Learning high-dimensional Markov forest distributions: Analysis of error rates

The problem of learning forest-structured discrete graphical models from i.i.d. samples is considered. An algorithm based on pruning of the Chow-Liu tree through adaptive thresholding is proposed. It is shown that this algorithm is both structurally consistent and risk consistent and the error proba...

Full description

Bibliographic Details
Main Authors: Tan, Vincent Yan Fu, Anandkumar, Animashree, Willsky, Alan S.
Other Authors: Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science
Format: Article
Language:en_US
Published: MIT Press 2011
Online Access:http://hdl.handle.net/1721.1/66514
https://orcid.org/0000-0003-0149-5888
Description
Summary:The problem of learning forest-structured discrete graphical models from i.i.d. samples is considered. An algorithm based on pruning of the Chow-Liu tree through adaptive thresholding is proposed. It is shown that this algorithm is both structurally consistent and risk consistent and the error probability of structure learning decays faster than any polynomial in the number of samples under fixed model size. For the high-dimensional scenario where the size of the model d and the number of edges k scale with the number of samples n, sufficient conditions on (n,d,k) are given for the algorithm to satisfy structural and risk consistencies. In addition, the extremal structures for learning are identified; we prove that the independent (resp., tree) model is the hardest (resp., easiest) to learn using the proposed algorithm in terms of error rates for structure learning.