Robust Estimation of Latent Tree Graphical Models: Inferring Hidden States With Inexact Parameters

DOI10.1109/TIT.2013.2251927MaRDI QIDQ5346462zbMATH OpenFDO

Authors Elchanan Mossel, Sebastien Roch, Allan Sly

Publication date 8 June 2017

Published in IEEE Transactions on Information Theory (Search for Journal in Brave)

Full work available at URL https://arxiv.org/abs/1109.4668

Mathematics Subject Classification ID

Applications of graph theory (05C90) Applications of Markov chains and discrete-time Markov processes on general state spaces (social mobility, learning theory, industrial processes, etc.) (60J20) Estimation in multivariate analysis (62H12) Image analysis in multivariate analysis (62H35) Signal theory (characterization, reconstruction, filtering, etc.) (94A12)

Abstract: Latent tree graphical models are widely used in computational biology, signal and image processing, and network tomography. Here we design a new efficient, estimation procedure for latent tree models, including Gaussian and discrete, reversible models, that significantly improves on previous sample requirement bounds. Our techniques are based on a new hidden state estimator which is robust to inaccuracies in estimated parameters. More precisely, we prove that latent tree models can be estimated with high probability in the so-called Kesten-Stigum regime with $O(lo{g}^{2}n)$ samples where $n$ is the number of nodes.

Recommendations

• scientific article; zbMATH DE number 5547949
• Incomplete graphical model inference via latent tree aggregation
• Learning latent tree graphical models
• On robust Gaussian graphical modeling
• Robust Bayesian graphical modeling using Dirichlet \(t\)-distributions
• Robust inference of trees
• Dynamic and robust Bayesian graphical models
• On estimation and inference in latent structure random graphs
• Hierarchical normalized completely random measures for robust graphical modeling
• Robust estimators for nondecomposable elliptical graphical models

Cited in

(8)

• Stable graphical model estimation with random forests for discrete, continuous, and mixed variables
• Sufficient condition for root reconstruction by parsimony on binary trees with general weights
• Phase transition on the convergence rate of parameter estimation under an Ornstein-Uhlenbeck diffusion on a tree
• Exact or approximate inference in graphical models: why the choice is dictated by the treewidth, and how variable elimination can be exploited
• Community detection and percolation of information in a geometric setting
• Non-linear log-Sobolev inequalities for the Potts semigroup and applications to reconstruction problems
• Identifiability in robust estimation of tree structured models
• Gaussian broadcast on grids

This page was built for publication: Robust Estimation of Latent Tree Graphical Models: Inferring Hidden States With Inexact Parameters

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q5346462)