Solving nonconvex quadratic optimization problems by neural networks

In this paper, we propose a projection neural network model for solving a class of smooth nonconvex optimization problems where the feasible set is convex but the objective function is not convex. Compared with the existing neural network models for solving nonconvex quadratic problems, this neural network model canbe applied to solve problems that local optima need not be global optima. Simulation results are given to illustrate the global convergence and performance of the proposed model for nonconvex quadratic optimization problems with quadratic constraint

Keywords:

Smooth nonconvex optimization , recurrent neural networks , global optimality conditions , global convergence , Lagrange multipliers , S-lemma