Robust Parallel Fast-ICA Algorithms Using Batch and Adaptive MMSE Estimators

Autores
Messina, Francisco; Cernuschi-Frías, Bruno
Año de publicación
2012
Idioma
inglés
Tipo de recurso
documento de conferencia
Estado
versión publicada
Descripción
All the algorithms for ICA require high-order statistics to estimate the independent components. This is because second-order information is insufficient to assess that two random variables are independent of each other. It is known that the robustness of the high-order sample estimators is poor, meaning that a few outliers can change dramatically its value. In this paper, we generalize the alternative robust statistics for moments and cumulants introduced by Welling presenting the MMSE-robust moments. Then we present a batch and adaptive versions of an algorithm for estimating the parameters that define the estimator. Finally, we modify two FastICA algorithms of ICA based on kurtosis and negentropy to apply the MMSE robust estimators and show some experiments with supergaussian sources to demonstrate the improvement.
Sociedad Argentina de Informática e Investigación Operativa
Materia
Ciencias Informáticas
ICA
Algorithm
Batch and Adaptive MMSE Estimators
Nivel de accesibilidad
acceso abierto
Condiciones de uso
http://creativecommons.org/licenses/by-nc-sa/4.0/
Repositorio
SEDICI (UNLP)
Institución
Universidad Nacional de La Plata
OAI Identificador
oai:sedici.unlp.edu.ar:10915/123933
Acceder
id SEDICI_299debb971ad059cd0d5318240d3818e
oai_identifier_str oai:sedici.unlp.edu.ar:10915/123933
network_acronym_str SEDICI
repository_id_str 1329
network_name_str SEDICI (UNLP)
spelling Robust Parallel Fast-ICA Algorithms Using Batch and Adaptive MMSE EstimatorsMessina, FranciscoCernuschi-Frías, BrunoCiencias InformáticasICAAlgorithmBatch and Adaptive MMSE EstimatorsAll the algorithms for ICA require high-order statistics to estimate the independent components. This is because second-order information is insufficient to assess that two random variables are independent of each other. It is known that the robustness of the high-order sample estimators is poor, meaning that a few outliers can change dramatically its value. In this paper, we generalize the alternative robust statistics for moments and cumulants introduced by Welling presenting the MMSE-robust moments. Then we present a batch and adaptive versions of an algorithm for estimating the parameters that define the estimator. Finally, we modify two FastICA algorithms of ICA based on kurtosis and negentropy to apply the MMSE robust estimators and show some experiments with supergaussian sources to demonstrate the improvement.Sociedad Argentina de Informática e Investigación Operativa2012-08info:eu-repo/semantics/conferenceObjectinfo:eu-repo/semantics/publishedVersionObjeto de conferenciahttp://purl.org/coar/resource_type/c_5794info:ar-repo/semantics/documentoDeConferenciaapplication/pdf240-251http://sedici.unlp.edu.ar/handle/10915/123933enginfo:eu-repo/semantics/altIdentifier/url/https://41jaiio.sadio.org.ar/sites/default/files/21_AST_2012.pdfinfo:eu-repo/semantics/altIdentifier/issn/1850-2806info:eu-repo/semantics/openAccesshttp://creativecommons.org/licenses/by-nc-sa/4.0/Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International (CC BY-NC-SA 4.0)reponame:SEDICI (UNLP)instname:Universidad Nacional de La Platainstacron:UNLP2025-09-29T11:29:43Zoai:sedici.unlp.edu.ar:10915/123933Institucionalhttp://sedici.unlp.edu.ar/Universidad públicaNo correspondehttp://sedici.unlp.edu.ar/oai/snrdalira@sedici.unlp.edu.arArgentinaNo correspondeNo correspondeNo correspondeopendoar:13292025-09-29 11:29:43.479SEDICI (UNLP) - Universidad Nacional de La Platafalse
dc.title.none.fl_str_mv Robust Parallel Fast-ICA Algorithms Using Batch and Adaptive MMSE Estimators
title Robust Parallel Fast-ICA Algorithms Using Batch and Adaptive MMSE Estimators
spellingShingle Robust Parallel Fast-ICA Algorithms Using Batch and Adaptive MMSE Estimators
Messina, Francisco
Ciencias Informáticas
ICA
Algorithm
Batch and Adaptive MMSE Estimators
title_short Robust Parallel Fast-ICA Algorithms Using Batch and Adaptive MMSE Estimators
title_full Robust Parallel Fast-ICA Algorithms Using Batch and Adaptive MMSE Estimators
title_fullStr Robust Parallel Fast-ICA Algorithms Using Batch and Adaptive MMSE Estimators
title_full_unstemmed Robust Parallel Fast-ICA Algorithms Using Batch and Adaptive MMSE Estimators
title_sort Robust Parallel Fast-ICA Algorithms Using Batch and Adaptive MMSE Estimators
dc.creator.none.fl_str_mv Messina, Francisco
Cernuschi-Frías, Bruno
author Messina, Francisco
author_facet Messina, Francisco
Cernuschi-Frías, Bruno
author_role author
author2 Cernuschi-Frías, Bruno
author2_role author
dc.subject.none.fl_str_mv Ciencias Informáticas
ICA
Algorithm
Batch and Adaptive MMSE Estimators
topic Ciencias Informáticas
ICA
Algorithm
Batch and Adaptive MMSE Estimators
dc.description.none.fl_txt_mv All the algorithms for ICA require high-order statistics to estimate the independent components. This is because second-order information is insufficient to assess that two random variables are independent of each other. It is known that the robustness of the high-order sample estimators is poor, meaning that a few outliers can change dramatically its value. In this paper, we generalize the alternative robust statistics for moments and cumulants introduced by Welling presenting the MMSE-robust moments. Then we present a batch and adaptive versions of an algorithm for estimating the parameters that define the estimator. Finally, we modify two FastICA algorithms of ICA based on kurtosis and negentropy to apply the MMSE robust estimators and show some experiments with supergaussian sources to demonstrate the improvement.
Sociedad Argentina de Informática e Investigación Operativa
description All the algorithms for ICA require high-order statistics to estimate the independent components. This is because second-order information is insufficient to assess that two random variables are independent of each other. It is known that the robustness of the high-order sample estimators is poor, meaning that a few outliers can change dramatically its value. In this paper, we generalize the alternative robust statistics for moments and cumulants introduced by Welling presenting the MMSE-robust moments. Then we present a batch and adaptive versions of an algorithm for estimating the parameters that define the estimator. Finally, we modify two FastICA algorithms of ICA based on kurtosis and negentropy to apply the MMSE robust estimators and show some experiments with supergaussian sources to demonstrate the improvement.
publishDate 2012
dc.date.none.fl_str_mv 2012-08
dc.type.none.fl_str_mv info:eu-repo/semantics/conferenceObject
info:eu-repo/semantics/publishedVersion
Objeto de conferencia
http://purl.org/coar/resource_type/c_5794
info:ar-repo/semantics/documentoDeConferencia
format conferenceObject
status_str publishedVersion
dc.identifier.none.fl_str_mv http://sedici.unlp.edu.ar/handle/10915/123933
url http://sedici.unlp.edu.ar/handle/10915/123933
dc.language.none.fl_str_mv eng
language eng
dc.relation.none.fl_str_mv info:eu-repo/semantics/altIdentifier/url/https://41jaiio.sadio.org.ar/sites/default/files/21_AST_2012.pdf
info:eu-repo/semantics/altIdentifier/issn/1850-2806
dc.rights.none.fl_str_mv info:eu-repo/semantics/openAccess
http://creativecommons.org/licenses/by-nc-sa/4.0/
Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International (CC BY-NC-SA 4.0)
eu_rights_str_mv openAccess
rights_invalid_str_mv http://creativecommons.org/licenses/by-nc-sa/4.0/
Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International (CC BY-NC-SA 4.0)
dc.format.none.fl_str_mv application/pdf
240-251
dc.source.none.fl_str_mv reponame:SEDICI (UNLP)
instname:Universidad Nacional de La Plata
instacron:UNLP
reponame_str SEDICI (UNLP)
collection SEDICI (UNLP)
instname_str Universidad Nacional de La Plata
instacron_str UNLP
institution UNLP
repository.name.fl_str_mv SEDICI (UNLP) - Universidad Nacional de La Plata
repository.mail.fl_str_mv alira@sedici.unlp.edu.ar
_version_ 1844616175948922880
score 13.070432

Publicaciones similares