Skip navigation

Structure selection for convolutive non-negative matrix factorization using normalized maximum likelihood coding

Structure selection for convolutive non-negative matrix factorization using normalized maximum likelihood coding

Suzuki, Atsushi, Miyaguchi, Kohei and Yamanishi, Kenji (2017) Structure selection for convolutive non-negative matrix factorization using normalized maximum likelihood coding. In: 2016 IEEE 16th International Conference on Data Mining (ICDM). IEEE, Barcelona, pp. 1221-1226. ISBN 978-1509054749 ISSN 2374-8486 (doi:https://doi.org/10.1109/ICDM.2016.0163)

[img]
Preview
PDF (Author Accepted Manuscript)
30536 SUZUKI_Structure_Selection_for_Non-Negative_Matrix_Factorization_2017.pdf - Accepted Version

Download (614kB) | Preview

Abstract

Convolutive non-negative matrix factorization (CNMF) is a promising method for extracting features from sequential multivariate data. Conventional algorithms for CNMF require that the structure, or the number of bases for expressing the data, be specified in advance. We are concerned with the issue of how we can select the best structure of CNMF from given data. We first introduce a framework of probabilistic modeling of CNMF and reduce this issue to statistical model selection. The problem is here that conventional model selection criteria such as AIC, BIC, MDL cannot straightforwardly be applied since the probabilistic model for CNMF is irregular in the sense that parameters are not uniquely identifiable. We overcome this problem to propose a novel criterion for best structure selection for CNMF. The key idea is to apply the technique of latent variable completion in combination with normalized maximum likelihood coding criterion under the minimum description length principle. We empirically demonstrate the effectiveness of our method using artificial and real data sets.

Item Type: Conference Proceedings
Title of Proceedings: 2016 IEEE 16th International Conference on Data Mining (ICDM)
Additional Information: The 2016 IEEE 16th International Conference on Data Mining (ICDM) was held in Barcelona, Spain from 12-15 December 2016.
Uncontrolled Keywords: convolutive nonnegative matrix factorization
Subjects: Q Science > QA Mathematics > QA75 Electronic computers. Computer science
Faculty / Department / Research Group: Faculty of Liberal Arts & Sciences
Faculty of Liberal Arts & Sciences > School of Computing & Mathematical Sciences (CAM)
Last Modified: 14 Jan 2021 00:24
Selected for GREAT 2016: None
Selected for GREAT 2017: None
Selected for GREAT 2018: None
Selected for GREAT 2019: None
Selected for REF2021: None
URI: http://gala.gre.ac.uk/id/eprint/30536

Actions (login required)

View Item View Item

Downloads

Downloads per month over past year

View more statistics