Recurrent neural networks for solving second-order cone programs

This paper proposes using the neural networks to efficiently solve the second-order cone programs (SOCP). To establish the neural networks, the SOCP is first reformulated as a second-order cone complementarity problem (SOCCP) with the Karush-Kuhn-Tucker conditions of the SOCP. The SOCCP functions, which transform the SOCCP into a set of nonlinear equations, are then utilized to design the neural networks. We propose two kinds of neural networks with the different SOCCP functions. The first neural network uses the Fischer-Burmeister function to achieve an unconstrained minimization with a merit function. We show that the merit function is a Lyapunov function and this neural network is asymptotically stable. The second neural network utilizes the natural residual function with the cone projection function to achieve low computation complexity. It is shown to be Lyapunov stable and converges globally to an optimal solution under some condition. The SOCP simulation results demonstrate the effectiveness of the proposed neural networks.

[1]  Richard M. Golden,et al.  Mathematical Methods for Neural Network Analysis and Design , 1996 .

[2]  Stephen P. Boyd,et al.  Fast Computation of Optimal Contact Forces , 2007, IEEE Transactions on Robotics.

[3]  Youshen Xia,et al.  A new neural network for solving linear and quadratic programming problems , 1996, IEEE Trans. Neural Networks.

[4]  Masao Fukushima,et al.  Smoothing Functions for Second-Order-Cone Complementarity Problems , 2002, SIAM J. Optim..

[5]  Dimitri P. Bertsekas,et al.  Nonlinear Programming , 1997 .

[6]  Donald Goldfarb,et al.  Second-order cone programming , 2003, Math. Program..

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

[8]  Marshall C. Y. Kuo.  Solution of Nonlinear Equations , 1968, IEEE Transactions on Computers.

[9]  Masao Fukushima,et al.  Equivalent differentiable optimization problems and descent methods for asymmetric variational inequality problems , 1992, Math. Program..

[10]  Lisa Turner,et al.  Applications of Second Order Cone Programming , 2012 .

[11]  R. D. Murphy,et al.  Iterative solution of nonlinear equations , 1994 .

[12]  Jun Wang,et al.  A recurrent neural network for solving nonlinear convex programs subject to linear constraints , 2005, IEEE Transactions on Neural Networks.

[13]  Danchi Jiang,et al.  A Lagrangian network for kinematic control of redundant robot manipulators , 1999, IEEE Trans. Neural Networks.

[14]  Paul Tseng,et al.  An unconstrained smooth minimization reformulation of the second-order cone complementarity problem , 2005, Math. Program..

[15]  Jun Wang,et al.  A projection neural network and its application to constrained optimization problems , 2002 .

[16]  Stephen P. Boyd,et al.  Control applications of nonlinear convex programming , 1998 .

[17]  Dimitris Bertsimas,et al.  Constrained Stochastic LQC: A Tractable Approach , 2007, IEEE Transactions on Automatic Control.

[18]  Sanyang Liu,et al.  A Neural Network Algorithm for Second-Order Conic Programming , 2005, ISNN.

[19]  Jun Wang,et al.  Grasping-force optimization for multifingered robotic hands using a recurrent neural network , 2004, IEEE Transactions on Robotics and Automation.

[20]  Jun Wang,et al.  A general projection neural network for solving monotone variational inequalities and related optimization problems , 2004, IEEE Transactions on Neural Networks.

[21]  Gao Xing-bao.  A neural network for nonlinear programming with linear constraints , 2001 .

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

[23]  Jein-Shan Chen,et al.  Neural networks for solving second-order cone constrained variational inequality problem , 2012, Comput. Optim. Appl..

[24]  Paul Tseng,et al.  Analysis of nonsmooth vector-valued functions associated with second-order cones , 2004, Math. Program..

[25]  Youshen Xia,et al.  A recurrent neural network for nonlinear convex optimization subject to nonlinear inequality constraints , 2004, IEEE Trans. Circuits Syst. I Regul. Pap..

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

[27]  Jinde Cao,et al.  A high performance neural network for solving nonlinear programming problems with hybrid constraints , 2001 .

[28]  Masao Fukushima,et al.  On the Local Convergence of Semismooth Newton Methods for Linear and Nonlinear Second-Order Cone Programs Without Strict Complementarity , 2009, SIAM J. Optim..

[29]  James M. Ortega,et al.  Iterative solution of nonlinear equations in several variables , 2014, Computer science and applied mathematics.