Using the simultaneous generalized Schur decomposition as a Candecomp/Parafac algorithm for ill-conditioned data

Journal of Chemometrics

Volumn 23, Issue 7-8, 2009, Pages 385-392

  Stegeman, Alwin ^a  

^a UNIVERSITY OF GRONINGEN   (Netherlands)

Author keywords

Candecomp; Degenerate solutions; Diverging components; Parafac; Schur decomposition

Indexed keywords

CANDECOMP; DEGENERATE SOLUTION; DIVERGING COMPONENT; GENERALIZED SCHUR DECOMPOSITION; ILL-CONDITIONED; OUTER PRODUCT; PARAFAC; SCHUR DECOMPOSITION; SUMS OF SQUARES; THREE-WAY ARRAYS;

EID: 70349658465     PISSN: 08869383     EISSN: 1099128X     Source Type: Journal    
DOI: 10.1002/cem.1232     Document Type: Article

References (32)

1. Carroll JD, Chang JJ. Analysis of individual differences in multidimensional scaling via an n-way generalization of Eckart-Young decomposition. Psychometrika 1970; 35: 283-319.
2. Harshman RA. Foundations of the Parafac procedure: models and conditions for an explanatory multimodal factor analysis. UCLA Working Papers in Phonetics 1970; 16: 1-84.
3. Tomasi G, Bro R. A comparison of algorithms for fitting the Parafac model. Comput. Stat. Data Anal. 2006; 50: 1700-1734.
4. Kroonenberg PM. Applied Multiway Data Analysis. Wiley Series in Probability and Statistics, 2008.
5. Smilde A, Bro R, Geladi P. Multi-way Analysis: Applications in the Chemical Sciences. Wiley: Chichester, 2004.
6. Sidiropoulos ND, Giannakis G, Bro R. Blind Parafac receivers for DS- CDMA systems. IEEE Trans. Signal Process. 2000; 48: 810-823.
7. Sidiropoulos ND, Bro R, Giannakis G. Parallel factor analysis in sensor array processing. IEEE Trans. Signal Process. 2000; 48: 2377-2388.
8. Tucker LR. Some mathematical notes on three-mode factor analysis. Psychometrika 1966; 31: 279-311.
9. Kruskal JB. Three-way arrays: rank and uniqueness of trilinear decompositions, with applications to arithmetic complexity and statistics. Linear Algebra Appl. 1977; 18: 95-138.
10. Stegeman A, Sidiropoulos ND. On Kruskal's uniqueness condition for the Candecomp/Parafac decomposition. Linear Algebra Appl. 2007; 420: 540-552.
11. Mitchell BC, Burdick DS. Slowly converging Parafac sequences: swamps and two-factor degeneracies. J. Chemometr.1994;8:155-168.
12. Harshman RA, Lundy ME. Data preprocessing and the extended Parafac model. In Research Methods for Multimode Data Analysis, Law HG, Snyder CW, Jr., Hattie JA, McDonald RP (eds). Praeger: New York, 1984; 216-284.
13. Paatero P. Construction and analysis of degenerate Parafac models. J. Chemometr. 2000; 14: 285-299.
14. Stegeman A. Degeneracy in Candecomp/Parafac explained for p×p×2 arrays of rank p+1 or higher. Psychometrika 2006; 71: 483- 501.
15. Stegeman A. Degeneracy in Candecomp/Parafac and Indscal explainedforseveralthree-slicedarrayswithatwo-valuedtypicalrank. Psychometrika 2007; 72: 601-619.
16. Stegeman A. Low-rank approximation of generic p × q × 2 arrays and diverging components in the Candecomp/Parafac model. SIAM J. Matrix Anal. Appl. 2008; 30: 988-1007.
17. De Silva V, Lim L-H. Tensor rank and the ill-posedness of the best low-rank approximation problem. SIAM J. Matrix Anal. Appl. 2008; 30: 1084-1127.
18. Kruskal JB, Harshman RA, Lundy ME. How 3-MFA data can cause degenerate Parafac solutions, among other relationships. In Multiway Data Analysis, Coppi R, Bolasco S (eds). North-Holland: Amsterdam, 1989; 115-121.
19. Krijnen WP, Dijkstra TK, Stegeman A. On the non-existence of optimal solutions and the occurrence of degeneracy in the Candecomp/Parafac model. Psychometrika 2008; 73: 431-439.
20. Rayens WS, Mitchell BC. Two-factor degeneracies and a stabilization of Parafac. Chemometr. Intell. Lab. Syst. 1997; 38: 173-181.
21. Kiers HAL. A three-step algorithm for Candecomp/Parafac analysis of large data sets with multicollinearity. J.Chemometr.1998; 12: 155-171.
22. Cao YZ, Chen ZP, Mo CY, Wu HL, Yu RQ. A Parafac algorithm using penaltydiagonalizationerror(PDE)forthree-waydataarrayresolution. Analyst 2000; 125: 2303-2310.
23. Rajih M, Comon P, Harshman RA. Enhanced line search: A novel method to accelerate Parafac. SIAM J. Matrix Anal. Appl. 2008; 30: 1128-1147.
24. Zhao H-G. A heuristic method for computing the best rank-r approximation to higher-order tensors. Int. J. Contemp. Math. Sci. 2008; 3: 471-476.
25. Navasca C, De Lathauwer L, Kindermann S. Swampreducing technique for tensor decomposition. Proceedings of the 16th European Signal Processing Conference (EUSIPCO 2008), Lausanne, Switzerland, 25-29 August 2008.
26. Lim L-H. Optimal solutions to non-negative Parafac/multilinear NMF always exist. Talk at the Workshop on Tensor Decompositions and Applications, CIRM, Luminy, Marseille, France, August 29-September 2 2005.
27. Stegeman A, De Lathauwer L. A method to avoid diverging components in the Candecomp/Parafac model for generic I × J × 2 arrays. SIAM J. Matrix Anal. Appl. 2009; 30: 1614-1638.
28. De Lathauwer L, De Moor B, Vandewalle J. Computation of the canconical decomposition by means of a simultaneous generalized Schur decomposition. SIAM J. Matrix Anal. Appl. 2004; 26: 295-327.
29. Van der Veen A-J, Paulraj A. An analytical constant modulus algorithm. IEEE Trans. Signal Process. 1996; 44: 1136-1155.
30. Lundy ME, Harshman RA, Kruskal JB. A two-stage procedure incorporating good features of both trilinear and quadrilinear models. In Multiway Data Analysis, Coppi R, Bolasco S (eds). North-Holland: Amsterdam, 1989; 123-130.
31. Harshman RA. The problem and nature of degenerate solutions or decompositions of 3-way arrays. Talk at the Workshop on Tensor Decompositions, AIM, Palo Alto, USA, 19-23 July 2004.
32. Hopke PK, Paatero P, Jia H, Ross RT, Harshman RA. Three- way (Parafac) factor analysis: examination and comparison of alternative computational methods as applied to ill-conditioned data. Chemometr. Intell. Lab. Syst. 1998; 43: 25-42.