Prior-Preconditioned Conjugate Gradient Method for Accelerated Gibbs Sampling in “Large n , Large p ” Bayesian Sparse Regression
From MaRDI portal
Publication:6144762
DOI10.1080/01621459.2022.2057859arXiv1810.12437MaRDI QIDQ6144762
Marc A. Suchard, Akihiko Nishimura
Publication date: 8 January 2024
Published in: Journal of the American Statistical Association (Search for Journal in Brave)
Full work available at URL: https://arxiv.org/abs/1810.12437
Markov chain Monte Carlo; sparse matrix; numerical linear algebra; variable selection; conjugate gradient; big data
62-XX: Statistics
Related Items
Cites Work
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Bayesian variable selection and estimation for group Lasso
- Matching methods for causal inference: a review and a look forward
- Asymptotic properties of Bayes risk for the horseshoe prior
- The formal definition of reference priors
- Fast model-fitting of Bayesian variable selection regression using the iterative complex factorization algorithm
- Principal component analysis.
- Lasso meets horseshoe: a survey
- Geometric ergodicity for Bayesian shrinkage models
- Penalized regression, standard errors, and Bayesian Lassos
- Direct Methods for Sparse Matrices
- Difference Filter Preconditioning for Large Covariance Matrices
- Numerical Methods for Large Eigenvalue Problems
- Efficient Sampling for Gaussian Linear Regression With Arbitrary Priors
- The horseshoe estimator for sparse signals
- From Potential Theory to Matrix Iterations in Six Steps
- Gaussian Markov Random Fields
- Iterative Krylov Methods for Large Linear Systems
- Practical Bayesian modeling and inference for massive spatial data sets on modest computing environments†
- A Simple Method for Estimating Interactions Between a Treatment and a Large Number of Covariates
- The Bayesian Bridge
- Dirichlet–Laplace Priors for Optimal Shrinkage
- Bayesian Inference for Logistic Models Using Pólya–Gamma Latent Variables
- Convergence Analysis of Krylov Subspace Iterations with Methods from Potential Theory
- The Lanczos and Conjugate Gradient Algorithms
- Methods of conjugate gradients for solving linear systems
