 |
Book sections
Structured Variable Selection for Regularized Generalized Canonical Correlation Analysis, The Multiple Facets of Partial Least Squares and Related Methods
Tommy Lofstedt
1
Fouad Hadj-Selem
1
Vincent Guillemot
1
Cathy Philippe
2
Edouard Duchesnay
3
Vincent Frouin
1
Arthur Tenenhaus
4
Tommy Lofstedt 1
Author
Fouad Hadj-Selem 1
Mail :
Author
Vincent Guillemot 1
Mail :
Author
Cathy Philippe 2
Mail :
Author
Edouard Duchesnay 3
Mail : Site :
Author
Vincent Frouin 1
Mail :
Author IdHAL : vincent-ejm-frouin ORCID : https://orcid.org/0000-0001-9360-6623
Arthur Tenenhaus 4
Mail :
Author
1
NEUROSPIN - Service NEUROSPIN (France)
- DRF (CEA) - Direction de Recherche Fondamentale (CEA) : DRF/JOLIOT (Direction de Recherche Fondamentale
Fundamental Research Division
CEA Saclay
91191 Gif-sur-Yvette
- France)
- CEA - Commissariat à l'énergie atomique et aux énergies alternatives (Centre de Saclay Centre de Grenoble Centre de Cadarache etc - France)
- Université Paris-Saclay (Espace Technologique, Bat. Discovery - RD 128 - 2e ét., 91190 Saint-Aubin - France)
2
UMR 8203 - Vectorologie et thérapeutiques anti-cancéreuses [Villejuif] (Gustave Roussy - PR2
114 rue Edouard Vaillant
94805 Villejuif CEDEX - France)
- UP11 - Université Paris-Sud - Paris 11 : UMR 8203 (Bâtiment 300 - 91405 Orsay cedex - France)
- IGR - Institut Gustave Roussy : UMR 8203 (114, rue Édouard-Vaillant 94805 Villejuif Cedex -France - France)
- CNRS - Centre National de la Recherche Scientifique : UMR 8203 (France)
3
UNATI - Unité Analyse et Traitement de l'Information (France)
- NEUROSPIN - Service NEUROSPIN : DRF/JOLIOT (France)
- DRF (CEA) - Direction de Recherche Fondamentale (CEA) : DRF/JOLIOT (Direction de Recherche Fondamentale
Fundamental Research Division
CEA Saclay
91191 Gif-sur-Yvette
- France)
- CEA - Commissariat à l'énergie atomique et aux énergies alternatives (Centre de Saclay Centre de Grenoble Centre de Cadarache etc - France)
- Université Paris-Saclay (Espace Technologique, Bat. Discovery - RD 128 - 2e ét., 91190 Saint-Aubin - France)
- DRF (CEA) - Direction de Recherche Fondamentale (CEA) : DRF/JOLIOT (Direction de Recherche Fondamentale
Fundamental Research Division
CEA Saclay
91191 Gif-sur-Yvette
- France)
4
L2S - Laboratoire des signaux et systèmes (Plateau de Moulon 3 rue Joliot Curie 91192 GIF SUR YVETTE CEDEX - France)
- CNRS - Centre National de la Recherche Scientifique (France)
- CentraleSupélec (3, rue Joliot Curie, Plateau de Moulon, 91192 GIF-SUR-YVETTE Cedex - France)
- UP11 - Université Paris-Sud - Paris 11 (Bâtiment 300 - 91405 Orsay cedex - France)
Abstract : Regularized Generalized Canonical Correlation Analysis (RGCCA) extends regularized canonical correlation analysis to more than two sets of variables. Sparse GCCA (SGCCA) was recently proposed to address the issue of variable selection. However, the variable selection scheme offered by SGCCA is limited to the covariance (τ = 1) link between blocks. In this paper we go beyond the covariance link by proposing an extension of SGCCA for the full RGCCA model (τ ∈ [0, 1]). In addition, we also propose an extension of SGCCA that exploits pre-given structural relationships between variables within blocks. Specifically, we propose an algorithm that allows structured and sparsity-inducing penalties to be included in the RGCCA optimization problem.
Document type :
Book sections
Complete list of metadatas
https://hal-centralesupelec.archives-ouvertes.fr/hal-01396614
Contributor : Alexandra Siebert <>
Submitted on : Monday, November 14, 2016 - 4:28:49 PM
Last modification on : Tuesday, June 23, 2020 - 2:18:02 PM
Contributor : Alexandra Siebert <>
Submitted on : Monday, November 14, 2016 - 4:28:49 PM
Last modification on : Tuesday, June 23, 2020 - 2:18:02 PM
Identifiers
- HAL Id : hal-01396614, version 1
- DOI : 10.1007/978-3-319-40643-5_10
Collections
CNRS | L2S | SUP_LSS | CEA | FNCLCC | IGR | CENTRALESUPELEC | SUP_SIGNAUX | UNIV-PARIS-SACLAY | JOLIOT | CEA-DRF | NEUROSPIN | CEA-UPSAY
Citation
Tommy Lofstedt, Fouad Hadj-Selem, Vincent Guillemot, Cathy Philippe, Edouard Duchesnay, et al.. Structured Variable Selection for Regularized Generalized Canonical Correlation Analysis, The Multiple Facets of Partial Least Squares and Related Methods
. Springer Proceedings in Mathematics & Statistics, pp.129-139, 2016, The Multiple Facets of Partial Least Squares and Related Methods, ⟨10.1007/978-3-319-40643-5_10⟩. ⟨hal-01396614⟩
