Skip to main content

Region Detection in Markov Random Fields: Gaussian Case

Publication ,  Journal Article
Soloveychik, I; Tarokh, V
February 11, 2018

We consider the problem of model selection in Gaussian Markov fields in the sample deficient scenario. The benchmark information-theoretic results in the case of d-regular graphs require the number of samples to be at least proportional to the logarithm of the number of vertices to allow consistent graph recovery. When the number of samples is less than this amount, reliable detection of all edges is impossible. In many applications, it is more important to learn the distribution of the edge (coupling) parameters over the network than the specific locations of the edges. Assuming that the entire graph can be partitioned into a number of spatial regions with similar edge parameters and reasonably regular boundaries, we develop new information-theoretic sample complexity bounds and show that a bounded number of samples can be sufficient to consistently recover these regions. Finally, we introduce and analyze an efficient region growing algorithm capable of recovering the regions with high accuracy. We show that it is consistent and demonstrate its performance benefits in synthetic simulations.

Duke Scholars

Publication Date

February 11, 2018
 

Citation

APA
Chicago
ICMJE
MLA
NLM
Soloveychik, I., & Tarokh, V. (2018). Region Detection in Markov Random Fields: Gaussian Case.
Soloveychik, Ilya, and Vahid Tarokh. “Region Detection in Markov Random Fields: Gaussian Case,” February 11, 2018.
Soloveychik I, Tarokh V. Region Detection in Markov Random Fields: Gaussian Case. 2018 Feb 11;
Soloveychik, Ilya, and Vahid Tarokh. Region Detection in Markov Random Fields: Gaussian Case. Feb. 2018.
Soloveychik I, Tarokh V. Region Detection in Markov Random Fields: Gaussian Case. 2018 Feb 11;

Publication Date

February 11, 2018