Abstract
The Fast Quasi-Newton algorithm described in this paper has been seen to avoid the performance degradation caused in basic adaptive algorithms by colored input signals. The FQN algorithm offers convergence performance far superior to LMS, and is comparable to RLS in tracking ability. At the same time, FQN requires only O(N) computation, and should prove to be robust in finite-precision implementation. The latter expectation results from the fact that the FQN algorithm has no internal variables that are recursively computed for more than N time steps. Thus round-off errors are not allowed to accumulate. The FQN algorithm should prove to be useful in a variety of adaptive system applications.
Preview
Unable to display preview. Download preview PDF.
References
A. Papoulis, Probability, Random Variables, and Stochastic Processes, second edition. New York: McGraw-Hill, 1984.
R. D. Gitlin and F. Magee, "Self-Orthogonalizing Adaptive Equalization Algorithms," IEEE Trans. Comm., vol COM-25, no. 7, pp. 666–672, July 1977.
A. Giordano and F. Hsu, Least Square Estimation with Applications to Digital Signal Processing. New York: Wiley, 1985.
D. Manolakis, N. Kalouptsidis, and G. Carayannis, "Fast Algorithms for Discrete-Time Wiener Filters with Optimum Lag," IEEE Trans. Acoust., Speech, Sig. Proc., vol. ASSP-31, no. 1, pp. 168–179, Feb. 1983.
G. Goodwin and K. Sin, Adaptive Filtering, Prediction, and Control. Englewood Cliffs, NJ: Prentice-Hall, 1984.
J.M. Cioffi, "Limited-Precision Effects in Adaptive Filtering," IEEE Trans. Circuits and Systems, vol. CAS-34, no. 7, pp. 821–833, July 1987.
S.H. Ardalan and S.T. Alexander, "Fixed-Point Roundoff Error Analysis of the Exponentially Windowed RLS Algorithm for Time-Varying Systems," IEEE Trans. Acoust., Speech, Signal Proc., vol. ASSP-35, no. 6, pp. 770–783, June 1987.
Author information
Authors and Affiliations
Editor information
Rights and permissions
Copyright information
© 1989 Springer-Verlag
About this paper
Cite this paper
Marshall, D.F., Jenkins, W.K. (1989). Analysis of a Fast Quasi-Newton adaptive filtering algorithm. In: Porter, W.A., Kak, S.C. (eds) Advances in Communications and Signal Processing. Lecture Notes in Control and Information Sciences, vol 129. Springer, Berlin, Heidelberg. https://doi.org/10.1007/BFb0042737
Download citation
DOI: https://doi.org/10.1007/BFb0042737
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-51424-4
Online ISBN: 978-3-540-46259-0
eBook Packages: Springer Book Archive