Structured Variable Selection for Regularized Generalized Canonical Correlation Analysis

被引：1

作者：

Lofstedt, Tommy ^{[1
]}

Hadj-Selem, Fouad ^{[2
]}

Guillemot, Vincent ^{[3
]}

Philippe, Cathy ^{[4
]}

Duchesnay, Edouard ^{[2
]}

Frouin, Vincent ^{[2
]}

Tenenhaus, Arthur ^{[3
,5
]}

机构：

[1] Umea Univ, Computat Life Sci Cluster CLiC, Dept Chem, Umea, Sweden

[2] CEA Saclay, NeuroSpin, Gif Sur Yvette, France

[3] Brain & Spine Inst, Bioinformat Biostat Core Facil, IHU A ICM, Paris, France

[4] Gustave Roussy, Villejuif, France

[5] Univ Paris Sud, CNRS, Cent Supelec, Lab Signaux & Syst,UMR CNRS 8506, Paris, France

来源：

MULTIPLE FACETS OF PARTIAL LEAST SQUARES AND RELATED METHODS | 2016年 / 173卷

关键词：

RGCCA; Variable selection; Structured penalty; Sparse penalty;

D O I：

10.1007/978-3-319-40643-5_10

中图分类号：

O1 [数学];

学科分类号：

0701 ; 070101 ;

摘要：

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 (tau = 1) link between blocks. In this paper we go beyond the covariance link by proposing an extension of SGCCA for the full RGCCA model. (tau epsilon [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.

引用

页码：129 / 139

页数：11

共 17 条

[1]

[Anonymous], 2013, PROXIMAL ALGORITHMS

[2]

[Anonymous], ARXIV11092415

[3] An Efficient Optimization Algorithm for Structured Sparse CCA, with Applications to eQTL Mapping [J].

Chen X. ;

Liu H. .

Statistics in Biosciences, 2012, 4 (1) :3-26

[4] Proximal Splitting Methods in Signal Processing [J].

Combettes, Patrick L. ;

Pesquet, Jean-Christophe .

FIXED-POINT ALGORITHMS FOR INVERSE PROBLEMS IN SCIENCE AND ENGINEERING, 2011, 49 :185-+

[5]

de Leeuw J., 1994, INFORM SYSTEMS DATA, P308, DOI DOI 10.1007/978-3-642-46808-7_28

[6]

FLEISS JL, 1971, PSYCHOL BULL, V76, P378, DOI 10.1037/h0031619

[7]

Hadj-Selem F., 2016, ITERATIVE SMOO UNPUB

[8] Total Variation Regularization for fMRI-Based Prediction of Behavior [J].

Michel, Vincent ;

Gramfort, Alexandre ;

Varoquaux, Gael ;

Eger, Evelyn ;

Thirion, Bertrand .

IEEE TRANSACTIONS ON MEDICAL IMAGING, 2011, 30 (07) :1328-1340

[9] Smooth minimization of non-smooth functions [J].

Nesterov, Y .

MATHEMATICAL PROGRAMMING, 2005, 103 (01) :127-152

[10] Preserved Self-Awareness following Extensive Bilateral Brain Damage to the Insula, Anterior Cingulate, and Medial Prefrontal Cortices [J].

Philippi, Carissa L. ;

Feinstein, Justin S. ;

Khalsa, Sahib S. ;

Damasio, Antonio ;

Tranel, Daniel ;

Landini, Gregory ;

Williford, Kenneth ;

Rudrauf, David .

PLOS ONE, 2012, 7 (08)

← 1 2 →