High-Dimensional Structure Estimation in Ising Models: Local Separation Criterion

Details High-Dimensional Structure Estimation in Ising Models: Local Separation Criterion High-Dimensional Structure Estimation in Ising Models: Local Separation Criterion

2011-07-08

arxiv.org/abs/1107.1736v3

Statistics

Machine Learning

Scientific paper

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 non-asymptotic necessary and sufficient conditions for structure estimation.

Affiliated with

Also associated with

No associations

Rating

High-Dimensional Structure Estimation in Ising Models: Local Separation Criterion does not yet have a rating. At this time, there are no reviews or comments for this scientific paper.

If you have personal experience with High-Dimensional Structure Estimation in Ising Models: Local Separation Criterion, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and High-Dimensional Structure Estimation in Ising Models: Local Separation Criterion will most certainly appreciate the feedback.

Rate now

Comments { 0 }

Profile ID: LFWR-SCP-O-674645