Sparse nonnegative matrix factorization using ℓ0-constraints

Robert Peharz, Michael Stark, Franz Pernkopf

Onderzoeksoutput: Hoofdstuk in Boek/Rapport/CongresprocedureConferentiebijdrageAcademicpeer review

16 Citaten (Scopus)

Samenvatting

Although nonnegative matrix factorization (NMF) favors a part-based and sparse representation of its input, there is no guarantee for this behavior. Several extensions to NMF have been proposed in order to introduce sparseness via the ℓ1-norm, while little work is done using the more natural sparseness measure, the ℓ0-pseudo-norm. In this work we propose two NMF algorithms with ℓ0-sparseness constraints on the bases and the coefficient matrices, respectively. We show that classic NMF [1] is a suited tool for ℓ0-sparse NMF algorithms, due to a property we call sparseness maintenance. We apply our algorithms to synthetic and real-world data and compare our results to sparse NMF [2] and nonnegative KSVD [3].

Originele taal-2Engels
TitelProceedings of the 2010 IEEE International Workshop on Machine Learning for Signal Processing, MLSP 2010
Pagina's83-88
Aantal pagina's6
DOI's
StatusGepubliceerd - 24 nov 2010
Extern gepubliceerdJa
Evenement2010 IEEE 20th International Workshop on Machine Learning for Signal Processing, MLSP 2010 - Kittila, Finland
Duur: 29 aug 20101 sep 2010

Congres

Congres2010 IEEE 20th International Workshop on Machine Learning for Signal Processing, MLSP 2010
Land/RegioFinland
StadKittila
Periode29/08/101/09/10

Vingerafdruk

Duik in de onderzoeksthema's van 'Sparse nonnegative matrix factorization using ℓ<sup>0</sup>-constraints'. Samen vormen ze een unieke vingerafdruk.

Citeer dit