TY - JOUR
T1 - Global convergence of modified multiplicative updates for nonnegative matrix factorization
AU - Takahashi, Norikazu
AU - Hibi, Ryota
N1 - Funding Information:
Acknowledgements This work was partially supported by JSPS KAKENHI Grant Numbers 24560076 and 23310104, and by the project “R&D for cyber-attack predictions and rapid response technology by means of international cooperation” of the Ministry of Internal Affairs and Communications, Japan.
PY - 2014/3
Y1 - 2014/3
N2 - Nonnegative matrix factorization (NMF) is the problem of approximating a given nonnegative matrix by the product of two nonnegative matrices. The multiplicative updates proposed by Lee and Seung are widely used as efficient computational methods for NMF. However, the global convergence of these updates is not formally guaranteed because they are not defined for all pairs of nonnegative matrices. In this paper, we consider slightly modified versions of the original multiplicative updates and study their global convergence properties. The only difference between the modified updates and the original ones is that the former do not allow variables to take values less than a user-specified positive constant. Using Zangwill's global convergence theorem, we prove that any sequence of solutions generated by either of those modified updates has at least one convergent subsequence and the limit of any convergent subsequence is a stationary point of the corresponding optimization problem. Furthermore, we propose algorithms based on the modified updates that always stop within a finite number of iterations.
AB - Nonnegative matrix factorization (NMF) is the problem of approximating a given nonnegative matrix by the product of two nonnegative matrices. The multiplicative updates proposed by Lee and Seung are widely used as efficient computational methods for NMF. However, the global convergence of these updates is not formally guaranteed because they are not defined for all pairs of nonnegative matrices. In this paper, we consider slightly modified versions of the original multiplicative updates and study their global convergence properties. The only difference between the modified updates and the original ones is that the former do not allow variables to take values less than a user-specified positive constant. Using Zangwill's global convergence theorem, we prove that any sequence of solutions generated by either of those modified updates has at least one convergent subsequence and the limit of any convergent subsequence is a stationary point of the corresponding optimization problem. Furthermore, we propose algorithms based on the modified updates that always stop within a finite number of iterations.
KW - Finite termination
KW - Global convergence
KW - Multiplicative update
KW - Nonnegative matrix factorization
UR - http://www.scopus.com/inward/record.url?scp=84894416864&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=84894416864&partnerID=8YFLogxK
U2 - 10.1007/s10589-013-9593-0
DO - 10.1007/s10589-013-9593-0
M3 - Article
AN - SCOPUS:84894416864
VL - 57
SP - 417
EP - 440
JO - Computational Optimization and Applications
JF - Computational Optimization and Applications
SN - 0926-6003
IS - 2
ER -