TY - GEN

T1 - Partitioned Hierarchical alternating least squares algorithm for CP tensor decomposition

AU - Phan, Anh Huy

AU - Tichavsky, Petr

AU - Cichocki, Andrzej

PY - 2017/6/16

Y1 - 2017/6/16

N2 - Canonical polyadic decomposition (CPD), also known as PARAFAC, is a representation of a given tensor as a sum of rank-one tensors. Traditional method for accomplishing CPD is the alternating least squares (ALS) algorithm. This algorithm is easy to implement with very low computational complexity per iteration. A disadvantage is that in difficult scenarios, where factor matrices in the decomposition contain nearly collinear columns, the number of iterations needed to achieve convergence might be very large. In this paper, we propose a modification of the algorithm which has similar complexity per iteration as ALS, but in difficult scenarios it needs a significantly lower number of iterations.

AB - Canonical polyadic decomposition (CPD), also known as PARAFAC, is a representation of a given tensor as a sum of rank-one tensors. Traditional method for accomplishing CPD is the alternating least squares (ALS) algorithm. This algorithm is easy to implement with very low computational complexity per iteration. A disadvantage is that in difficult scenarios, where factor matrices in the decomposition contain nearly collinear columns, the number of iterations needed to achieve convergence might be very large. In this paper, we propose a modification of the algorithm which has similar complexity per iteration as ALS, but in difficult scenarios it needs a significantly lower number of iterations.

KW - CANDECOMP/PARAFAC

KW - partitioning ALS

KW - tensor decomposition

UR - http://www.scopus.com/inward/record.url?scp=85023755669&partnerID=8YFLogxK

U2 - 10.1109/ICASSP.2017.7952615

DO - 10.1109/ICASSP.2017.7952615

M3 - Conference contribution

AN - SCOPUS:85023755669

T3 - ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings

SP - 2542

EP - 2546

BT - 2017 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2017 - Proceedings

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 2017 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2017

Y2 - 5 March 2017 through 9 March 2017

ER -