Geodesic
A proximal ANLS algorithm for nonnegative tensor factorization with a periodic enhanced line search
Applications of Mathematics, Tome 58 (2013) no. 5, pp. 493-509 Cet article a éte moissonné depuis la source Czech Digital Mathematics Library

Voir la notice de l'article

The Alternating Nonnegative Least Squares (ANLS) method is commonly used for solving nonnegative tensor factorization problems. In this paper, we focus on algorithmic improvement of this method. We present a Proximal ANLS (PANLS) algorithm to enforce convergence. To speed up the PANLS method, we propose to combine it with a periodic enhanced line search strategy. The resulting algorithm, PANLS/PELS, converges to a critical point of the nonnegative tensor factorization problem under mild conditions. We also provide some numerical results comparing the ANLS and PANLS/PELS methods.
The Alternating Nonnegative Least Squares (ANLS) method is commonly used for solving nonnegative tensor factorization problems. In this paper, we focus on algorithmic improvement of this method. We present a Proximal ANLS (PANLS) algorithm to enforce convergence. To speed up the PANLS method, we propose to combine it with a periodic enhanced line search strategy. The resulting algorithm, PANLS/PELS, converges to a critical point of the nonnegative tensor factorization problem under mild conditions. We also provide some numerical results comparing the ANLS and PANLS/PELS methods.
DOI : 10.1007/s10492-013-0026-2
Classification : 15A69, 65F99, 65K05
Keywords: nonnegative tensor factorization; proximal method; alternating least squares; enhanced line search; global convergence 
@article{10_1007_s10492_013_0026_2,
     author = {Bunker, Douglas and Han, Lixing and Zhang, Shuhua},
     title = {A proximal {ANLS} algorithm for nonnegative tensor factorization with a periodic enhanced line search},
     journal = {Applications of Mathematics},
     pages = {493--509},
     year = {2013},
     volume = {58},
     number = {5},
     doi = {10.1007/s10492-013-0026-2},
     mrnumber = {3104615},
     zbl = {06282093},
     language = {en},
     url = {http://geodesic.mathdoc.fr/articles/10.1007/s10492-013-0026-2/}
}
TY  - JOUR
AU  - Bunker, Douglas
AU  - Han, Lixing
AU  - Zhang, Shuhua
TI  - A proximal ANLS algorithm for nonnegative tensor factorization with a periodic enhanced line search
JO  - Applications of Mathematics
PY  - 2013
SP  - 493
EP  - 509
VL  - 58
IS  - 5
UR  - http://geodesic.mathdoc.fr/articles/10.1007/s10492-013-0026-2/
DO  - 10.1007/s10492-013-0026-2
LA  - en
ID  - 10_1007_s10492_013_0026_2
ER  - 
%0 Journal Article
%A Bunker, Douglas
%A Han, Lixing
%A Zhang, Shuhua
%T A proximal ANLS algorithm for nonnegative tensor factorization with a periodic enhanced line search
%J Applications of Mathematics
%D 2013
%P 493-509
%V 58
%N 5
%U http://geodesic.mathdoc.fr/articles/10.1007/s10492-013-0026-2/
%R 10.1007/s10492-013-0026-2
%G en
%F 10_1007_s10492_013_0026_2
Bunker, Douglas; Han, Lixing; Zhang, Shuhua. A proximal ANLS algorithm for nonnegative tensor factorization with a periodic enhanced line search. Applications of Mathematics, Tome 58 (2013) no. 5, pp. 493-509. doi: 10.1007/s10492-013-0026-2

Cité par Sources :