Doubly sparse factor models for unifying feature transformation and feature selection

A number of unsupervised learning methods for high-dimensional data are largely divided into two groups based on their procedures, i.e., (1) feature selection, which discards irrelevant dimensions of the data, and (2) feature transformation, which constructs new variables by transforming and mixing...

Full description

Saved in:
Bibliographic Details
Published inJournal of physics. Conference series Vol. 233; no. 1; p. 012021
Main Authors Katahira, Kentaro, Matsumoto, Narihisa, Sugase-Miyamoto, Yasuko, Okanoya, Kazuo, Okada, Masato
Format Journal Article
LanguageEnglish
Published Bristol IOP Publishing 01.06.2010
Subjects
Bayesian analysis
Physics
Statistical inference
Online AccessGet full text

Cover

More Information
Summary:A number of unsupervised learning methods for high-dimensional data are largely divided into two groups based on their procedures, i.e., (1) feature selection, which discards irrelevant dimensions of the data, and (2) feature transformation, which constructs new variables by transforming and mixing over all dimensions. We propose a method that both selects and transforms features in a common Bayesian inference procedure. Our method imposes a doubly automatic relevance determination (ARD) prior on the factor loading matrix. We propose a variational Bayesian inference for our model and demonstrate the performance of our method on both synthetic and real data.
ISSN:1742-6596
1742-6588
1742-6596
DOI:10.1088/1742-6596/233/1/012021