High-dimensional structure estimation in Ising models: Local separation criterion
Animashree Anandkumar, Vincent Y. F. Tan, Furong Huang, Alan S. Willsky
The Annals of Statistics · 2012 · Volume 40 · Issue 3
Abstract
We consider the problem of high-dimensional Ising (graphical) model selection. We propose a simple algorithm for structure estimation based on the thresholding of the empirical conditional variation distances. We introduce a novel criterion for tractable graph families, where this method is efficient, based on the presence of sparse local separators between node pairs in the underlying graph. For such graphs, the proposed algorithm has a sample complexity of $n=\Omega(J_{\min}^{-2}\log p)$, where $p$ is the number of variables, and $J_{\min}$ is the minimum (absolute) edge potential in the model. We also establish nonasymptotic necessary and sufficient conditions for structure estimation.
Keywords
05C80, 62H12, graphical model selection, Ising models, local-separation property
Enable JavaScript for citation tools and additional paper interactions.