Implements variational Bayesian algorithms to perform scalable variable selection for sparse, high-dimensional linear and logistic regression models. Features include a novel prioritized updating scheme, which uses a preliminary estimator of the variational means during initialization to generate an updating order prioritizing large, more relevant, coefficients. Sparsity is induced via spike-and-slab priors with either Laplace or Gaussian slabs. By default, the heavier-tailed Laplace density is used. Formal derivations of the algorithms and asymptotic consistency results may be found in Kolyan Ray and Botond Szabo (JASA 2020) and Kolyan Ray, Botond Szabo, and Gabriel Clara (NeurIPS 2020).
Version: | 0.1.1 |
Imports: | Rcpp (≥ 1.0.5), selectiveInference (≥ 1.2.5), glmnet (≥ 4.0-2), stats |
LinkingTo: | Rcpp, RcppArmadillo, RcppEnsmallen |
Published: | 2025-01-24 |
DOI: | 10.32614/CRAN.package.sparsevb |
Author: | Gabriel Clara [aut, cre], Botond Szabo [aut], Kolyan Ray [aut] |
Maintainer: | Gabriel Clara <gabriel.j.clara at gmail.com> |
BugReports: | https://gitlab.com/gclara/varpack/-/issues |
License: | GPL (≥ 3) |
NeedsCompilation: | yes |
CRAN checks: | sparsevb results |
Reference manual: | sparsevb.pdf |
Package source: | sparsevb_0.1.1.tar.gz |
Windows binaries: | r-devel: sparsevb_0.1.1.zip, r-release: sparsevb_0.1.1.zip, r-oldrel: sparsevb_0.1.1.zip |
macOS binaries: | r-devel (arm64): sparsevb_0.1.1.tgz, r-release (arm64): sparsevb_0.1.1.tgz, r-oldrel (arm64): sparsevb_0.1.1.tgz, r-devel (x86_64): sparsevb_0.1.1.tgz, r-release (x86_64): sparsevb_0.1.1.tgz, r-oldrel (x86_64): sparsevb_0.1.1.tgz |
Old sources: | sparsevb archive |
Please use the canonical form https://CRAN.R-project.org/package=sparsevb to link to this page.
mirror server hosted at Truenetwork, Russian Federation.