English

High-Dimensional Gaussian Graphical Model Selection: Walk Summability and Local Separation Criterion

Machine Learning 2012-03-06 v3 Statistics Theory Statistics Theory

Abstract

We consider the problem of high-dimensional Gaussian graphical model selection. We identify a set of graphs for which an efficient estimation algorithm exists, and this algorithm is based on thresholding of empirical conditional covariances. Under a set of transparent conditions, we establish structural consistency (or sparsistency) for the proposed algorithm, when the number of samples n=omega(J_{min}^{-2} log p), where p is the number of variables and J_{min} is the minimum (absolute) edge potential of the graphical model. The sufficient conditions for sparsistency are based on the notion of walk-summability of the model and the presence of sparse local vertex separators in the underlying graph. We also derive novel non-asymptotic necessary conditions on the number of samples required for sparsistency.

Keywords

Cite

@article{arxiv.1107.1270,
  title  = {High-Dimensional Gaussian Graphical Model Selection: Walk Summability and Local Separation Criterion},
  author = {Animashree Anandkumar and Vincent Y. F. Tan and Alan. S. Willsky},
  journal= {arXiv preprint arXiv:1107.1270},
  year   = {2012}
}
R2 v1 2026-06-21T18:33:14.456Z