The FastICA Algorithm Revisited: Convergence Analysis

The fast independent component analysis (FastICA) algorithm is one of the most popular methods to solve problems in ICA and blind source separation. It has been shown experimentally that it outperforms most of the commonly used ICA algorithms in convergence speed. A rigorous local convergence analysis has been presented only for the so-called one-unit case, in which just one of the rows of the separating matrix is considered. However, in the FastICA algorithm, there is also an explicit normalization step, and it may be questioned whether the extra rotation caused by the normalization will affect the convergence speed. The purpose of this paper is to show that this is not the case and the good convergence properties of the one-unit case are also shared by the full algorithm with symmetrical normalization. A local convergence analysis is given for the general case, and the global behavior is illustrated numerically for two sources and two mixtures in several typical cases

[1]  Aapo Hyvärinen,et al.  Fast and robust fixed-point algorithms for independent component analysis , 1999, IEEE Trans. Neural Networks.

[2]  Shun-ichi Amari,et al.  Stability Analysis Of Adaptive Blind Source Separation , 1997 .

[3]  E. Oja,et al.  Convergence of the symmetrical FastICA algorithm , 2002, Proceedings of the 9th International Conference on Neural Information Processing, 2002. ICONIP '02..

[4]  C. L. Nikias,et al.  Higher-order spectra analysis : a nonlinear signal processing framework , 1993 .

[5]  D. Chakrabarti,et al.  A fast fixed - point algorithm for independent component analysis , 1997 .

[6]  A. Hyvärinen,et al.  One-unit contrast functions for independent component analysis: a statistical analysis , 1997 .

[7]  Andrzej Cichocki,et al.  Stability Analysis of Learning Algorithms for Blind Source Separation , 1997, Neural Networks.

[8]  Andrzej Cichocki,et al.  Adaptive blind signal and image processing , 2002 .

[9]  Liqing Zhang,et al.  Self-adaptive blind source separation based on activation functions adaptation , 2004, IEEE Transactions on Neural Networks.

[10]  Lei Xu,et al.  One-Bit-Matching Conjecture for Independent Component Analysis , 2004, Neural Computation.

[11]  Jitendra K. Tugnait,et al.  Comments on 'New criteria for blind deconvolution of nonminimum phase systems (channels)' , 1992, IEEE Trans. Inf. Theory.

[12]  Nathalie Delfosse,et al.  Adaptive blind separation of independent sources: A deflation approach , 1995, Signal Process..

[13]  Erkki Oja,et al.  Efficient Variant of Algorithm FastICA for Independent Component Analysis Attaining the CramÉr-Rao Lower Bound , 2006, IEEE Transactions on Neural Networks.

[14]  Jinwen Ma,et al.  A Further Result on the ICA One-Bit-Matching Conjecture , 2005, Neural Computation.

[15]  Jean-Francois Cardoso,et al.  Eigen-structure of the fourth-order cumulant tensor with application to the blind source separation problem , 1990, International Conference on Acoustics, Speech, and Signal Processing.

[16]  Pierre Comon,et al.  Independent component analysis, A new concept? , 1994, Signal Process..

[17]  Erkki Oja,et al.  Cramer-Rao lower bound for linear independent component analysis , 2005, Proceedings. (ICASSP '05). IEEE International Conference on Acoustics, Speech, and Signal Processing, 2005..

[18]  P. Tichavský,et al.  Efficient variant of algorithm fastica for independent component analysis attaining the cramer-RAO lower bound , 2005, IEEE/SP 13th Workshop on Statistical Signal Processing, 2005.

[19]  M. Girolami,et al.  Advances in Independent Component Analysis , 2000, Perspectives in Neural Computing.

[20]  Phillip A. Regalia,et al.  Monotonic convergence of fixed-point algorithms for ICA , 2003, IEEE Trans. Neural Networks.

[21]  J. J. Lacoume,et al.  Sources indentification: a solution based on the cumulants , 1988, Fourth Annual ASSP Workshop on Spectrum Estimation and Modeling.

[22]  Erkki Oja,et al.  Performance analysis of the FastICA algorithm and Crame/spl acute/r-rao bounds for linear independent component analysis , 2006, IEEE Transactions on Signal Processing.

[23]  Erkki Oja,et al.  One-unit Learning Rules for Independent Component Analysis , 1996, NIPS.

[24]  Changyuan Fan,et al.  On the Convergence Behavior of the FastICA Algorithm with the Kurtosis Cost Function , 2007, Third International Conference on Intelligent Information Hiding and Multimedia Signal Processing (IIH-MSP 2007).

[25]  Erkki Oja,et al.  An Experimental Comparison of Neural Algorithms for Independent Component Analysis and Blind Separation , 1999, Int. J. Neural Syst..