English

Inferring sparse Gaussian graphical models with latent structure

Methodology 2010-04-05 v1 Applications

Abstract

Our concern is selecting the concentration matrix's nonzero coefficients for a sparse Gaussian graphical model in a high-dimensional setting. This corresponds to estimating the graph of conditional dependencies between the variables. We describe a novel framework taking into account a latent structure on the concentration matrix. This latent structure is used to drive a penalty matrix and thus to recover a graphical model with a constrained topology. Our method uses an 1\ell_1 penalized likelihood criterion. Inference of the graph of conditional dependencies between the variates and of the hidden variables is performed simultaneously in an iterative \textsc{em}-like algorithm. The performances of our method is illustrated on synthetic as well as real data, the latter concerning breast cancer.

Keywords

Cite

@article{arxiv.0810.3177,
  title  = {Inferring sparse Gaussian graphical models with latent structure},
  author = {Christophe Ambroise and Julien Chiquet and Catherine Matias},
  journal= {arXiv preprint arXiv:0810.3177},
  year   = {2010}
}

Comments

35 pages, 15 figures

R2 v1 2026-06-21T11:32:03.761Z