Title
A Further Improvement Of A Fast Damped Gauss-Newton Algorithm For Candecomp-Parafac Tensor Decomposition
Abstract
In this paper, a novel implementation of the damped Gauss-Newton algorithm (also known as Levenberg-Marquart) for the CANDECOMP-PARAFAC (CP) tensor decomposition is proposed. The method is based on a fast inversion of the approximate Hessian for the problem. It is shown that the inversion can be computed on O(NR6) operations, where N and R is the tensor order and rank, respectively. It is less than in the best existing state-of-the art algorithm with O((NR6)-R-3) operations. The damped Gauss-Newton algorithm is suitable namely for difficult scenarios, where nearly-colinear factors appear in several modes simultaneously. Performance of the method is shown on decomposition of large tensors (100 x 100 x 100 and 100 x 100 x 100 x 100) of rank 5 to 90.
Year
DOI
Venue
2013
10.1109/ICASSP.2013.6638809
2013 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH AND SIGNAL PROCESSING (ICASSP)
Keywords
Field
DocType
Multilinear models, canonical polyadic decomposition, damped Gauss-Newton algorithm
Mathematical optimization,Tensor,Mathematical analysis,Inversion (meteorology),Hessian matrix,Gauss–Newton algorithm,Mathematics,Newton's method,Tensor decomposition
Conference
ISSN
Citations 
PageRank 
1520-6149
3
0.44
References 
Authors
11
3
Name
Order
Citations
PageRank
Petr Tichavský134141.01
Anh Huy Phan282851.60
Andrzej Cichocki35228508.42