Shrinkage with shrunken shoulders: Gibbs sampling shrinkage model posteriors with guaranteed convergence rates

DOI10.1214/22-ba1308arXiv1911.02160MaRDI QIDQ6122024

Marc A. Suchard, Akihiko Nishimura

Publication date: 27 February 2024

Published in: Bayesian Analysis (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/1911.02160

zbMATH Keywords

Markov chain Monte Carlo; ergodicity; Bayesian inference; sparsity; generalized linear model

Mathematics Subject Classification ID

62J07: Ridge regression; shrinkage estimators (Lasso)

62F15: Bayesian inference

62-XX: Statistics

60J20: Applications of Markov chains and discrete-time Markov processes on general state spaces (social mobility, learning theory, industrial processes, etc.)

Cites Work

• Unnamed Item
• Unnamed Item
• Sparsity information and regularization in the horseshoe and other shrinkage priors
• Sparse Bayesian time-varying covariance estimation in many dimensions
• Overall objective priors
• Conditions for posterior contraction in the sparse normal means problem
• The Pólya-gamma Gibbs sampler for Bayesian logistic regression is uniformly ergodic
• General state space Markov chains and MCMC algorithms
• Honest exploration of intractable probability distributions via Markov chain Monte Carlo.
• Geometric ergodicity of Pólya-Gamma Gibbs sampler for Bayesian logistic regression with a flat prior
• On the use of Cauchy prior distributions for Bayesian logistic regression
• Asymptotic optimality of one-group shrinkage priors in sparse high-dimensional problems
• Honest confidence regions for nonparametric regression
• Lasso meets horseshoe: a survey
• Adaptive posterior contraction rates for the horseshoe
• Geometric ergodicity for Bayesian shrinkage models
• Inference with normal-gamma prior distributions in regression problems
• Markov Chains and De-initializing Processes
• The horseshoe estimator for sparse signals
• Markov Chains and Stochastic Stability
• The Bayesian Lasso
• Minorization Conditions and Convergence Rates for Markov Chain Monte Carlo
• The Bayesian Bridge
• Dynamic Shrinkage Processes
• Bayesian Inference for Logistic Models Using Pólya–Gamma Latent Variables
• The Graphical Horseshoe Estimator for Inverse Covariance Matrices
• Prior-Preconditioned Conjugate Gradient Method for Accelerated Gibbs Sampling in “Large n , Large p ” Bayesian Sparse Regression