Optimal classification in sparse Gaussian graphic model

DOI10.1214/13-AOS1163zbMath1294.62061arXiv1212.5332OpenAlexW3100712906MaRDI QIDQ2438761

Yanyan Li

Publication date: 6 March 2014

Published in: The Annals of Statistics (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/1212.5332

zbMATH Keywords

chromatic numberphase diagramprecision matrixsparse graphFisher's LDAFisher's separationrare and weak model

Mathematics Subject Classification ID

Nonparametric estimation (62G05) Statistics of extreme values; tail inference (62G32)

Related Items

Integrative genetic risk prediction using non‐parametric empirical Bayes classification, Scalable inference for high-dimensional precision matrix, Adaptive threshold-based classification of sparse high-dimensional data, Large-scale inference with block structure, High-dimensional sparse MANOVA, Estimating the amount of sparsity in two-point mixture models, Optimal classification in sparse Gaussian graphic model, Bayesian sparse graphical models for classification with application to protein expression data, Halfspace depths for scatter, concentration and shape matrices, Detecting rare and faint signals via thresholding maximum likelihood estimators, Diagonally Dominant Principal Component Analysis, Unnamed Item, Dynamic linear discriminant analysis in high dimensional space, Robust Variable and Interaction Selection for Logistic Regression and General Index Models, Reproducible learning in large-scale graphical models, Innovated interaction screening for high-dimensional nonlinear classification, Higher criticism for large-scale inference, especially for rare and weak effects

Uses Software

• glasso

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Innovated higher criticism for detecting sparse signals in correlated noise
• Sparse inverse covariance estimation with the graphical lasso
• UPS delivers optimal phase diagram in high-dimensional variable selection
• Sparse linear discriminant analysis by thresholding for high dimensional data
• Global testing under sparse alternatives: ANOVA, multiple comparisons and the higher criticism
• High-dimensional classification using features annealed independence rules
• Minimax risk over \(l_ p\)-balls for \(l_ q\)-error
• Some problems of hypothesis testing leading to infinitely divisible distributions
• Some theory for Fisher's linear discriminant function, `naive Bayes', and some alternatives when there are many more variables than observations
• Minimax detection of a signal for \(l^ n\)-balls.
• Higher criticism for detecting sparse heterogeneous mixtures.
• High-dimensional covariance estimation by minimizing \(\ell _{1}\)-penalized log-determinant divergence
• Optimal classification in sparse Gaussian graphic model
• Tests alternative to higher criticism for high-dimensional means under sparsity and column-wise dependence
• Goodness-of-fit tests via phi-divergences
• The Dantzig selector: statistical estimation when \(p\) is much larger than \(n\). (With discussions and rejoinder).
• Estimation and confidence sets for sparse normal mixtures
• Regularized estimation of large covariance matrices
• Higher criticism thresholding: Optimal feature selection when useful features are rare and weak
• Impossibility of successful classification when useful features are rare and weak
• A Constrainedℓ₁Minimization Approach to Sparse Precision Matrix Estimation
• A Direct Estimation Approach to Sparse Linear Discriminant Analysis
• Classification of sparse high-dimensional vectors
• Feature selection by higher criticism thresholding achieves the optimal phase diagram
• Theoretical Measures of Relative Performance of Classifiers for High Dimensional Data with Small Sample Sizes
• Variable Selection via Nonconcave Penalized Likelihood and its Oracle Properties
• Empirical Bayes Estimates for Large-Scale Prediction Problems
• Random forests