Local convergence analysis of FastICA and related algorithms

IEEE Transactions on Neural Networks

Volumn 19, Issue 6, 2008, Pages 1022-1032

  Shen, Hao ^a   Kleinsteuber, Martin ^a,b   Hüper, Knut ^a  

^a AUSTRALIAN NATIONAL UNIVERSITY   (Australia)

^b UNIVERSITY OF WÜRZBURG   (Germany)

Author keywords

Approximate Newton method; Convergence analysis; FastICA; Independent component analysis (ICA); Principal fiber bundle

Indexed keywords

APPROXIMATE NEWTON METHOD; CONVERGENCE ANALYSIS; FASTICA; FASTICA ALGORITHMS; GRAM-SCHMIDT; HIGHER ORDERS; LOCAL CONVERGENCES; ORTHONORMALIZATION; PARALLELIZED VERSIONS; POLAR DECOMPOSITIONS; PRINCIPAL FIBER BUNDLE; QR DECOMPOSITIONS; RIGOROUS ANALYSIS; SHIFT STRATEGIES; STILL MISSING;

CONVERGENCE OF NUMERICAL METHODS; HEMODYNAMICS; NEWTON-RAPHSON METHOD; PRINCIPAL COMPONENT ANALYSIS;

INDEPENDENT COMPONENT ANALYSIS;

ALGORITHM; ARTICLE; ARTIFICIAL NEURAL NETWORK; AUTOMATED PATTERN RECOGNITION; HUMAN; PRINCIPAL COMPONENT ANALYSIS;

ALGORITHMS; HUMANS; NEURAL NETWORKS (COMPUTER); PATTERN RECOGNITION, AUTOMATED; PRINCIPAL COMPONENT ANALYSIS;

EID: 49149129855     PISSN: 10459227     EISSN: None     Source Type: Journal    
DOI: 10.1109/TNN.2007.915117     Document Type: Article

References (24)

1. A. Hyvärinen, J. Karhunen, and E. Oja, Independent Component Analysis. New York: Wiley, 2001.
2. P. Comon, "Independent component analysis, a new concept?," Signal Process., vol. 36, no. 3, pp. 287-314, 1994.
3. A. Hyvärinen and E. Oja, "A fast fixed-point algorithm for independent component analysis," Neural Comput., vol. 9, no. 7, pp. 1483-1492, 1997.
4. A. Hyvärinen, "Fast and robust fixed-point algorithms for independent component analysis," IEEE Trans. Neural Netw., vol. 10, no. 3, pp. 626-634, May 1999.
5. H. Shen and K. Hüper, "Local convergence analysis of FastICA," in Lecture Notes in Computer Science. Berlin, Germany: Springer-Verlag, 2006, vol. 3889, pp. 893-900.
6. S. Douglas, "Relationships between the FastICA algorithm and the Rayleigh quotient iteration," in Lecture Notes in Computer Science Berlin, Germany: Springer-Verlag, 2006, vol. 3889, pp. 781-789.
7. B. N. Parlett, The Symmetric Eigenvalue Problem, ser. SIAM Classics In Applied Mathematics. Philadelphia, PA: SIAM, 1997.
8. H. Shen, K. Hüper, and A.-K. Seghouane, "Geometric optimization and FastICA algorithms," in Proc. 17th Int. Symp. Math. Theory Netw. Syst., Kyoto, Japan, 2006, pp. 1412-1418.
9. K. Hüper, "A calculus approach to matrix eigenvalue algorithms," Ph.D. dissertation, Dept. Math., Univ. Würzburg, Würzburg, Germany, Jul. 2002.
10. N. Delfosseand and P. Loubaton, "aptive blind separation of independent sources: A deflation approach," Signal Process., vol. 45, no. 1, pp. 59-83, 1995.
11. G. Golub and C. F. van Loan, Matrix Computations, 2nd ed. Baltimore, MD: The Johns Hopkins Univ. Press, 1989.
12. E. Oja, "Convergence of the symmetrical fastICA algorithm," in Proc. 9th Int. Conf. Neural Inf. Process., L. Wang, J. C. Rajapakse, K. Fukushima, S.-Y. Lee, and X. Yao, Eds., 2002, vol. 3, pp. 1368-1372.
13. E. Oja and Z. Yuan, "The fastICA algorithm revisited: Convergence analysis," IEEE Trans. Neural Netw., vol. 17, no. 6, pp. 1370-1381, Nov. 2006.
14. K. Hüper, H. Shen, and A.-K. Seghouane, "Local convergence properties of FastICA and some generalizations," in Proc. 31st IEEE Int. Conf. Acoust. Speech Signal Process., Toulouse, France, 2006, pp. V1009-V1012.
15. H. Shen, K. Hüper, and M. Kleinsteuber, "On FastICA algorithms and some generalizations," in Numerical Linear Algebra in Signals, Systems and Control, ser. Lecture Notes in Electrical Engineering. Berlin, Germany: Springer-Verlag, 2008, submitted for publication.
16. S. Kobayashi and K. Nomizu, Foundations of Differential Geometry. New York: Wiley, 1996, vol. 1.
17. T. Bröcker and T.-T. Dieck, Representations of Compact Lie Groups New York: Springer-Verlag, 1985.
18. M. Kleinsteuber, "Jacobi-type methods on semisimple lie algebras - A Lie algebraic approach to the symmetric eigenvalue problem," Ph.D. dissertation, Faculty Math. Comput. Sci., Bayerische Julius-Maximilians-Universität Würzburg, Germany, 2006.
19. P. Regalia and E. Kofidis, "Monotonic convergence of fixed-point algorithms for ICA," IEEE Trans. Neural Netw., vol. 14, no. 4, pp. 943-949, Jul. 2003.
20. M. Kleinsteuber and K. Hüper, "An intrinsic CG algorithm for computing dominant subspaces," in Proc. 32nd IEEE Int. Conf. Acoust. Speech Signal Process., 2007, pp. IV1405-IV1408.
21. M. Nikpour, K. Hüper, and J. H. Manton, "Generalizations of the Rayleigh quotient iteration for the iterative refinement of the eigenvectors of real symmetric matrices," in Proc. 30th IEEE Int. Conf. Acoust. Speech Signal Process., Philadelphia, PA, 2005, pp. V1041-V1044.
22. A. Hyvärinen and U. Köster, "FastISA: A fast fixed-point algorithm for independent subspace analysis," in Proc. 14th Eur. Symp. Artif. Neural Netw., Bruges, Belgium, 2006, pp. 371-376.
23. H. Shen and K. Hüper, "Generalized fastICA for independent subspace analysis," in Proc. 32nd IEEE Int. Conf. Acoust. Speech Signal Process., 2007, pp. IV1409-IV1412.
24. Y. Nishimori, S. Akaho, S. Abdallah, and M. Plumbley, "Flag manifolds for subspace ICA problems," in Proc. 32nd IEEE Int. Conf. Acoust. Speech Signal Process., 2007, pp. IV1417-IV1420.