Cramér-Rao-induced bounds for CANDECOMP/PARAFAC tensor decomposition

IEEE Transactions on Signal Processing

Volumn 61, Issue 8, 2013, Pages 1986-1997

  Tichavský, Petr ^a   Phan, Anh Huy ^b   Koldovský, Zbyněk ^a,c  

^a INSTITUTE OF INFORMATION THEORY AND AUTOMATION   (Czech Republic)

^b RIKEN BRAIN SCIENCE INSTITUTE   (Japan)

^c TECHNICAL UNIVERSITY OF LIBEREC   (Czech Republic)

Author keywords

Canonical polyadic decomposition; Cram r Rao lower bound; multilinear models; stability; uniqueness

Indexed keywords

ARBITRARY DIMENSION; CANONICAL POLYADIC DECOMPOSITIONS; LOWER BOUNDS; MULTILINEAR MODELS; NOISY OBSERVATIONS; TENSOR DECOMPOSITION; UNBIASED ESTIMATES; UNIQUENESS;

ARTS COMPUTING; CONVERGENCE OF NUMERICAL METHODS;

TENSORS;

EID: 84875651157     PISSN: 1053587X     EISSN: None     Source Type: Journal    
DOI: 10.1109/TSP.2013.2245660     Document Type: Article

References (48)

1. R. Bro, "Multi-way analysis in the food industry models, algorithms, and applications," Univ. Amsterdam. Amsterdam, The Netherlands [Online]. Available: http://www/models.life.ku.dk/research/theses/, 1998
2. P. M. Kroonenberg, Applied Multiway Data Analysis. New York, NY, USA: Wiley, 2008.
3. A. Smilde, R. Bro, and P. Geladi, Multi-way Analysis: Applications in the Chemical Sciences. New York, NY, USA: Wiley, 2004.
4. A. Cichocki, R. Zdunek, A. H. Phan, and S. I. Amari, Nonnegative Matrix and Tensor Factorizations: Applications to Exploratory Multi-way Data Analysis and Blind Source Separation. New York, NY, USA: Wiley, 2009.
5. V. De Silva and L.-H. Lim, "Tensor rank and the ill-posedness of the best low-rank approximation problem," SIAM J. Matrix Anal. Appl., vol. 30, pp. 1084-1127, 2008.
6. W. P. Krijnen, T. K. Dijkstra, and A. Stegeman, "On the non-existence of optimal solutions and the occurrence of "degeneracy" in the Cande-comp/Parafac model," Psychometrika, vol. 73, pp. 431-439, 2008.
7. R. A. Harshman, "Foundations of the PARAFAC procedure: Model and conditions for an "explanatory" multimode factor analysis," UCLA Working Papers Phonet., vol. 16, pp. 1-84, 1970.
8. R. A. Harshman, "Determination and proof of minimum uniqueness conditions for PARAFAC," UCLA Working Papers Phonet., vol. 22, pp. 111-117, 1972.
9. J. B. Kruskal, "Three-way arrays: Rank and uniqueness of trilinear decompositions, with application to arithmetic complexity and statistics," Linear Algebra Appl., vol. 18, pp. 95-138, 1977.
10. J. B. Kruskal, "Rank, decomposition, and uniqueness for 3-way and N-way arrays," in Multiway Data Analysis. Amsterdam, The Netherlands: North-Holland, 1989, pp. 7-18.
11. N. D. Sidiropoulos and R. Bro, "On the uniqueness of multilinear de composition of N-way arrays," J. Chemometr., vol. 14, pp. 229-239, May 2000.
12. J. M. F. Ten Berge and N. D. Sidiropoulos, "On uniqueness in CAN-DECOMP/PARAFAC," Psychometrika, vol. 67, no. 3, pp. 399-409, Sep. 2002.
13. T. Jiang and N. D. Sidiropoulos, "Kruskal's permutation lemma and the identification of Candecomp/Parafac and bilinear models with constant modulus constraints," IEEE Trans. Signal Process., vol. 52, pp. 2625-2636, 2004.
14. L. De Lathauwer, "A link between the canonical decomposition in multilinear algebra and simultaneous matrix diagonalization," SIAM J. Matrix Anal. Appl., vol. 28, pp. 642-666, 2006. (Pubitemid 47109355)
15. A. Stegeman and N. D. Sidiropoulos, "On Kruskal's uniqueness condition for the Candecomp/Parafac decomposition," Linear Algebra Appl., vol. 420, pp. 540-552, 2007. (Pubitemid 44751783)
16. A. Stegeman, "On uniqueness conditions for Candecomp/Parafac and Indscal with full column rank in one mode," Linear Algebra Appl., vol. 431, no. 1-2, pp. 211-227, 2009.
17. A. Stegeman and A. L. F. de Almeida, "Uniqueness conditions for constrained three-way factor decompositions with linearly dependent loadings," SIAM J. Matrix Anal. Appl., vol. 31, no. 3, pp. 1469-1490, Aug. 2009.
18. A. Stegeman, "On uniqueness of the nth order tensor decomposition into rank-1 terms with linear independence in one mode," SIAM J. Matrix Anal. Appl., vol. 31, no. 5, pp. 2498-2516, 2010.
19. A. Stegeman, "On uniqueness of the canonical tensor decomposition with some form of symmetry," SIAM J. Matrix Anal. Appl., vol. 32, no. 3, pp. 561-583, 2011.
20. D. Brie, S. Miron, F. Caland, and C. Mustin, "An uniqueness condition for the 4-way CANDECOMP/PARAFAC model with collinear loadings in three modes," in Proc. Int. Conf. Acoust., Speech, Signal Process. (ICASSP), 2011, pp. 4112-4115.
21. I. Domanov and L. De Lathauwer, "On the uniqueness of the canonical polyadic decomposition of third-order tensors-Part I: Basic results and uniqueness of one factor matrix," [Online]. Available: http://arxiv. org/pdf/1301.4602v1.pdf
22. I. Domanov and L. De Lathauwer, "On the uniqueness of the canonical polyadic decomposition of third-order tensors-Part II: Uniqueness of the overall decomposition," [Online]. Available: http://arxiv.org/pdf/1301.4603v1.pdf
23. X. Guo, S. Miron, D. Brie, and A. Stegeman, "Uni-mode and partial uniqueness conditions for CANDECOMP/PARAFAC of three-way arrays with linearly dependent loadings," SIAM J. Matrix Anal. Appl., vol. 33, no. 1, pp. 111-129, 2012.
24. A. Stegeman, "Candecomp/Parafac: From diverging components to a decomposition in block terms," SIAM J. Matrix Anal. Appl., vol. 33, pp. 291-316, 2012.
25. S. Basu and Y. Bresler, "The stability of nonlinear least squares problems and the Cramér-Rao bound," IEEE Trans. Signal Process., vol. 48, pp. 3426-3436, Dec. 2000.
26. G. Tomasi and R. Bro, "A comparison of algorithms for fitting the PARAFAC model," Computat. Statist. Data Anal., vol. 50, no. 7, pp. 1700-1734, Apr. 2006. (Pubitemid 43052351)
27. P. Paatero, "A weighted non-negative least squares algorithm for three-way 'PARAFAC' factor analysis," Chemometr. Intell. Lab. Syst., vol. 38, pp. 223-242, 1997. (Pubitemid 27512497)
28. A.-H. Phan, P. Tichavský, and A. Cichocki, "Low complexity damped Gauss-Newton algorithms for CANDECOMP/PARAFAC," SIAM J. Matrix Anal. Appl., vol. 34, pp. 126-147, 2013.
29. P. Tichavský and Z. Koldovský, "Stability of CANDECOMP-PARAFAC tensor decomposition," in Proc. Int. Conf. Acoust., Speech, Signal Process. (ICASSP), Prague, Czech Republic, 2011, pp. 4164-4167.
30. P. Tichavský and Z. Koldovský, "Weight adjusted tensor method for blind separation of underdetermined mixtures of nonstationary sources," IEEE Trans. Signal Process., vol. 59, no. 3, pp. 1037-1047, Mar. 2011.
31. X. Liu and N. D. Sidiropoulos, "Cramér-Rao lower bounds for low-rank decomposition of multidimensional arrays," IEEE Trans. Signal Process., vol. 49, no. 9, pp. 2074-2086, Sep. 2001. (Pubitemid 32866214)
32. T. Jiang and N. D. Sidiropoulos, "Blind identification of out of cell users in DS-CDMA," EURASIP J. Appl. Signal Process. (Special Issue on Advances in Smart Antennas), no. 9, pp. 1212-1224, Aug. 2004.
33. Z. Koldovský, P. Tichavský, and A.H. Phan, "Stability analysis and fast damped-gauss-newton algorithm for INDSCAL tensor decomposition," in Proc. IEEE Workshop Statist. Signal Process., Nice, France, Jun. 2011, pp. 581-584.
34. A.-H. Phan, P. Tichavský, and A. Cichocki, "CANDECOMP/PARAFAC decomposition of high-order tensors through tensor reshaping," IEEE Trans. Signal Process., submitted for publication.
35. R. Bro, R. A. Harshman, N. D. Sidiropoulos, and M. E. Lundy, "Modeling multi-way data with linearly dependent loadings," J. Chemometr., vol. 23, no. 7-8, pp. 324-340, 2009.
36. M. B. Dosse, J. M. F. Berge, and J. N. Tendeiro, "Some new results on orthogonally constrained candecomp," J. Class., vol. 28, pp. 144-155, 2011.
37. M. Sorensen, L. De Lathauwer, P. Comon, S. Icart, and L. Deneire, "Canonical polyadic decomposition with a columnwise orthonormal factor matrix," SIAM J. Matrix Anal. Appl., vol. 33, no. 4, pp. 1190-1213, 2012.
38. J. Chen and Y. Saad, "On the tensor SVD and the optimal low rank orthogonal approximation of tensors," SIAM J. Matrix Anal. Appl., vol. 30, pp. 1709-1734, 2009.
39. J. Tendeiro, M. Bennani Dosse, and J. M. F. Ten Berge, "First and second-order derivatives for CP and INDSCAL," Chemometr. Intell. Lab. Syst., vol. 106, pp. 27-36, 2011.
40. A. Householder, The Theory of Matrices in Numerical Analysis. New York, NY, USA: Blaisdell, 1964.
41. G. Tomasi and R. Bro, "PARAFAC and missing values," Chemometr. Intell. Lab. Syst., vol. 75, pp. 163-180, 2005. (Pubitemid 40164340)
42. R. Bro, "Exploratory study of sugar production using fluorescence spectroscopy and multi-way analysis," Chemometr. Intell. Lab. Syst., vol. 46, pp. 133-147, 1999. (Pubitemid 29098981)
43. R. Bro, "Multi-way Analysis in the Food Industry-Models, Algorithms, and Applications," Ph.D. thesis, Univ. Amsterdam, Amsterdam, The Netherlands, 1998.
44. B. Porat, Digital Processing of Random Signals. Englewood Cliffs, NJ, USA: Prentice-Hall, 1994.
45. T. G. Kolda and B. W. Bader, "Tensor decompositions and applications," SIAM Rev., vol. 51, no. 3, pp. 455-500, Sep. 2009.
46. P. Comon, J. M. F. ten Berge, L. De Lathauwer, and J. Castaing, "Generic and typical ranks of multi-way arrays," Linear Algebra Appl., vol. 430, no. 11, pp. 2997-3007, 2009, (2009).
47. T. G. Kolda, "Orthogonal tensor decompositions," SIAM J. Matrix Anal. Appl., vol. 23, pp. 243-255, 2001.
48. P. Tichavský, A. H. Phan, and A. Cichocki, "A further improvement of a fast damped Gauss-Newton algorithm for CP tensor decomposition," in Proc. Int. Conf. Acoust., Speech, Signal Process. (ICASSP), 2013.