Sieve: Nonparametric Estimation by the Method of Sieves

Performs multivariate nonparametric regression/classification by the method of sieves (using orthogonal basis). The method is suitable for moderate high-dimensional features (dimension < 100). The l1-penalized sieve estimator, a nonparametric generalization of Lasso, is adaptive to the feature dimension with provable theoretical guarantees. We also include a nonparametric stochastic gradient descent estimator, Sieve-SGD, for online or large scale batch problems. Details of the methods can be found in: <doi:10.48550/arXiv.2206.02994> <doi:10.48550/arXiv.2104.00846><doi:10.48550/arXiv.2310.12140>.

Version:	2.1
Imports:	Rcpp, combinat, glmnet, methods, MASS
LinkingTo:	Rcpp, RcppArmadillo
Published:	2023-10-19
DOI:	10.32614/CRAN.package.Sieve
Author:	Tianyu Zhang
Maintainer:	Tianyu Zhang <tianyuz3 at andrew.cmu.edu>
License:	GPL-2
NeedsCompilation:	yes
Materials:	README
CRAN checks:	Sieve results

Documentation:

Reference manual:

Sieve.pdf

Downloads:

Package source:	Sieve_2.1.tar.gz
Windows binaries:	r-devel: Sieve_2.1.zip, r-release: Sieve_2.1.zip, r-oldrel: Sieve_2.1.zip
macOS binaries:	r-release (arm64): Sieve_2.1.tgz, r-oldrel (arm64): Sieve_2.1.tgz, r-release (x86_64): Sieve_2.1.tgz, r-oldrel (x86_64): Sieve_2.1.tgz
Old sources:	Sieve archive

Linking:

Please use the canonical form https://CRAN.R-project.org/package=Sieve to link to this page.