Information-Theoretic Limits of Selecting Binary Graphical Models in High Dimensions

DOI10.1109/TIT.2012.2191659zbMath1365.62212OpenAlexW2108829665WikidataQ105584791 ScholiaQ105584791MaRDI QIDQ5271791

Narayana P. Santhanam, Martin J. Wainwright

Publication date: 12 July 2017

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

Full work available at URL: https://doi.org/10.1109/tit.2012.2191659

Mathematics Subject Classification ID

Random fields; image analysis (62M40) Nonparametric estimation (62G05) Applications of graph theory (05C90) Information theory (general) (94A15) Contingency tables (62H17)

Related Items

Efficient learning of discrete graphical models*, Lower bounds for testing graphical models: colorings and antiferromagnetic Ising models, A note on concentration for polynomials in the Ising model, Ising model selection using ℓ ₁-regularized linear regression: a statistical mechanics analysis*, An expectation maximization algorithm for high-dimensional model selection for the Ising model with misclassified states*, Region selection in Markov random fields: Gaussian case, The minimax learning rates of normal and Ising undirected graphical models, Chernoff information between Gaussian trees, Learning a tree-structured Ising model in order to make predictions, Structure recovery for partially observed discrete Markov random fields on graphs under not necessarily positive distributions, Certifiably optimal sparse inverse covariance estimation, Structure estimation for discrete graphical models: generalized covariance matrices and their inverses, Combinatorial inference for graphical models, Statistical mechanics of the inverse Ising problem and the optimal objective function, Structure learning in inverse Ising problems using ℓ ₂-regularized linear estimator, On testing for parameters in Ising models, Property testing in high-dimensional Ising models, Large deviations of convex polyominoes, Statistical limits of sparse mixture detection, Learning performance in inverse Ising problems with sparse teacher couplings, Unnamed Item, High-dimensional Ising model selection with Bayesian information criteria, Unnamed Item