A recurrent neural network for real-time semidefinite programming

Semidefinite programming problem is an important optimization problem that has been extensively investigated. A real-time solution method for solving such a problem, however, is still not yet available. This paper proposes a novel recurrent neural network for this purpose. First, an auxiliary cost function is introduced to minimize the duality gap between the admissible points of the primal problem and the corresponding dual problem. Then a dynamical system is constructed to drive the duality gap to zero exponentially along any trajectory by modifying the gradient of the auxiliary cost function. Furthermore, a subsystem is developed to circumvent in the computation of matrix inverse, so that the resulting overall dynamical system can be realized using a recurrent neural network. The architecture of the resulting neural network is discussed. The operating characteristics and performance of the proposed approach are demonstrated by means of simulation results.

[1]  U. Helmke,et al.  Optimization and Dynamical Systems , 1994, Proceedings of the IEEE.

[2]  Jun Wang.  Recurrent neural networks for solving linear matrix equations , 1993 .

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

[4]  Yurii Nesterov,et al.  Interior-point polynomial algorithms in convex programming , 1994, Siam studies in applied mathematics.

[5]  M. Kothare,et al.  Robust constrained model predictive control using linear matrix inequalities , 1994, Proceedings of 1994 American Control Conference - ACC '94.

[6]  Farid Alizadeh,et al.  Interior Point Methods in Semidefinite Programming with Applications to Combinatorial Optimization , 1995, SIAM J. Optim..

[7]  E. Yaz.  Linear Matrix Inequalities In System And Control Theory , 1998, Proceedings of the IEEE.

[8]  Ching-Chi Hsu,et al.  Terminal attractor learning algorithms for back propagation neural networks , 1991, [Proceedings] 1991 IEEE International Joint Conference on Neural Networks.

[9]  Stephen P. Boyd,et al.  A primal—dual potential reduction method for problems involving matrix inequalities , 1995, Math. Program..

[10]  Marco Gori,et al.  Unimodal loading problems , 1997 .

[11]  Leonid Faybusovich,et al.  Semidefinite Programming: A Path-Following Algorithm for a Linear-Quadratic Functional , 1996, SIAM J. Optim..

[12]  Michael A. Shanblatt,et al.  Linear and quadratic programming neural network analysis , 1992, IEEE Trans. Neural Networks.

[13]  Robert J. Vanderbei,et al.  An Interior-Point Method for Semidefinite Programming , 1996, SIAM J. Optim..

[14]  M. S. Bazaraa,et al.  Nonlinear Programming , 1979 .

[15]  Hector A. Rosales-Macedo.  Nonlinear Programming: Theory and Algorithms (2nd Edition) , 1993 .

[16]  John J. Hopfield,et al.  Simple 'neural' optimization networks: An A/D converter, signal decision circuit, and a linear programming circuit , 1986 .

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

[18]  Dennis S. Bernstein,et al.  Benchmark Problems for Robust Control Design , 1991, 1991 American Control Conference.

[19]  Stephen P. Boyd,et al.  Linear Matrix Inequalities in Systems and Control Theory , 1994 .

[20]  Jun Wang,et al.  A deterministic annealing neural network for convex programming , 1994, Neural Networks.