Sparse estimation of large covariance matrices via a nested Lasso penalty
From MaRDI portal
Publication:2482977
Abstract: The paper proposes a new covariance estimator for large covariance matrices when the variables have a natural ordering. Using the Cholesky decomposition of the inverse, we impose a banded structure on the Cholesky factor, and select the bandwidth adaptively for each row of the Cholesky factor, using a novel penalty we call nested Lasso. This structure has more flexibility than regular banding, but, unlike regular Lasso applied to the entries of the Cholesky factor, results in a sparse estimator for the inverse of the covariance matrix. An iterative algorithm for solving the optimization problem is developed. The estimator is compared to a number of other covariance estimators and is shown to do best, both in simulations and on a real data example. Simulations show that the margin by which the estimator outperforms its competitors tends to increase with dimension.
Recommendations
- A Cholesky-based estimation for large-dimensional covariance matrices
- Covariance matrix selection and estimation via penalised normal likelihood
- Regularized estimation of large covariance matrices
- Adaptive estimation of covariance matrices via Cholesky decomposition
- Computationally efficient banding of large covariance matrices for ordered data and connections to banding the inverse Cholesky factor
Cites work
- A well-conditioned estimator for large-dimensional covariance matrices
- Class prediction by nearest shrunken centroids, with applications to DNA microarrays.
- Covariance matrix selection and estimation via penalised normal likelihood
- Efficient estimation of covariance selection models
- Empirical Bayes estimation of the multivariate normal covariance matrix
- Estimation of a covariance matrix under Stein's loss
- Estimation of high-dimensional prior and posterior covariance matrices in Kalman filter vari\-ants
- High dimensional covariance matrix estimation using a factor model
- scientific article; zbMATH DE number 3136275 (Why is no real title available?)
- scientific article; zbMATH DE number 3673370 (Why is no real title available?)
- scientific article; zbMATH DE number 845714 (Why is no real title available?)
- Joint mean-covariance models with applications to longitudinal data: unconstrained parameterisation
- Model selection and estimation in the Gaussian graphical model
- Nonparametric Estimation of Covariance Structure in Longitudinal Data
- Nonparametric estimation of large covariance matrices of longitudinal data
- On consistency and sparsity for principal components analysis in high dimensions
- On the distribution of the largest eigenvalue in principal components analysis
- Parsimonious Covariance Matrix Estimation for Longitudinal Data
- Pathwise coordinate optimization
- Regularized estimation of large covariance matrices
- Ridge Regression: Biased Estimation for Nonorthogonal Problems
- Some theory for Fisher's linear discriminant function, `naive Bayes', and some alternatives when there are many more variables than observations
- Sparsity and Smoothness Via the Fused Lasso
- The elements of statistical learning. Data mining, inference, and prediction
- Variable Selection via Nonconcave Penalized Likelihood and its Oracle Properties
Cited in
(73)- Covariance regularization by thresholding
- Sparsistency and rates of convergence in large covariance matrix estimation
- The Generalized Ridge Estimator of the Inverse Covariance Matrix
- Estimating large correlation matrices for international migration
- High dimensional covariance matrix estimation by penalizing the matrix-logarithm transformed likelihood
- Lasso, fractional norm and structured sparse estimation using a Hadamard product parametrization
- A constrained \(\ell1\) minimization approach for estimating multiple sparse Gaussian or nonparanormal graphical models
- Hierarchical sparse modeling: a choice of two group Lasso formulations
- A simple numerical method based simultaneous stochastic perturbation for estimation of high dimensional matrices
- Sparse permutation invariant covariance estimation
- High dimensional sparse covariance estimation via directed acyclic graphs
- Penalized model-based clustering with unconstrained covariance matrices
- Nonparametric estimation of covariance functions by model selection
- Adaptive estimation of covariance matrices via Cholesky decomposition
- Heterogeneous tail generalized COMFORT modeling via Cholesky decomposition
- A scalable sparse Cholesky based approach for learning high-dimensional covariance matrices in ordered data
- Estimation and optimal structure selection of high-dimensional Toeplitz covariance matrix
- Parsimony inducing priors for large scale state-space models
- Minimax estimation of large precision matrices with bandable Cholesky factor
- Network exploration via the adaptive LASSO and SCAD penalties
- Regularized estimation of precision matrix for high-dimensional multivariate longitudinal data
- Ultrahigh dimensional precision matrix estimation via refitted cross validation
- Bayesian estimation of large precision matrix based on Cholesky decomposition
- Multilevel Gaussian graphical model for multilevel networks
- New sequence spaces and function spaces on interval \([0, 1]\)
- Bayesian sparse covariance decomposition with a graphical structure
- Robust sparse precision matrix estimation for high-dimensional compositional data
- Regularized parameter estimation in high-dimensional Gaussian mixture models
- Forward adaptive banding for estimating large covariance matrices
- Estimating spatial covariance using penalised likelihood with weightedL1penalty
- Detecting the dimensionality for principal components model
- Robust estimation in joint mean-covariance regression model for longitudinal data
- Estimating summary statistics in the spike-train space
- Adjusting for high-dimensional covariates in sparse precision matrix estimation by _1-penalization
- Covariance estimation: the GLM and regularization perspectives
- Informative estimation and selection of correlation structure for longitudinal data
- Sparse estimation of multivariate Poisson log‐normal models from count data
- Robust estimation of sparse precision matrix using adaptive weighted graphical lasso approach
- A Cholesky-based estimation for large-dimensional covariance matrices
- Individual-specific, sparse inverse covariance estimation in generalized estimating equations
- Rates of convergence in conditional covariance matrix with nonparametric entries estimation
- Graph-guided banding of the covariance matrix
- Penalized least squares estimation with weakly dependent data
- A DC programming approach for sparse estimation of a covariance matrix
- Learning local dependence in ordered data
- Group Lasso estimation of high-dimensional covariance matrices
- Covariance matrix selection and estimation via penalised normal likelihood
- Correlation structure selection for longitudinal data with diverging cluster size
- Nonparametric modeling of longitudinal covariance structure in functional mapping of quantitative trait loci
- Covariance estimation via fiducial inference
- Cholesky-based model averaging for covariance matrix estimation
- A Stratified Penalized Kernel Method for Semiparametric Variable Labeling and Estimation of Multi-Output Time-Varying Coefficient Models for Nonstationary Time Series
- Adaptive Tests for Bandedness of High-dimensional Covariance Matrices
- Estimation of banded time-varying precision matrix based on SCAD and group Lasso
- Structural factor equation models for causal network construction via directed acyclic mixed graphs
- Bayesian nonstationary and nonparametric covariance estimation for large spatial data (with discussion)
- An adjoint-free four-dimensional variational data assimilation method via a modified Cholesky decomposition and an iterative Woodbury matrix formula
- The Bayesian nested Lasso for mixed frequency regression models
- A cautionary note on generalized linear models for covariance of unbalanced longitudinal data
- Bayesian sparse graphical models and their mixtures
- Sparse precision matrix estimation under lower polynomial moment assumption
- Testing for practically significant dependencies in high dimensions via bootstrapping maxima of U-statistics
- A new approach for ultrahigh dimensional precision matrix estimation
- Trade-off between predictive performance and FDR control for high-dimensional Gaussian model selection
- High-dimensional covariance estimation for Gaussian directed acyclic graph models with given order
- Nonparametric covariance estimation with shrinkage toward stationary models
- Bandwidth selection for large covariance and precision matrices
- Non-boundary covariance matrix estimation in generalized linear mixed effects models using data augmentation priors
- Estimation of the error structure in multivariate response linear regression models
- Test for bandedness of high-dimensional covariance matrices and bandwidth estimation
- Joint robust variable selection of mean and covariance model via shrinkage methods
- Improved multivariate normal mean estimation with unknown covariance when \(p\) is greater than \(n\)
- Estimation of covariance matrix via the sparse Cholesky factor with lasso
This page was built for publication: Sparse estimation of large covariance matrices via a nested Lasso penalty
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2482977)
