Solving nonlinear complementarity problems with neural networks: a reformulation method approach

In this paper, we present a neural network approach for solving nonlinear complementarity problems. The neural network model is derived from an unconstrained minimization reformulation of the complementarity problem. The existence and the convergence of the trajectory of the neural network are addressed in detail. In addition, we also explore the stability properties, such as the stability in the sense of Lyapunov, the asymptotic stability and the exponential stability, for the neural network model. The theory developed here is also valid for neural network models derived from a number of reformulation methods for nonlinear complementarity problems. Simulation results are also reported.

[1]  A. Fischer.  An NCP–Function and its Use for the Solution of Complementarity Problems , 1995 .

[2]  Abdesselam Bouzerdoum,et al.  Neural network for quadratic optimization with bound constraints , 1993, IEEE Trans. Neural Networks.

[3]  F. Clarke.  Optimization And Nonsmooth Analysis , 1983 .

[4]  Stefen Hui,et al.  On solving constrained optimization problems with neural networks: a penalty method approach , 1993, IEEE Trans. Neural Networks.

[5]  Liqun Qi,et al.  A nonsmooth version of Newton's method , 1993, Math. Program..

[6]  Francisco Facchinei,et al.  A nonsmooth inexact Newton method for the solution of large-scale nonlinear complementarity problems , 1997, Math. Program..

[7]  Liqun Qi,et al.  Convergence Analysis of Some Algorithms for Solving Nonsmooth Equations , 1993, Math. Oper. Res..

[8]  Ka Kit Cheung.  Neural networks for optimization , 2001 .

[9]  Michael C. Ferris,et al.  Engineering and Economic Applications of Complementarity Problems , 1997, SIAM Rev..

[10]  G. Lin.  Nonlinear Programming without Computation , 2022 .

[11]  A. Fischer.  A special newton-type optimization method , 1992 .

[12]  Jerzy Zabczyk,et al.  Mathematical control theory - an introduction , 1992, Systems & Control: Foundations & Applications.

[13]  Francisco Facchinei,et al.  A New Merit Function For Nonlinear Complementarity Problems And A Related Algorithm , 1997, SIAM J. Optim..

[14]  Christian Kanzow,et al.  On the resolution of monotone complementarity problems , 1996, Comput. Optim. Appl..

[15]  Stefen Hui,et al.  Solving linear programming problems with neural networks: a comparative study , 1995, IEEE Trans. Neural Networks.

[16]  L. Watson.  Solving the Nonlinear Complementarity Problem by a Homotopy Method , 1979 .

[17]  Francisco Facchinei,et al.  A semismooth equation approach to the solution of nonlinear complementarity problems , 1996, Math. Program..

[18]  M. Kojima,et al.  EXTENSION OF NEWTON AND QUASI-NEWTON METHODS TO SYSTEMS OF PC^1 EQUATIONS , 1986 .

[19]  Andrzej Cichocki,et al.  Neural networks for optimization and signal processing , 1993 .

[20]  Masao Fukushima,et al.  Modified Newton methods for solving a semismooth reformulation of monotone complementarity problems , 1996, Math. Program..

[21]  Edgar Sanchez-Sinencio,et al.  Nonlinear switched capacitor 'neural' networks for optimization problems , 1990 .

[22]  Francisco Facchinei,et al.  On the Accurate Identification of Active Constraints , 1998, SIAM J. Optim..

[23]  Richard W. Cottle,et al.  Linear Complementarity Problem. , 1992 .

[24]  L. Qi.  Regular Pseudo-Smooth NCP and BVIP Functions and Globally and Quadratically Convergent Generalized Newton Methods for Complementarity and Variational Inequality Problems , 1999 .

[25]  Andrzej Cichocki,et al.  A new neural network for solving linear programming problems , 1996 .

[26]  Jong-Shi Pang,et al.  Nonsmooth Equations: Motivation and Algorithms , 1993, SIAM J. Optim..

[27]  Houyuan Jiang,et al.  A New Nonsmooth Equations Approach to Nonlinear Complementarity Problems , 1997 .

[28]  C. Kanzow,et al.  A Penalized Fischer-Burmeister Ncp-Function: Theoretical Investigation And Numerical Results , 1997 .

[29]  S. Fang,et al.  Solving convex programming problems with equality constraints by neural networks , 1998 .

[30]  Houyuan Jiang,et al.  Semismooth Karush-Kuhn-Tucker Equations and Convergence Analysis of Newton and Quasi-Newton Methods for Solving these Equations , 1997, Math. Oper. Res..

[31]  Liao Li-Zhi,et al.  A neural network for the linear complementarity problem , 1999 .

[32]  Defeng Sun,et al.  On NCP-Functions , 1999, Comput. Optim. Appl..

[33]  Leon O. Chua,et al.  Neural networks for nonlinear programming , 1988 .

[34]  Xiaojun Chen,et al.  Global and superlinear convergence of the smoothing Newton method and its application to general box constrained variational inequalities , 1998, Math. Comput..