Skip to Main content Skip to Navigation
Conference papers

Stability analysis of multiplicative update algorithms for non-negative matrix factorization

Roland Badeau 1, * Nancy Bertin 2 Emmanuel Vincent 2
* Corresponding author
2 METISS - Speech and sound data modeling and processing
IRISA - Institut de Recherche en Informatique et Systèmes Aléatoires, Inria Rennes – Bretagne Atlantique
Abstract : Multiplicative update algorithms have encountered a great success to solve optimization problems with non-negativity constraints, such as the famous non-negative matrix factorization (NMF) and its many variants. However, despite several years of research on the topic, the understanding of their convergence properties is still to be improved. In this paper, we show that Lyapunov's stability theory provides a very enlightening viewpoint on the problem. We prove the stability of supervised NMF and study the more difficult case of unsupervised NMF. Numerical simulations illustrate those theoretical results, and the convergence speed of NMF multiplicative updates is analyzed.
Complete list of metadatas

Cited literature [10 references]  Display  Hide  Download
Contributor : Roland Badeau <>
Submitted on : Thursday, January 20, 2011 - 9:09:57 AM
Last modification on : Thursday, March 5, 2020 - 3:52:00 PM
Document(s) archivé(s) le : Thursday, April 21, 2011 - 2:43:04 AM


Files produced by the author(s)


  • HAL Id : hal-00557789, version 1


Roland Badeau, Nancy Bertin, Emmanuel Vincent. Stability analysis of multiplicative update algorithms for non-negative matrix factorization. International Conference on Acoustics, Speech and Signal Processing (ICASSP), May 2011, Prague, Czech Republic. 4 p. ⟨hal-00557789⟩



Record views


Files downloads