Abstract
Many ICA algorithms use prewhitening (second order decorrelation) as a preprocessing tool. This preprocessing can be shown to be valid when all hidden sources have fintie second moments, which is not required for the identifiability issue[9]. One would conjecture that if one or more sources do not have finite second moments then prewhitening would cause a breakdown. But we discover that this conjecture is not right. We provide some theories for this phenomenon as well as some simulation studies.
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
Amari, S.: Independent component analysis and method of estimating functions. IEICE Trans. Fundamentals E85-A(3), 540–547 (2002)
Bach, F., Jordan, M.: Kernel independent component analysis. Journal of Machine Learning Research 3, 1–48 (2002)
Bickel, P., Klaassen, C., Ritov, Y., Wellner, J.: Efficient and Adaptive Estimation for Semiparametric Models. Springer, New York (1993)
Cardoso, J.F.: On the performance of orthogonal source separation algorithms. In: Proc. EUSIPCO, Edinburgh, pp. 776–779 (1994)
Cardoso, J.F.: Blind signal separation: statistical principles. Proceedings of the IEEE 86(10), 2009–2025 (1998)
Cardoso, J.F.: High-order contrasts for independent component analysis. Neural Computation 11(1), 157–192 (1999)
Chen, A., Bickel, P.J.: Efficient independent component analysis - based on e.c.f. and one-step MLE. Technical report #634, Department of Statistics, University of California, Berkeley (2003)
Chen, A., Bickel, P.J.: Supplement to Consistent Independent Component Analysis and Prewhitening. Technical report #656, Department of Statistics, University of California, Berkeley (2004)
Comon, P.: Independent component analysis, a new concept? Signal Processing 36(3), 287–314 (1994)
Edelman, A., Arias, T., Smith, S.: The geometry of algorithms with orghogonality constriants. SIAM journal on Matrix Analysis and Applications 20(2), 303–353 (1999)
Eriksson, J., Koivanen, V.: Characteristic-function based independent component analysis. Signal Processing 83, 2195–2208 (2003)
Golub, G.: Matrix computation. Johns Hopkins University Press, Baltimore (1996)
Hyvarinen, A.: Fast and robust fixed-point algorithms for independent component analysis. IEEE Trans. on Neural Networks 10(3), 626–634 (1999)
Hyvarinen, A., Karhunen, J., Oja, E.: Independent Component Analysis. John Wiley & Sons, New York (2001)
Hyvarinen, A., Oja, E.: A fast fixed point algorithm for independent component analysis. Neural Computation 9(7), 1483–1492 (1997)
Kagan, A., Linnik, Y., Rao, C.: Characterization Problems in Mathematical Statistics. John Wiley & Sons, USA (1973)
Makeig, S., Westerfield, M., Jung, T.-P., Enghoff, S., Townsend, J., Courchesne, E., Sejnowski, T.J.: Dynamic brain sources of visual evoked responses. Science 295, 690–694 (2002)
Pham, D.T.: Contrast functions for ICA and sources separation. Technical report, BLISS project, France (2001)
Shereshevsk, Y., Yeredor, A., Messer, H.: Super-efficiency in blind signal separation of symmetric heavy-tailed sources. In: Proceedings of The 2001 IEEE Workshop on Statistical Signal Processing (SSP 2001), Singapore, August, pp. 78–81 (2001)
Widom, H.: Asymptotic behavior of the eigenvalues of certain integral equations. Transactions of the American Mathematical Society 109, 278–295 (1964)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2004 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Chen, A., Bickel, P.J. (2004). Robustness of Prewhitening Against Heavy-Tailed Sources. In: Puntonet, C.G., Prieto, A. (eds) Independent Component Analysis and Blind Signal Separation. ICA 2004. Lecture Notes in Computer Science, vol 3195. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-540-30110-3_29
Download citation
DOI: https://doi.org/10.1007/978-3-540-30110-3_29
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-23056-4
Online ISBN: 978-3-540-30110-3
eBook Packages: Springer Book Archive