Models of Random Sparse Eigenmatrices and Bayesian Analysis of Multivariate Structure

  title={Models of Random Sparse Eigenmatrices and Bayesian Analysis of Multivariate Structure},
  author={Andrew Cron and M. West},
  journal={arXiv: Methodology},
  • Andrew Cron, M. West
  • Published 2016
  • Computer Science, Mathematics
  • arXiv: Methodology
  • We discuss probabilistic models of random covariance structures defined by distributions over sparse eigenmatrices. The decomposition of orthogonal matrices in terms of Givens rotations defines a natural, interpretable framework for defining distributions on sparsity structure of random eigenmatrices. We explore theoretical aspects and implications for conditional independence structures arising in multivariate Gaussian models, and discuss connections with sparse PCA, factor analysis and… CONTINUE READING
    5 Citations


    Bayesian Learning in Sparse Graphical Factor Models via Annealed Entropy
    • 15
    • PDF
    Bayesian Inference for General Gaussian Graphical Models With Application to Multivariate Lattice Data
    • 97
    • Highly Influential
    • PDF
    Dynamic matrix-variate graphical models
    • 159
    • Highly Influential
    • PDF
    Sparse covariance estimation in heterogeneous samples.
    • 37
    • Highly Influential
    • PDF
    Sparse graphical models for exploring gene expression data
    • 440
    • Highly Influential
    • PDF
    High-Dimensional Sparse Factor Modeling: Applications in Gene Expression Genomics
    • 463
    • PDF
    Bayesian factor regression models in the''large p
    • 456
    • PDF
    Modeling covariance matrices via partial autocorrelations
    • 66
    • PDF