Structured Variable Selection for Regularized Generalized Canonical Correlation Analysis

  • Tommy LöfstedtEmail author
  • Fouad Hadj-Selem
  • Vincent Guillemot
  • Cathy Philippe
  • Edouard Duchesnay
  • Vincent Frouin
  • Arthur Tenenhaus
Conference paper
Part of the Springer Proceedings in Mathematics & Statistics book series (PROMS, volume 173)


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.


RGCCA Variable selection Structured penalty Sparse penalty 



This work was supported by grants from the French National Research Agency: ANR IA BRAINOMICS (ANR-10-BINF-04), and a European Commission grant: MESCOG (FP6 ERA-NET NEURON 01 EW1207).


  1. Chen, X., Liu, H.: An efficient optimization algorithm for structured sparse CCA, with applications to eQTL mapping. Stat. Biosci. 4, 3–26 (2011)CrossRefGoogle Scholar
  2. Combettes, P.L., Pesquet, J.C.: Proximal splitting methods in signal processing. In: Bauschke, H.H., Burachik, R.S., Combettes, P.L., Elser, V., Luke, D.R., Wolkowicz, H. (eds.) Fixed-Point Algorithms for Inverse Problems in Science and Engineering, pp. 185–212. Springer, New York (2011)CrossRefGoogle Scholar
  3. De Leeuw, J.: Block relaxation algorithms in statistics. In: Bock, H.-H., Lenski, W., Richter, M.M. (eds.) Information Systems and Data Analysis, pp. 308–325. Springer, Berlin (1994)CrossRefGoogle Scholar
  4. Fleiss, J.L.: Measuring nominal scale agreement among many raters. Psychol. Bull. 76, 378–382 (1971)CrossRefGoogle Scholar
  5. Hadj-Selem, F., Löfstedt, T., Duchesnay, E., Frouin, V., Guillemot, V.: Iterative Smoothing Algorithm for Regression with Structured Sparsity (2016, Submitted paper)Google Scholar
  6. Michel, V., Gramfort, A., Varoquaux, G., Eger, E., Thirion, B.: Total variation regularization for f MRI-based prediction of behavior. IEEE Trans. Med. Imaging 30, 1328–1340 (2011)CrossRefGoogle Scholar
  7. Nesterov, Y.: Smooth minimization of non-smooth functions. Math. Program. 103, 127–152 (2004)MathSciNetCrossRefzbMATHGoogle Scholar
  8. Parikh, N., Boyd, S.: Proximal Algorithms. Now Publishers Inc., New York (2013)Google Scholar
  9. Philippe, C., Puget, S., Bax, D.A., Job, B., Varlet, P., Junier, M.P., Andreiuolo, F., Carvalho, D., Reis, R., Guerrini-Rousseau, L., Roujeau, T., Dessen, P., Richon, C., Lazar, V., Le Teuff, G., Sainte-Rose, C., Geoerger, B., Vassal, G., Jones, C., Grill, J.: Mesenchymal transition and PDGFRA amplification/mutation are key distinct oncogenic events in pediatric diffuse intrinsic pontine gliomas. PloS one 7, 1–14 (2012)Google Scholar
  10. Qin, Z., Scheinberg, K., Goldfarb, D.: Efficient block-coordinate descent algorithms for the Group Lasso. Math. Program. Comput. 5, 143–169 (2013)MathSciNetCrossRefzbMATHGoogle Scholar
  11. Schäfer, J., Strimmer, K.: A shrinkage approach to large-scale covariance matrix estimation and implications for functional genomics. Stat. Appl. Genet. Mol. Biol. 4, 1–30 (2005)MathSciNetGoogle Scholar
  12. Schmidt, M., Le Roux, N., Bach, F.: Convergence rates of inexact proximal-gradient methods for convex optimization (2011). ArXiv:1109.2415Google Scholar
  13. Tenenhaus, A., Tenenhaus, M.: Regularized generalized canonical correlation analysis. Psychometrika 76, 257–284 (2011)MathSciNetCrossRefzbMATHGoogle Scholar
  14. Tenenhaus, A., Philippe, C., Guillemot, V., Lê Cao, K.A., Grill, J., Frouin, V.: Variable selection for generalized canonical correlation analysis. Biostatistics 15, 569–583 (2014)CrossRefGoogle Scholar
  15. van den Berg, E., Schmidt, M., Friedlander, M.P., Murphy, K.: Group sparsity via linear-time projection. Technical report TR-2008-09, Department of Computer Science, University of British Columbia, Vancouver (2008)Google Scholar
  16. Vinod, H.: Canonical ridge and econometrics of joint production. J. Econom. 4, 147–166 (1976)CrossRefzbMATHGoogle Scholar
  17. Witten, D.M., Tibshirani, R., Hastie, T.: A penalized matrix decomposition, with applications to sparse principal components and canonical correlation analysis. Biostatistics 10, 515–534 (2009)CrossRefGoogle Scholar

Copyright information

© Springer International Publishing Switzerland 2016

Authors and Affiliations

  • Tommy Löfstedt
    • 1
    Email author
  • Fouad Hadj-Selem
    • 2
  • Vincent Guillemot
    • 3
  • Cathy Philippe
    • 4
  • Edouard Duchesnay
    • 2
  • Vincent Frouin
    • 2
  • Arthur Tenenhaus
    • 5
  1. 1.Computational Life Science Cluster (CLiC), Department of ChemistryUmeå UniversityUmeåSweden
  2. 2.NeuroSpinCEA SaclayGif-sur-YvetteFrance
  3. 3.Bioinformatics/Biostatistics Core Facility, IHU-A-ICMBrain and Spine InstituteParisFrance
  4. 4.Gustave RoussyVillejuifFrance
  5. 5.Laboratoire des Signaux et Systèmes (L2S, UMR CNRS 8506)CentraleSupélec-CNRS-Université Paris-Sud and Bioinformatics/Biostatistics Platform IHU-A-ICM, Brain and Spine InstituteParisFrance

Personalised recommendations