Abstract
In this paper, a feedback neural network model is proposed for solving a class of convex quadratic bi-level programming problems based on the idea of successive approximation. Differing from existing neural network models, the proposed neural network has the least number of state variables and simple structure. Based on Lyapunov theories, we prove that the equilibrium point sequence of the feedback neural network can approximately converge to an optimal solution of the convex quadratic bi-level problem under certain conditions, and the corresponding sequence of the function value approximately converges to the optimal value of the convex quadratic bi-level problem. Simulation experiments on three numerical examples and a portfolio selection problem are provided to show the efficiency and performance of the proposed neural network approach.
Similar content being viewed by others
References
Bard J (1998) Practical bi-level optimization: algorithm and applications. Kluwer, Dordrecht
Dempe S (2002) Foundation of bi-level programming. Kluwer, London
Lee ES, Shih HS (2001) Fuzzy and multi-level decision making: an interactive computational approach. Springer, London
Bialas WF, Karwan MH (1982) On two-level optimization. IEEE Trans Autom Control 27:211–214
Yang H, Bell MGH (1998) Models and algorithms for road network design: a review and some new developments. Transp Rev 18:257–278
Ben-Ayed O, Blair O (1990) Computational difficulity of bi-level linear programming. Oper Res 38:556–560
Tank DW, Hopfield JJ (1986) Simple neural optimization networks: an A/D convert, signal decision circuit, and a linear programming circuit. IEEE Trans Circuits Syst CAS 33:533–541
Chen K, Leung Y, Leung K, Gao X (2002) A neural network for solving nonlinear programming problems. Neural Comput Appl 11:103–111
Leung Y, Chen K, Jiao Y, Gao X, Leung K (2001) A new gradient-based neural network for solving linear and quadratic programming problems. IEEE Trans Neural Netw 12:1074–1083
Wen U, Lan K, Shih H (2009) A review of Hopfield neural networks for solving mathematical programming problems. Eur J Oper Res 198:675–687
Huang B, Zhang H, Gong D, Wang Z (2013) A new result for projection neural networks to solve linear variational inequalities and related optimization problems. Neural Comput Appl 23:357–362
Xia Y, Wang J (1998) A general methodology for designing globally convergent optimizatin neural networks. IEEE Trans Neural Netw 9:1331–1343
Huang T, Huang H, Li C (2008) Stability of periodic solution in fuzzy BAM neural networks with finite distributed delays. Neurocomputing 71:3064–3069
Li C, Li CD, Huang T, Liao X (2011) Impulsive effects on stability of high-order BAM neural networks with time delays. Neurocomputing 74:1541–1550
Wen S, Zeng Z, Huang T (2013) Dynamic behaviors of memristor-based delayed recurrent networks. Neural Comput Appl 23:815–821
He X, Li C, Shu Y (2013) Fold-flip bifurcation analysis on a class of discrete-time neural network. Neural Comput Appl 22:375–381
Morrison DD (1968) Optimization by least squares. SIAM J Numer Anal 5:83–88
Leung Y, Chen K, Gao X (2003) A high-performance feedback neural network for solving convex nonlinear programming problems. IEEE Trans Neural Netw 14:1469–1477
Yang Y, Chao J (2008) A feedback neural network for solving convex constraint optimization problems. Appl Math Comput 201:340–350
Sheng Z, Lv Z, Xu R (1996) A new algorithm based on the frank-wolfe method and neural network for a class of bi-level decision making problems. Acta Automatica Sinica 22:657–665
Shih H, Wen U, Lee ES, Hsiao H (2004) A neural network approach to multiobjective and multilevel programming problems. Comput Math Appl 48:95–108
Lan K, Wen U, Lee ES (2007) A hybrid neural network approach to bi-level programming problems. Appl Math Lett 20:880–884
Lv Y, Hu T, Wang G, Wan Z (2008) A neural network approach for solving nonlinear bi-level programming problem. Comput Math Appl 58:2823–2829
Lv Y, Chen Z, Wan Z (2010) A neural network for solving a convex quadratic bi-level programming problem. J Comput Appl Math 234:505–511
Etoa Etoa JB (2011) Solving quadratic convex bi-level programming problems using a smoothing method. Appl Math Comput 217:6680–6690
An L, Quynh Y, Tao P (2012) A DC programming approach for a class of bi-level programming problems and its application in Portfolio Selection. Numer Algebra Control Optim 2:167–185
Facchinei F, Jiang H, Qi L (1999) A smoothing method for mathematical programming with equilibrium constraints. Math Program 85:107–134
LaSalle J (1976) The stability of dynamical systems. Springer, New York
Ben-Ayed O (1988) Bi-level linear programming: analysis and application to the network design problem, PhD thesis, University of Illinois at Urbana-Champaign, IL
Muu L, Quy N (2003) A global optimization method for solving convex quadratic bi-level programming problems. J Glob Optim 26:199–219
Acknowledgments
The authors are thankful to their editor and anonymous referees for their valuable comments and suggestions that have improved the quality of the paper significantly.
Author information
Authors and Affiliations
Corresponding author
Additional information
This research was partially supported by KJ120616, cstc2013jjB00001 and SRF for ROCS, SEM.
Rights and permissions
About this article
Cite this article
Li, J., Li, C., Wu, Z. et al. A feedback neural network for solving convex quadratic bi-level programming problems. Neural Comput & Applic 25, 603–611 (2014). https://doi.org/10.1007/s00521-013-1530-8
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00521-013-1530-8