Abstract
This paper describes a method to estimate the Lipschitz gain of an operator through identification with neural networks. It is shown that through simple manipulation of the network coefficients, the Lipschitz constant could be estimated. Illustrations and applications are also given to show the effectiveness and usefulness of this estimation scheme.
Similar content being viewed by others
References
C.A. Desoer and M. Vidyasagar, “Feedback Systems: Input-Output Properties”, Academic Press, 1975.
M. Vidyasagar, “Nonlinear Systems Analysis”, 2nd edition, Prentice Hall, 1993.
Rui J.P. Figueiredo and Guanrong Chen, “Nonlinear Feedback Control Systems: An Operator Theory Approach”, Academic Press, 1993.
Simon Haykin, “Neural Networks: A Comprehensive Foundation”, Macmillan, 1994.
V.V. Phansalkar and P.S. Sastry, “Analysis of the Back-Propagation Algorithm with Momentum,” IEEE Transactions on Neural Networks, Vol. 5, No. 3 pp. 505–506, 1994.
Philip D. Wasserman, “Advanced methods in Neural Computing”, VNR Computer Library, 1993.
Anthony John Robinson, “Dynamic Error Propagation Networks”, PhD Thesis - Cambridge University Engineering Department, 1989.
G. Zames, “On the Input-Output Stability of Time-Varying Nonlinear Feedback Systems Part I: Conditions Derived Using Concepts of Loop Gain, Gonicity, and Positivity,” IEEE Transactions on Automatic Control, Vol. AC-11, No. 2, pp. 228–238, 1966.
G. Zames, “On the Input-Output Stability of Time-Varying Nonlinear Feedback Systems Part II: Conditions Involving Circles in the Frequency Plane and Sector Nonlinearities,” IEEE Transactions on Automatic Control, Vol. AC-11, No. 3, pp. 465–476, 1966.
Author information
Authors and Affiliations
Rights and permissions
About this article
Cite this article
Sio, K., Lee, C. Estimation of the Lipschitz Norm with Neural Networks. Neural Processing Letters 6, 99–108 (1997). https://doi.org/10.1023/A:1009667824060
Issue Date:
DOI: https://doi.org/10.1023/A:1009667824060