A dual neural network for convex quadratic programming subject to linear equality and inequality constraints

Yunong Zhang, Jun Wang

Research output: Contribution to journalArticlepeer-review

151 Citations (Scopus)

Abstract

A recurrent neural network called the dual neural network is proposed in this Letter for solving the strictly convex quadratic programming problems. Compared to other recurrent neural networks, the proposed dual network with fewer neurons can solve quadratic programming problems subject to equality, inequality, and bound constraints. The dual neural network is shown to be globally exponentially convergent to optimal solutions of quadratic programming problems. In addition, compared to neural networks containing high-order nonlinear terms, the dynamic equation of the proposed dual neural network is piecewise linear, and the network architecture is thus much simpler. The global convergence behavior of the dual neural network is demonstrated by an illustrative numerical example.

Original languageEnglish
Pages (from-to)271-278
Number of pages8
JournalPhysics Letters, Section A: General, Atomic and Solid State Physics
Volume298
Issue number4
DOIs
Publication statusPublished - 10 Jun 2002
Externally publishedYes

Keywords

  • Dual neural network
  • Global convergence
  • Linear constraint
  • Projection operator
  • Quadratic programming

Fingerprint

Dive into the research topics of 'A dual neural network for convex quadratic programming subject to linear equality and inequality constraints'. Together they form a unique fingerprint.

Cite this