Prediction risk for the horseshoe regression

zbMath1489.62196arXiv1605.04796MaRDI QIDQ5381133

Jyotishka Datta, Anindya Bhadra, Yunfan Li, Brandon T. Willard, Nicholas G. Polson

Publication date: 7 June 2019

Full work available at URL: https://arxiv.org/abs/1605.04796

zbMATH Keywords

principal componentsStein's unbiased risk estimateshrinkage regressionglobal-local priors

Mathematics Subject Classification ID

Ridge regression; shrinkage estimators (Lasso) (62J07) Classification and discrimination; cluster analysis (statistical aspects) (62H30) Linear regression; mixed models (62J05) Bayesian inference (62F15)

Related Items (8)

Unnamed Item ⋮ Horseshoe Regularisation for Machine Learning in Complex and Deep Models¹ ⋮ Nearly optimal Bayesian shrinkage for high-dimensional regression ⋮ SURE-tuned bridge regression ⋮ Global-local mixtures: a unifying framework ⋮ Joint mean-covariance estimation via the horseshoe ⋮ The horseshoe-like regularization for feature subset selection ⋮ Lasso meets horseshoe: a survey

Uses Software

• ElemStatLearn
• sparsenet

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Nearly unbiased variable selection under minimax concave penalty
• Conditions for posterior contraction in the sparse normal means problem
• Degrees of freedom in lasso problems
• Asymptotically minimax empirical Bayes estimation of a sparse normal mean vector
• The horseshoe estimator: posterior concentration around nearly black vectors
• Asymptotic properties of Bayes risk of a general class of shrinkage priors in multiple hypothesis testing under sparsity
• Bayesian linear regression with sparse priors
• Smoothing noisy data with spline functions: Estimating the correct degree of smoothing by the method of generalized cross-validation
• The horseshoe+ estimator of ultra-sparse signals
• High-dimensional asymptotics of prediction: ridge regression and classification
• The risk inflation criterion for multiple regression
• Improved minimax predictive densities under Kullback-Leibler loss
• On the half-Cauchy prior for a global scale parameter
• Inference with normal-gamma prior distributions in regression problems
• Variance estimation in high-dimensional linear models
• SparseNet: Coordinate Descent With Nonconvex Penalties
• Estimating the Error Rate of a Prediction Rule: Improvement on Cross-Validation
• The horseshoe estimator for sparse signals
• Limit expressions for the risk of james‐stein estimators
• Normal Variance-Mean Mixtures and z Distributions
• Approximate non-Gaussian filtering with linear state and observation relations
• Prediction Via Orthogonalized Model Mixing
• Variable Selection via Nonconcave Penalized Likelihood and its Oracle Properties
• Sparse Partial Least Squares Regression for Simultaneous Dimension Reduction and Variable Selection
• The Spike-and-Slab LASSO
• A Statistical View of Some Chemometrics Regression Tools
• Generalized double Pareto shrinkage
• EMVS: The EM Approach to Bayesian Variable Selection
• Minimax Rates of Estimation for High-Dimensional Linear Regression Over $\ell_q$-Balls
• Dirichlet–Laplace Priors for Optimal Shrinkage
• Default Bayesian analysis with global-local shrinkage priors
• Bayesian prediction with adaptive ridge estimators
• Ridge Regression: Biased Estimation for Nonorthogonal Problems
• Some Comments on C P
• Local Shrinkage Rules, Lévy Processes and Regularized Regression
• The Estimation of Prediction Error
• A new look at the statistical model identification

This page was built for publication: Prediction risk for the horseshoe regression