Abstract
This paper proposes a neural network for saddle point problems (SPP) by an approximation approach. It first proves both the existence and the convergence property of approximate solutions, and then shows that the proposed network is globally exponentially stable and the solution of (SPP) is approximated. Simulation results are given to demonstrate further the effectiveness of the proposed network.
Supported by the National Key Basic Research Project (973 Project)(2002cb312205), the Grant of the NSF of China(10471114), and the Grant of the NSF of Fujian Province, China (A04100021).
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Bertsekas, D.P.: Nonlinear Programming, 2nd edn. Athena Scientific (1999)
Ye, Z., Zhang, B., Cao, C.: Convergence Analysis on Minimax Neural Networks (in Chinese). Information and Control 26, 1–6 (1997)
Gao, X.-B., Liao, L.-Z., Xue, W.: A Neural Network for a Class of Convex Quadratic Minimax Problems with Constraints. IEEE Trans. on Neural Networks 15, 622–628 (2004)
Tao, Q., Fang, T.: The Neural Network Model for Solving Minimax Problems with Constraints (in Chinese). Control Theory Applicat 17, 82–84 (2000)
Gao, X.-B.: Exponential Stability of Globally Projected Dynamic Systems. IEEE Trans. on Neural Networks 14, 426–431 (2003)
Ortega, J.M., Rheinboldt, W.C.: Interative Solution of Nonlinear Equations in Several Variables. Academic, New York (1970)
Browder, F.E.: Nonlinear Monotone Operators and Convex Sets in Banach spaces. Bull. Amer. Math. Soc. 71, 780–785 (1965)
Ekeland, I., Teman, R.: Convex Analysis and Variational Problems. North-Holland, Amsterdam (1976)
Cichocki, A., Unbehauen, R.: Neural Networks for Optimization and Signal Processing. Wiley, New York (1993)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2005 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Shen, X., Song, S., Cheng, L. (2005). A Neural Network for Constrained Saddle Point Problems: An Approximation Approach. In: Wang, L., Chen, K., Ong, Y.S. (eds) Advances in Natural Computation. ICNC 2005. Lecture Notes in Computer Science, vol 3610. Springer, Berlin, Heidelberg. https://doi.org/10.1007/11539087_60
Download citation
DOI: https://doi.org/10.1007/11539087_60
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-28323-2
Online ISBN: 978-3-540-31853-8
eBook Packages: Computer ScienceComputer Science (R0)