Two-timescale projection neural networks in collaborative neurodynamic approaches to global optimization and distributed optimization

Banghua Huang; Yang Liu; Yun-Liang Jiang; Jun Wang

doi:10.1016/j.neunet.2023.10.011

Two-timescale projection neural networks in collaborative neurodynamic approaches to global optimization and distributed optimization

Banghua Huang, Yang Liu^*, Yun-Liang Jiang, Jun Wang^*

^*Corresponding author for this work

Research output: Journal Publications and Reviews › RGC 21 - Publication in refereed journal › peer-review

18 Citations (Scopus)

Abstract

In this paper, we propose a two-timescale projection neural network (PNN) for solving optimization problems with nonconvex functions. We prove the convergence of the PNN with sufficiently different timescales to a local optimal solution. We develop a collaborative neurodynamic approach with multiple such PNNs to search for global optimal solutions. In addition, we develop a collaborative neurodynamic approach with multiple PNNs connected via a directed graph for distributed global optimization. We elaborate on four numerical examples to illustrate the characteristics of the approaches. © 2023 Elsevier Ltd

Original language	English
Pages (from-to)	83-91
Journal	Neural Networks
Volume	169
Online published	16 Oct 2023
DOIs	https://doi.org/10.1016/j.neunet.2023.10.011
Publication status	Published - Jan 2024

Funding

This work was partially supported by the National Natural Science Foundation of China under grant 62173308 and U22A20102, the Natural Science Foundation of Zhejiang Province of China under grant LR20F030001, the Jinhua Science and Technology Project under grant 2022-1-042, and the Research Grants Council of the Hong Kong Special Administrative Region of China through the General Research Fund under Grant 11202019.

Research Keywords

Collaborative neurodynamic optimization
Distributed optimization
Global optimization
Nonconvex functions
Two-timescale systems

RGC Funding Information

RGC-funded

Access Output

10.1016/j.neunet.2023.10.011

Other Access Options

Check CityUHK Library

Permanent Link

Right click to copy link

Cite this

@article{64d0a9b4db3b487f9c328dda816bbf91,

title = "Two-timescale projection neural networks in collaborative neurodynamic approaches to global optimization and distributed optimization",

abstract = "In this paper, we propose a two-timescale projection neural network (PNN) for solving optimization problems with nonconvex functions. We prove the convergence of the PNN with sufficiently different timescales to a local optimal solution. We develop a collaborative neurodynamic approach with multiple such PNNs to search for global optimal solutions. In addition, we develop a collaborative neurodynamic approach with multiple PNNs connected via a directed graph for distributed global optimization. We elaborate on four numerical examples to illustrate the characteristics of the approaches. {\textcopyright} 2023 Elsevier Ltd",

keywords = "Collaborative neurodynamic optimization, Distributed optimization, Global optimization, Nonconvex functions, Two-timescale systems",

author = "Banghua Huang and Yang Liu and Yun-Liang Jiang and Jun Wang",

year = "2024",

month = jan,

doi = "10.1016/j.neunet.2023.10.011",

language = "English",

volume = "169",

pages = "83--91",

journal = "Neural Networks",

issn = "0893-6080",

publisher = "Elsevier Ltd.",

}

TY - JOUR

T1 - Two-timescale projection neural networks in collaborative neurodynamic approaches to global optimization and distributed optimization

AU - Huang, Banghua

AU - Liu, Yang

AU - Jiang, Yun-Liang

AU - Wang, Jun

PY - 2024/1

Y1 - 2024/1

N2 - In this paper, we propose a two-timescale projection neural network (PNN) for solving optimization problems with nonconvex functions. We prove the convergence of the PNN with sufficiently different timescales to a local optimal solution. We develop a collaborative neurodynamic approach with multiple such PNNs to search for global optimal solutions. In addition, we develop a collaborative neurodynamic approach with multiple PNNs connected via a directed graph for distributed global optimization. We elaborate on four numerical examples to illustrate the characteristics of the approaches. © 2023 Elsevier Ltd

AB - In this paper, we propose a two-timescale projection neural network (PNN) for solving optimization problems with nonconvex functions. We prove the convergence of the PNN with sufficiently different timescales to a local optimal solution. We develop a collaborative neurodynamic approach with multiple such PNNs to search for global optimal solutions. In addition, we develop a collaborative neurodynamic approach with multiple PNNs connected via a directed graph for distributed global optimization. We elaborate on four numerical examples to illustrate the characteristics of the approaches. © 2023 Elsevier Ltd

KW - Collaborative neurodynamic optimization

KW - Distributed optimization

KW - Global optimization

KW - Nonconvex functions

KW - Two-timescale systems

UR - http://www.scopus.com/inward/record.url?scp=85174352315&partnerID=8YFLogxK

UR - https://www.scopus.com/record/pubmetrics.uri?eid=2-s2.0-85174352315&origin=recordpage

U2 - 10.1016/j.neunet.2023.10.011

DO - 10.1016/j.neunet.2023.10.011

M3 - RGC 21 - Publication in refereed journal

SN - 0893-6080

VL - 169

SP - 83

EP - 91

JO - Neural Networks

JF - Neural Networks

ER -

Two-timescale projection neural networks in collaborative neurodynamic approaches to global optimization and distributed optimization

Abstract

Funding

Research Keywords

RGC Funding Information

Access Output

Other Access Options

Permanent Link

Other Files and Links

Fingerprint

GRF: Collaborative Neurodynamic Approaches to Portfolio Optimization

Cite this

Two-timescale projection neural networks in collaborative neurodynamic approaches to global optimization and distributed optimization

Abstract

Funding

Research Keywords

RGC Funding Information

Access Output

Other Access Options

Permanent Link

Other Files and Links

Fingerprint

Projects

GRF: Collaborative Neurodynamic Approaches to Portfolio Optimization

Cite this