An RNN-Based Algorithm for Decentralized-Partial-Consensus Constrained Optimization

被引：21

作者：

Xia, Zicong ^{[1
]}

Liu, Yang ^{[1
]}

Qiu, Jianlong ^{[2
]}

Ruan, Qihua ^{[3
]}

Cao, Jinde ^{[4
,5
]}

机构：

[1] Zhejiang Normal Univ, Coll Math & Comp Sci, Jinhua 321004, Zhejiang, Peoples R China

[2] Linyi Univ, Key Lab Complex Syst & Intelligent Comp Univ Shan, Sch Automat & Elect Engn, Linyi 276005, Shandong, Peoples R China

[3] Putian Univ, Sch Math & Finance, Putian 351100, Peoples R China

[4] Southeast Univ, Sch Math, Nanjing 210096, Peoples R China

[5] Yonsei Univ, Yonsei Frontier Lab, Seoul 03722, South Korea

来源：

IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS | 2023年 / 34卷 / 01期

基金：

中国国家自然科学基金;

关键词：

Optimization; Recurrent neural networks; Cost function; Task analysis; Optimization methods; Neurodynamics; Learning systems; Decentralized-partial-consensus optimization (DPCO); nonsmooth analysis; partial-consensus matrix; recurrent neural networks (RNNs); PROJECTION NEURAL-NETWORK; DISTRIBUTED OPTIMIZATION; MULTIAGENT SYSTEMS; RESOURCE-ALLOCATION; VARIATIONAL-INEQUALITIES; NONSMOOTH OPTIMIZATION; SUBJECT; DESIGN;

D O I：

10.1109/TNNLS.2021.3098668

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

This technical note proposes a decentralized-partial-consensus optimization (DPCO) problem with inequality constraints. The partial-consensus matrix originating from the Laplacian matrix is constructed to tackle the partial-consensus constraints. A continuous-time algorithm based on multiple interconnected recurrent neural networks (RNNs) is derived to solve the optimization problem. In addition, based on nonsmooth analysis and Lyapunov theory, the convergence of continuous-time algorithm is further proved. Finally, several examples demonstrate the effectiveness of main results.

引用

页码：534 / 542

页数：9

共 40 条

[1]

Boyd S., 2004, Convex Optimization, DOI 10.1017/CBO9780511804441

[2]

Clarke F.H., 1990, Optimization and nonsmooth analysis

[3] Distributed Continuous-Time Algorithms for Resource Allocation Problems Over Weight-Balanced Digraphs [J].

Deng, Zhenhua ;

Liang, Shu ;

Hong, Yiguang .

IEEE TRANSACTIONS ON CYBERNETICS, 2018, 48 (11) :3116-3125

[4] Distributed optimal resource allocation of second-order multiagent systems [J].

Deng, Zhenhua ;

Liang, Shu ;

Yu, Weiyong .

INTERNATIONAL JOURNAL OF ROBUST AND NONLINEAR CONTROL, 2018, 28 (14) :4246-4260

[5] Efficient Online Learning Algorithms Based on LSTM Neural Networks [J].

Ergen, Tolga ;

Kozat, Suleyman Serdar .

IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS, 2018, 29 (08) :3772-3783

[6] A Collective Neurodynamic Optimization Approach to Nonnegative Matrix Factorization [J].

Fan, Jianchao ;

Wang, Jun .

IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS, 2017, 28 (10) :2344-2356

[7] Saving Human Lives: What Complexity Science and Information Systems can Contribute [J].

Helbing, Dirk ;

Brockmann, Dirk ;

Chadefaux, Thomas ;

Donnay, Karsten ;

Blanke, Ulf ;

Woolley-Meza, Olivia ;

Moussaid, Mehdi ;

Johansson, Anders ;

Krause, Jens ;

Schutte, Sebastian ;

Perc, Matjaz .

JOURNAL OF STATISTICAL PHYSICS, 2015, 158 (03) :735-781

[8] Learning With Interpretable Structure From Gated RNN [J].

Hou, Bo-Jian ;

Zhou, Zhi-Hua .

IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS, 2020, 31 (07) :2267-2279

[9] Distributed Optimization for Robot Networks: From Real-Time Convex Optimization to Game-Theoretic Self-Organization [J].

Jaleel, Hassan ;

Shamma, Jeff S. .

PROCEEDINGS OF THE IEEE, 2020, 108 (11) :1953-1967

[10] Continuous-Time Algorithm for Approximate Distributed Optimization With Affine Equality and Convex Inequality Constraints [J].

Jiang, Xinrui ;

Qin, Sitian ;

Xue, Xiaoping .

IEEE TRANSACTIONS ON SYSTEMS MAN CYBERNETICS-SYSTEMS, 2021, 51 (09) :5809-5818

← 1 2 3 4 →