Geometric ergodicity of Gibbs samplers for the horseshoe and its regularized variants

DOI10.1214/21-EJS1932zbMath1498.62138arXiv2101.00366OpenAlexW3118918056MaRDI QIDQ2136599

Suman Bhattacharya, Kshitij Khare, Subhadip Pal

Publication date: 11 May 2022

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

Full work available at URL: https://arxiv.org/abs/2101.00366

zbMATH Keywords

Markov chain Monte Carlogeometric ergodicityhigh-dimensional linear regressionhorseshoe prior

Mathematics Subject Classification ID

Computational methods in Markov chains (60J22) Ridge regression; shrinkage estimators (Lasso) (62J07) Linear regression; mixed models (62J05) Bayesian inference (62F15) Monte Carlo methods (65C05)

Related Items

Horseshoe Priors for Edge-Preserving Linear Bayesian Inversion

Cites Work

• Unnamed Item
• Sparsity information and regularization in the horseshoe and other shrinkage priors
• Geometric ergodicity of the Bayesian Lasso
• Markov chains and stochastic stability
• Gibbs sampling, exponential families and orthogonal polynomials
• Inverses of \(2\times 2\) block matrices
• On the geometric ergodicity of Hamiltonian Monte Carlo
• Batch means and spectral variance estimators in Markov chain Monte Carlo
• Geometric ergodicity for Bayesian shrinkage models
• On the half-Cauchy prior for a global scale parameter
• Markov Chains and De-initializing Processes
• Fixed-Width Output Analysis for Markov Chain Monte Carlo
• The horseshoe estimator for sparse signals
• Minorization Conditions and Convergence Rates for Markov Chain Monte Carlo
• Convergence of Conditional Metropolis-Hastings Samplers
• Dirichlet–Laplace Priors for Optimal Shrinkage
• Trace Class Markov Chains for Bayesian Inference with Generalized Double Pareto Shrinkage Priors