Selecting β-divergence for nonnegative matrix factorization by score matching

Authors:
Zhiyun Lu;Zhirong Yang;Erkki Oja
Affiliations:
Department of Information and Computer Science, Aalto University, Finland;Department of Information and Computer Science, Aalto University, Finland;Department of Information and Computer Science, Aalto University, Finland
Venue:
ICANN'12 Proceedings of the 22nd international conference on Artificial Neural Networks and Machine Learning - Volume Part II
Year:
2012

Citing 8
Cited 0

Advances in Minimum Description Length: Theory and Applications (Neural Information Processing)

Advances in Minimum Description Length: Theory and Applications (Neural Information Processing)
Estimation of Non-Normalized Statistical Models by Score Matching

The Journal of Machine Learning Research
Some extensions of score matching

Computational Statistics & Data Analysis
A Generalized Divergence Measure for Nonnegative Matrix Factorization

Neural Computation
Sparse non-negative matrix factorizations via alternating non-negativity-constrained least squares for microarray data analysis

Bioinformatics
Nonnegative matrix factorization with the itakura-saito divergence: With application to music analysis

Neural Computation
Nonnegative Matrix and Tensor Factorizations: Applications to Exploratory Multi-way Data Analysis and Blind Source Separation

Nonnegative Matrix and Tensor Factorizations: Applications to Exploratory Multi-way Data Analysis and Blind Source Separation
Algorithms for nonnegative matrix factorization with the β-divergence

Neural Computation

Quantified Score

Hi-index	0.00

Visualization

Abstract

Nonnegative Matrix Factorization (NMF) based on the family of β-divergences has shown to be advantageous in several signal processing and data analysis tasks. However, how to automatically select the best divergence among the family for given data remains unknown. Here we propose a new estimation criterion to resolve the problem of selecting β. Our method inserts the point estimate of factorizing matrices from β-NMF into a Tweedie distribution that underlies β-divergence. Next, we adopt a recent estimation method called Score Matching for β selection in order to overcome the difficulty of calculating the normalizing constant in Tweedie distribution. Our method is tested on both synthetic and real-world data. Experimental results indicate that our selection criterion can accurately estimate β compared to ground truth or established research findings.