Theorems on Positive Data : On the Uniqueness of NMF
Joint Authors
Christensen, Mads Græsbøll
Plumbley, Mark D.
Laurberg, Hans
Jensen, Søren Holdt
Hansen, Lars Kai
Source
Computational Intelligence and Neuroscience
Issue
Vol. 2008, Issue 2008 (31 Dec. 2008), pp.1-9, 9 p.
Publisher
Hindawi Publishing Corporation
Publication Date
2008-05-11
Country of Publication
Egypt
No. of Pages
9
Main Subjects
Abstract EN
We investigate the conditions for which nonnegative matrix factorization (NMF) is unique and introduce several theorems which can determine whether the decomposition is in fact unique or not.
The theorems are illustrated by several examples showing the use of the theorems and their limitations.
We have shown that corruption of a unique NMF matrix by additive noise leads to a noisy estimation of the noise-free unique solution.
Finally, we use a stochastic view of NMF to analyze which characterization of the underlying model will result in an NMF with small estimation errors.
American Psychological Association (APA)
Laurberg, Hans& Christensen, Mads Græsbøll& Plumbley, Mark D.& Hansen, Lars Kai& Jensen, Søren Holdt. 2008. Theorems on Positive Data : On the Uniqueness of NMF. Computational Intelligence and Neuroscience،Vol. 2008, no. 2008, pp.1-9.
https://search.emarefa.net/detail/BIM-496959
Modern Language Association (MLA)
Laurberg, Hans…[et al.]. Theorems on Positive Data : On the Uniqueness of NMF. Computational Intelligence and Neuroscience No. 2008 (2008), pp.1-9.
https://search.emarefa.net/detail/BIM-496959
American Medical Association (AMA)
Laurberg, Hans& Christensen, Mads Græsbøll& Plumbley, Mark D.& Hansen, Lars Kai& Jensen, Søren Holdt. Theorems on Positive Data : On the Uniqueness of NMF. Computational Intelligence and Neuroscience. 2008. Vol. 2008, no. 2008, pp.1-9.
https://search.emarefa.net/detail/BIM-496959
Data Type
Journal Articles
Language
English
Notes
Includes bibliographical references
Record ID
BIM-496959