Premium
A three–step algorithm for CANDECOMP/PARAFAC analysis of large data sets with multicollinearity
Author(s) -
Kiers Henk A. L.
Publication year - 1998
Publication title -
journal of chemometrics
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.47
H-Index - 92
eISSN - 1099-128X
pISSN - 0886-9383
DOI - 10.1002/(sici)1099-128x(199805/06)12:3<155::aid-cem502>3.0.co;2-5
Subject(s) - multicollinearity , algorithm , computation , regularization (linguistics) , computer science , point (geometry) , mathematics , statistics , artificial intelligence , regression analysis , geometry
Abstract Fitting the CANDECOMP/PARAFAC model by the standard alternating least squares algorithm often requires very many iterations. One case in point is that of analysing data with mild to severe multicollinearity. If, in addition, the size of the data is large, the computation of one CANDECOMP/PARAFAC solution is very time‐consuming. The present paper describes a three‐step procedure which is much more efficient than the ordinary CANDECOMP/PARAFAC algorithm, by combining the idea of data compression with a form of regularization of the compressed data array. © 1998 John Wiley & Sons, Ltd.