A neural network with finite-time convergence for a class of variational inequalities

Authors:
Xing-Bao Gao;Li-Li Du
Affiliations:
College of Mathematics and Information Science, Shaanxi Normal University, Xi’an, Shaanxi, P.R. China;College of Mathematics and Information Science, Shaanxi Normal University, Xi’an, Shaanxi, P.R. China
Venue:
ICIC'06 Proceedings of the 2006 international conference on Intelligent Computing - Volume Part I
Year:
2006

Citing 8
Cited 2

Linear-quadratic programming and optimal control

SIAM Journal on Control and Optimization
Finite-dimensional variational inequality and nonlinear complementarity problems: a survey of theory, algorithms and applications

Mathematical Programming: Series A and B
Co-Coercivity and Its Role In the Convergence of Iterative Schemes For Solving Variational Inequalities

SIAM Journal on Optimization
A recurrent neural network with exponential convergence for solving convex quadratic program and related linear piecewise equations

Neural Networks
A general methodology for designing globally convergent optimization neural networks

IEEE Transactions on Neural Networks
Exponential stability of globally projected dynamic systems

IEEE Transactions on Neural Networks
A novel neural network for nonlinear convex programming

IEEE Transactions on Neural Networks
A novel neural network for variational inequalities with linear and nonlinear constraints

IEEE Transactions on Neural Networks

An alternative recurrent neural network for solving variational inequalities and related optimization problems

IEEE Transactions on Systems, Man, and Cybernetics, Part B: Cybernetics
A new one-layer neural network for linear and quadratic programming

IEEE Transactions on Neural Networks

Quantified Score

Hi-index	0.00

Visualization

Abstract

In this paper, a new neural network for a class of variational inequalities with linear and nonlinear constraints is proposed by converting it into an extended variational inequality. The proposed neural network with the asymmetric mapping is proved to be stable in the sense of Lyapunov and converge to a solution of the original problem within a finite time under a weaker co-coercivity condition by using a convex energy function. Meanwhile, the finite-time convergence for the proposed network with the gradient mapping is also shown under some mild conditions. Compared with the existing neural networks, the new model is suitable to parallel implementation with lower complexity, and can be applied to solve some nonmonotone problems. The validity and transient behavior of the proposed neural network are demonstrated by numerical examples.