Berry-Esseen bounds for estimating undirected graphs

DOI10.1214/14-EJS928zbMATH Open1298.62089arXiv1309.6933OpenAlexW2081308366MaRDI QIDQ405339FDOQ405339

Authors: Mladen Kolar, Alessandro Rinaldo, Larry Wasserman 

Publication date: 5 September 2014

Published in: Electronic Journal of Statistics (Search for Journal in Brave)

Abstract: We consider the problem of providing nonparametric confidence guarantees for undirected graphs under weak assumptions. In particular, we do not assume sparsity, incoherence or Normality. We allow the dimension $D$ to increase with the sample size $n$. First, we prove lower bounds that show that if we want accurate inferences with low assumptions then there are limitations on the dimension as a function of sample size. When the dimension increases slowly with sample size, we show that methods based on Normal approximations and on the bootstrap lead to valid inferences and we provide Berry-Esseen bounds on the accuracy of the Normal approximation. When the dimension is large relative to sample size, accurate inferences for graphs under low assumptions are not possible. Instead we propose to estimate something less demanding than the entire partial correlation graph. In particular, we consider: cluster graphs, restricted partial correlation graphs and correlation graphs.

Full work available at URL: https://arxiv.org/abs/1309.6933

Recommendations

• The nonparanormal: semiparametric estimation of high dimensional undirected graphs
• Confidence intervals for high-dimensional inverse covariance estimation
• Estimation of Gaussian graphs by model selection
• Asymptotic normality and optimalities in estimation of large Gaussian graphical models
• Berry-Esseen bounds for generalized \(U\)-statistics

zbMATH Keywords

high-dimensional inferencegraphical models

Mathematics Subject Classification ID

Multivariate distribution of statistics (62H10) Nonparametric tolerance and confidence regions (62G15) Estimation in multivariate analysis (62H12)

Cites Work

• Gaussian graphical model estimation with false discovery rate control
• Title not available (Why is that?)
• Title not available (Why is that?)
• High-dimensional graphs and variable selection with the Lasso
• A well-conditioned estimator for large-dimensional covariance matrices
• Comparison and anti-concentration bounds for maxima of Gaussian random vectors
• Bootstrap and wild bootstrap for high dimensional linear models
• Model selection and estimation in the Gaussian graphical model
• High-dimensional covariance estimation by minimizing \(\ell _{1}\)-penalized log-determinant divergence
• Model selection for Gaussian concentration graphs
• Asymptotic behavior of likelihood methods for exponential families when the number of parameters tends to infinity
• Combinatorial methods in density estimation
• Normal approximation for nonlinear statistics using a concentration inequality approach
• A robust procedure for Gaussian graphical model search from microarray data with \(p\) larger than \(n\)
• PC algorithm for nonparanormal graphical models

Cited In (7)

• Simultaneous inference for pairwise graphical models with generalized score matching
• Bootstrapping max statistics in high dimensions: near-parametric rates under weak variance decay and application to functional and multinomial data
• Discrete Malliavin-Stein method: Berry-Esseen bounds for random graphs and percolation
• On a complete and sufficient statistic for the correlated Bernoulli random graph model
• Optimal-order bounds on the rate of convergence to normality in the multivariate delta method
• Post-regularization inference for time-varying nonparanormal graphical models
• A Berry-Esseen bound with applications to vertex degree counts in the Erdős-Rényi random graph

This page was built for publication: Berry-Esseen bounds for estimating undirected graphs

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q405339)