A neural network for the linear complementarity problem

Authors:
Liao Li-Zhi;Qi Hou-Duo
Affiliations:
Department of Mathematics Hong Kong Baptist University Kowloon Tong, Hong Kong;Institute of Computational Mathematics and Scientific/Engineering Computing Chinese Academy of Sciences, P.O. Box 2719, Beijing, P.R. China
Venue:
Mathematical and Computer Modelling: An International Journal
Year:
1999

Citing 12
Cited 3

On the resolution of monotone complementarity problems

Computational Optimization and Applications
Modified Projection-Type Methods for Monotone Variational Inequalities

SIAM Journal on Control and Optimization
Some Noninterior Continuation Methods for LinearComplementarity Problems

SIAM Journal on Matrix Analysis and Applications
A semismooth equation approach to the solution of nonlinear complementarity problems

Mathematical Programming: Series A and B
Engineering and Economic Applications of Complementarity Problems

SIAM Review
Semismooth Karush-Kuhn-Tucker equations and convergence analysis of Newton and quasi-Newton methods for solving these equations

Mathematics of Operations Research
Neural Networks for Optimization and Signal Processing

Neural Networks for Optimization and Signal Processing
A New Merit Function For Nonlinear Complementarity Problems And A Related Algorithm

SIAM Journal on Optimization
A high-performance neural network for solving linear and quadratic programming problems

IEEE Transactions on Neural Networks
A new neural network for solving linear and quadratic programming problems

IEEE Transactions on Neural Networks
Linear and quadratic programming neural network analysis

IEEE Transactions on Neural Networks
Solving linear programming problems with neural networks: a comparative study

IEEE Transactions on Neural Networks

Stability Analysis of Gradient-Based Neural Networks for Optimization Problems

Journal of Global Optimization
Neurodynamical Optimization

Journal of Global Optimization
Recurrent neural networks for solving second-order cone programs

Neurocomputing

Quantified Score

Hi-index	0.98

Visualization

Abstract

An artificial neural network is proposed in this paper for solving the linear complementarity problem. The new neural network is based on a reformulation of the linear complementarity problem into the unconstrained minimization problem. Our new neural network can be easily implemented on a circuit. On the theoretical aspect, we analyze the existence of the equilibrium points for our neural network. In addition, we prove that if the equilibrium point exists for the neural network, then any such equilibrium point is both asymptotically and bounded (Lagrange) stable for any initial state. Furthermore, linear programming and certain quadratical programming problems (not necessarily convex) can be also solved by the neural network. Simulation results on several problems including a nonconvex one are also reported.