Open Access Green as soon as Postprint is submitted to ZB.
Information-theoretic model selection for independent components.
In: Proceedings (Latent variable analysis and signal separation : 9th international conference, 27-30 September 2010, St. Malo, France). Berlin [u.a.]: Springer, 2010. 254-262 (Lect. Notes Comput. Sc. ; 6365)
Independent Component Analysis (ICA) is an essential building block for data analysis in many applications. Selecting the truly meaningful components from the result of an ICA algorithm, or comparing the results of different algorithms, however, are non-trivial problems. We introduce a very general technique for evaluating ICA results rooted in information-theoretic model selection. The basic idea is to exploit the natural link between non-Gaussianity and data compression: The better the data transformation represented by one or several ICs improves the effectiveness of data compression, the higher is the relevance of the ICs. In an extensive experimental evaluation we demonstrate that our novel information-theoretic measure robustly selects the most interesting components from data without requiring any assumptions or thresholds.
Altmetric
Additional Metrics?
Edit extra informations
Login
Publication type
Article: Conference contribution
Editors
Vigneron, V.* ; Zarzoso, V.* ; Moreau, E.*
ISSN (print) / ISBN
0302-9743
e-ISSN
1611-3349
ISBN
364215994X
Conference Title
Latent variable analysis and signal separation : 9th international conference
Conference Date
27-30 September 2010
Conference Location
St. Malo, France
Proceedings Title
Proceedings
Quellenangaben
Volume: 6365,
Pages: 254-262
Publisher
Springer
Publishing Place
Berlin [u.a.]
Non-patent literature
Publications