Computer Engineering

Research output: Contribution to journal › Article › peer-review

41 Scopus citations

Abstract

In this paper, we consider distributed optimization problems over a multiagent network, where each agent can only partially evaluate the objective function, and it is allowed to exchange messages with its immediate neighbors. Differently from all existing works on distributed optimization, our focus is given to optimizing a class of nonconvex problems and under the challenging setting, where each agent can only access the zeroth-order information (i.e., the functional values) of its local functions. For different types of network topologies, such as undirected connected networks or star networks, we develop efficient distributed algorithms and rigorously analyze their convergence and rate of convergence (to the set of stationary solutions). Numerical results are provided to demonstrate the efficiency of the proposed algorithms.

Original language	English (US)
Article number	8629972
Pages (from-to)	3995-4010
Number of pages	16
Journal	IEEE Transactions on Automatic Control
Volume	64
Issue number	10
DOIs	https://doi.org/10.1109/TAC.2019.2896025
State	Published - Oct 2019

Bibliographical note

Funding Information:
Manuscript received September 19, 2017; revised March 1, 2018 and September 18, 2018; accepted November 23, 2018. Date of publication January 30, 2019; date of current version September 25, 2019. This work was supported in part by the National Science Foundation under Grant CMMI-1727757 and Grant CCF-1526078 and in part by the Air Force Office of Scientific Research under Grant 15RT0767. Recommended by Associate Editor U. V. Shanbhag. (Corresponding author: Mingyi Hong.) D. Hajinezhad is with the SAS Institute, Cary, NC 27513 USA (e-mail:, davood.hajinezhad@sas.com).

Publisher Copyright:
© 2019 IEEE.

Keywords

Distributed optimization
Nonconvex optimization
Primal-dual algorithms
Zeroth-order information

Publisher link

10.1109/TAC.2019.2896025

Find It

Find It at U of M Libraries

Cite this

@article{7ca23e6b2b7448f3b9ca4ad9b0ddf8ed,

title = "ZONE: Zeroth-order nonconvex multiagent optimization over networks",

abstract = "In this paper, we consider distributed optimization problems over a multiagent network, where each agent can only partially evaluate the objective function, and it is allowed to exchange messages with its immediate neighbors. Differently from all existing works on distributed optimization, our focus is given to optimizing a class of nonconvex problems and under the challenging setting, where each agent can only access the zeroth-order information (i.e., the functional values) of its local functions. For different types of network topologies, such as undirected connected networks or star networks, we develop efficient distributed algorithms and rigorously analyze their convergence and rate of convergence (to the set of stationary solutions). Numerical results are provided to demonstrate the efficiency of the proposed algorithms.",

keywords = "Distributed optimization, Nonconvex optimization, Primal-dual algorithms, Zeroth-order information",

author = "Davood Hajinezhad and Mingyi Hong and Alfredo Garcia",

note = "Funding Information: Manuscript received September 19, 2017; revised March 1, 2018 and September 18, 2018; accepted November 23, 2018. Date of publication January 30, 2019; date of current version September 25, 2019. This work was supported in part by the National Science Foundation under Grant CMMI-1727757 and Grant CCF-1526078 and in part by the Air Force Office of Scientific Research under Grant 15RT0767. Recommended by Associate Editor U. V. Shanbhag. (Corresponding author: Mingyi Hong.) D. Hajinezhad is with the SAS Institute, Cary, NC 27513 USA (e-mail:, davood.hajinezhad@sas.com). Publisher Copyright: {\textcopyright} 2019 IEEE.",

year = "2019",

month = oct,

doi = "10.1109/TAC.2019.2896025",

language = "English (US)",

volume = "64",

pages = "3995--4010",

journal = "IEEE Transactions on Automatic Control",

issn = "0018-9286",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

number = "10",

}

TY - JOUR

T1 - ZONE

T2 - Zeroth-order nonconvex multiagent optimization over networks

AU - Hajinezhad, Davood

AU - Hong, Mingyi

AU - Garcia, Alfredo

N1 - Funding Information: Manuscript received September 19, 2017; revised March 1, 2018 and September 18, 2018; accepted November 23, 2018. Date of publication January 30, 2019; date of current version September 25, 2019. This work was supported in part by the National Science Foundation under Grant CMMI-1727757 and Grant CCF-1526078 and in part by the Air Force Office of Scientific Research under Grant 15RT0767. Recommended by Associate Editor U. V. Shanbhag. (Corresponding author: Mingyi Hong.) D. Hajinezhad is with the SAS Institute, Cary, NC 27513 USA (e-mail:, davood.hajinezhad@sas.com). Publisher Copyright: © 2019 IEEE.

PY - 2019/10

Y1 - 2019/10

N2 - In this paper, we consider distributed optimization problems over a multiagent network, where each agent can only partially evaluate the objective function, and it is allowed to exchange messages with its immediate neighbors. Differently from all existing works on distributed optimization, our focus is given to optimizing a class of nonconvex problems and under the challenging setting, where each agent can only access the zeroth-order information (i.e., the functional values) of its local functions. For different types of network topologies, such as undirected connected networks or star networks, we develop efficient distributed algorithms and rigorously analyze their convergence and rate of convergence (to the set of stationary solutions). Numerical results are provided to demonstrate the efficiency of the proposed algorithms.

AB - In this paper, we consider distributed optimization problems over a multiagent network, where each agent can only partially evaluate the objective function, and it is allowed to exchange messages with its immediate neighbors. Differently from all existing works on distributed optimization, our focus is given to optimizing a class of nonconvex problems and under the challenging setting, where each agent can only access the zeroth-order information (i.e., the functional values) of its local functions. For different types of network topologies, such as undirected connected networks or star networks, we develop efficient distributed algorithms and rigorously analyze their convergence and rate of convergence (to the set of stationary solutions). Numerical results are provided to demonstrate the efficiency of the proposed algorithms.

KW - Distributed optimization

KW - Nonconvex optimization

KW - Primal-dual algorithms

KW - Zeroth-order information

UR - http://www.scopus.com/inward/record.url?scp=85075572639&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85075572639&partnerID=8YFLogxK

U2 - 10.1109/TAC.2019.2896025

DO - 10.1109/TAC.2019.2896025

M3 - Article

AN - SCOPUS:85075572639

SN - 0018-9286

VL - 64

SP - 3995

EP - 4010

JO - IEEE Transactions on Automatic Control

JF - IEEE Transactions on Automatic Control

IS - 10

M1 - 8629972

ER -

ZONE: Zeroth-order nonconvex multiagent optimization over networks

Abstract

Bibliographical note

Keywords

Publisher link

Find It

Other files and links

Fingerprint

Cite this