Neural networks for solving second-order cone programs based on complementarity functions

Research output: Contribution to journalArticle

Abstract

This paper surveys two neural networks for solving nonlinear convex programs with the second-order cone constraints. The neural network models are designed based on two different C-functions associated with a second-order cone. Various stabilities along with the neural networks are presented. Numerical comparisons are also reported.

Original languageEnglish
Pages (from-to)1621-1641
Number of pages21
JournalJournal of Nonlinear and Convex Analysis
Volume19
Issue number10
Publication statusPublished - 2018 Jan 1

Fingerprint

Second-order Cone
Complementarity
Cones
Neural Networks
Cone Constraints
Neural networks
Convex Program
Numerical Comparisons
Neural Network Model

Keywords

  • Generalized FB function
  • Neural network
  • Second-order cone
  • Stability

ASJC Scopus subject areas

  • Analysis
  • Geometry and Topology
  • Control and Optimization
  • Applied Mathematics

Cite this

Neural networks for solving second-order cone programs based on complementarity functions. / Chen, Jein Shan.

In: Journal of Nonlinear and Convex Analysis, Vol. 19, No. 10, 01.01.2018, p. 1621-1641.

Research output: Contribution to journalArticle

@article{81b8133afb6341b7a3f843d8e133ae16,
title = "Neural networks for solving second-order cone programs based on complementarity functions",
abstract = "This paper surveys two neural networks for solving nonlinear convex programs with the second-order cone constraints. The neural network models are designed based on two different C-functions associated with a second-order cone. Various stabilities along with the neural networks are presented. Numerical comparisons are also reported.",
keywords = "Generalized FB function, Neural network, Second-order cone, Stability",
author = "Chen, {Jein Shan}",
year = "2018",
month = "1",
day = "1",
language = "English",
volume = "19",
pages = "1621--1641",
journal = "Journal of Nonlinear and Convex Analysis",
issn = "1345-4773",
publisher = "Yokohama Publishers",
number = "10",

}

TY - JOUR

T1 - Neural networks for solving second-order cone programs based on complementarity functions

AU - Chen, Jein Shan

PY - 2018/1/1

Y1 - 2018/1/1

N2 - This paper surveys two neural networks for solving nonlinear convex programs with the second-order cone constraints. The neural network models are designed based on two different C-functions associated with a second-order cone. Various stabilities along with the neural networks are presented. Numerical comparisons are also reported.

AB - This paper surveys two neural networks for solving nonlinear convex programs with the second-order cone constraints. The neural network models are designed based on two different C-functions associated with a second-order cone. Various stabilities along with the neural networks are presented. Numerical comparisons are also reported.

KW - Generalized FB function

KW - Neural network

KW - Second-order cone

KW - Stability

UR - http://www.scopus.com/inward/record.url?scp=85059041152&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85059041152&partnerID=8YFLogxK

M3 - Article

VL - 19

SP - 1621

EP - 1641

JO - Journal of Nonlinear and Convex Analysis

JF - Journal of Nonlinear and Convex Analysis

SN - 1345-4773

IS - 10

ER -