English

A Large-Deviation Analysis of the Maximum-Likelihood Learning of Markov Tree Structures

Machine Learning 2016-11-15 v3 Information Theory math.IT

Abstract

The problem of maximum-likelihood (ML) estimation of discrete tree-structured distributions is considered. Chow and Liu established that ML-estimation reduces to the construction of a maximum-weight spanning tree using the empirical mutual information quantities as the edge weights. Using the theory of large-deviations, we analyze the exponent associated with the error probability of the event that the ML-estimate of the Markov tree structure differs from the true tree structure, given a set of independently drawn samples. By exploiting the fact that the output of ML-estimation is a tree, we establish that the error exponent is equal to the exponential rate of decay of a single dominant crossover event. We prove that in this dominant crossover event, a non-neighbor node pair replaces a true edge of the distribution that is along the path of edges in the true tree graph connecting the nodes in the non-neighbor pair. Using ideas from Euclidean information theory, we then analyze the scenario of ML-estimation in the very noisy learning regime and show that the error exponent can be approximated as a ratio, which is interpreted as the signal-to-noise ratio (SNR) for learning tree distributions. We show via numerical experiments that in this regime, our SNR approximation is accurate.

Keywords

Cite

@article{arxiv.0905.0940,
  title  = {A Large-Deviation Analysis of the Maximum-Likelihood Learning of Markov Tree Structures},
  author = {Vincent Y. F. Tan and Animashree Anandkumar and Lang Tong and Alan S. Willsky},
  journal= {arXiv preprint arXiv:0905.0940},
  year   = {2016}
}

Comments

Accepted to the IEEE Transactions on Information Theory on Nov 18, 2010

R2 v1 2026-06-21T12:59:02.931Z