Approximate joint singular value decomposition of an asymmetric rectangular matrix set

IEEE Transactions on Signal Processing

Volumn 59, Issue 1, 2011, Pages 415-424

  Congedo, Marco ^a   Phlypo, Ronald ^a   Pham, Dinh Tuan ^a  

^a CNRS   (France)

Author keywords

Bilinear orthogonal approximate joint diagonalization; Givens rotations; Jacobi iterations; L dwin orthogonalization; power iteration; singular value decomposition

Indexed keywords

APPROXIMATE JOINT DIAGONALIZATION (AJD); GIVENS ROTATION; JACOBI ITERATION; ORTHOGONALIZATION; POWER ITERATION;

ALGORITHMS; INDEPENDENT COMPONENT ANALYSIS; JACOBIAN MATRICES; LINEAR ALGEBRA; SINGULAR VALUE DECOMPOSITION;

BLIND SOURCE SEPARATION;

EID: 84862788553     PISSN: 1053587X     EISSN: None     Source Type: Journal    
DOI: 10.1109/TSP.2010.2087018     Document Type: Article

References (39)

1. L. Parra and P. Sadja, "Blind source separation via generalized eigen- value decomposition," J. Mach. Learn. Res., vol. 4, pp. 1261-1269, 2003.
2. L. Tong, R.-W. Liu, V. C. Soon, and Y.-F. Huang, "Indeterminacy and identiability of blind identication," IEEE Trans. Circuits Syst., vol. 38, no. 5, pp. 499-509, 1991.
3. A. Belouchrani, K. Abed-Meraim, J. Cardoso, and E. Moulines, "A blind source separation technique using second order statistics," IEEE Trans. Signal Process., vol. 45, no. 2, pp. 434-444, 1997.
4. J.-F. Cardoso and A. Souloumiac, "Blind beamforming for non-Gaussian signals," Proc. Inst. Electr. Eng.-F, vol. 140, no. 6, pp. 362-370, 1993.
5. E. Moreau, "A generalization of joint-diagonalization criteria for source separation," IEEE Trans. Signal Process., vol. 49, no. 3, pp. 530-541, Mar. 2001.
6. F. J. Theis and Y. Inouye, "On the use of joint diagonalization in blind signal processing," in Proc. IEEE Int. Symp. Circuits Syst. (ISCAS), Kos, Greece, 2006, pp. 3589-3592.
7. D.T.Pham,"Jointapproximatediagonalizationofpositivedenitema- trices," SIAM J. Matrix Anal. Appl. , vol. 22, no. 4, pp. 1136-1152, 2000.
8. R. Vollgraf and K. Obermayer, "Quadratic optimization for simulta- neous matrix diagonalization," IEEE Trans. Signal Process., vol. 54, no. 9, pp. 3270-3278, Sep. 2006.
9. P. Tichavský and A. Yeredor, "Fast approximate joint diagonalization incorporating weight matrices," IEEE Trans. Signal Process., vol. 57, no. 3, pp. 878-891, Mar. 2009.
10. E. M. Fadaili, N. T. Moreau, and E. Moreau, "Nonorthogonal joint di- agonalization/zerodiagonalizationforsourceseparationbasedontime- frequency distributions," IEEE Trans. Signal Process., vol. 55, no. 5, pp. 1673-1687, May 2007.
11. X.-L. Li and X.-D. Zhang, "Nonorthogonal joint diagonalization free of degenerate solution," IEEE Trans. Signal Process., vol. 55, no. 5, pp. 1803-1814, May 2007.
12. F.Wang,Z.Liu,andJ.Zhang,"Nonorthogonaljointdiagonalizational- gorithm based on trigonometric parameterization," IEEE Trans. Signal Process., vol. 55, no. 11, pp. 5299-5308, Nov. 2007.
13. G. Zhou, Z. Yang, Z. Wu, and J. Zhang, "Non-orthogonal joint diago- nalization with diagonal constraints," Progress in Nat. Sci., vol. 18, pp. 735-739, 2008.
14. A. Souloumiac, "Nonorthogonal joint diagonalization by combining givens and hyperbolic rotations," IEEE Trans. Signal Process., vol. 57, no. 6, pp. 2222-2231, Jun. 2009.
15. M. Congedo and D.-T. Pham, "Least-squares joint diagonalization of a matrix set by a congruence transformation," presented at the Sin- gaporean-French IPAL Symp. (SinFra'09), Singapore, Feb. 18-20, 2009.
16. D.-T. Pham and M. Congedo, "Least square joint diagonalization of matrices under an intrinsic scale constraint," in Proc. 8th Int. Conf. Indepen. Compon. Anal. Signal Separ. (ICA), 2008, pp. 298-305.
17. S. Degerine and E. Kane, "A comparative study of approximate joint diagonalization algorithms for blind source separation in presence of additive noise," IEEE Trans. Signal Process., vol. 55, no. 6, pp. 3022-3031, Jun. 2007.
18. R. Iferroudjene,K. Abed-Meraim,and A. Belouchrani, "A new Jabobi- like method for joint diagonalization of arbitrary non-defective ma- trices," Appl. Math. Computat., vol. 211, pp. 363-373, 2009.
19. A. Ziehe, P. Laskov, G. Nolte, and K.-R. Müller, "A fast algorithm for joint diagonalization with non-orthogonal transformations and its application to blind source separation," J. Mach. Learn. Res., vol. 5, pp. 777-800, 2004.
20. Handbook of Blind Source Separation. Independent Component Anal- ysis and Applications, P. Comon and C. Jutten, Eds. Oxford, U.K.: Academic, 2010.
21. M. Wax and J. Sheinvald, "A least-squares approach to joint diagonal- ization," IEEE Trans. Signal Process., vol. 4, no. 2, pp. 52-53, Feb. 1997.
22. A. Cichocki and S.-I. Amari, Adaptive Blind Signal and Image Pro- cessing Learning Algorithms and Applications, 2005 ed. New York: Wiley, 2002.
23. A. Hyvärinen, J. Karhunen, and E. Oja, Independent Component Anal- ysis. New York: Wiley Intersci., 2001.
24. B. Pesquet-Popescu, J.-C. Pesquet, and A. P. Petropulu, "Joint singular value decomposition-A new tool for separable representation of im- ages," in Proc. Int. Image Process. Conf., 2001, vol. 2, pp. 569-572.
25. G. Hori, "Comparison of two main approaches to joint SVD," in Inde- pendentComponentAnalysisandSignalSeparation,ser.LectureNotes in Computer Science, T. Adali, C. Jutten, J. A. Romano, and A. Barros, Eds. Berlin, Heidelberg: Springer, 2009, vol. 5441, pp. 42-49.
26. M. Congedo, C. Gouy-Pailler, and C. Jutten, "On the blind source sep- aration of human electroencephalogram by approximate joint diago- nalization of second order statistics," Clin. Neurophysiol., vol. 119, no. 12, pp. 2677-2686, 2008.
27. J.-F. Cardoso and B. H. Laheld, "Equivariant adaptive source separa- tion," IEEE Trans. Signal Process., vol. 44, no. 12, pp. 3017-3030, 1996.
28. B. Afsari, "Sensitivity analysis for the problem of matrix joint diago- nalization," SIAM J. Matrix Anal. Appl., vol. 30, no. 3, pp. 1148-1171, 2008.
29. A. Aïssa-El-Bey, K. Abed-Meraim, Y. Grenier, and Y. Hua, "A gen- eral framework for second-order blind separation of stationary colored sources," Signal Process., vol. 88, pp. 2123-2137, 2008.
30. F. Theis, "Uniqueness of complex and multidimensional independent component analysis," Signal Process., vol. 84, pp. 951-956, 2004.
31. N. Correa, T. Adali, Y. Li, and V. Calhoun, "Canonical correlation analysis for data fusion and group interferences," IEEE Signal Process. Mag., vol. 27, no. 4, pp. 39-50, 2010.
32. J. D. Carroll, "Generalization of canonical correlation analysis to three or more sets of variables," Proc. 76th Ann. Conv. APA, pp. 227-228, 1968.
33. C. Eckart and G. Young, "The approximation of one matrix by another of lower rank," Psychometrika, vol. 1, pp. 211-218, 1936.
34. J.-F. Cardoso and A. Souloumiac, "Jacobi angles for simultaneous di- agonalization,"SIAM J.Matrix Anal.Appl., vol. 17,no.1, pp.161-164, 1996.
35. L. De Lathauwer and P. Comon, "Higher-order power method," in Proc. Nonlinear Theory and its Applications (NOLTA), Las Vegas, NV, 1995, vol. 1, pp. 91-96.
36. B. C. Carlson and J. M. Keller, "Orthogonalization procedures and the localization of Wannier functions," Phys. Rev., vol. 105, no. 1, pp. 102-103, 1957.
37. G. H. Golub and C. F. Van Loan, Matrix Computations, 3rd ed. Bal- timore, MD: The Johns Hopkins Univ. Press, 1996.
38. O. Macchi and E. Moreau, "Self-adaptive source separation by direct and recursive networks," in Proc. Int. Conf. Digit. Signal Process. (DSP), 1993, pp. 1154-1159.
39. P. Welch, "The use of fast fourier transform for the estimation of power spectra: A method based on time averaging over short, modied periodograms," IEEE Trans. Audio Electroacoust., vol. 15, no. 2, pp. 70-74, 1967.