SAM: Sparse Additive Modelling

Computationally efficient tools for high dimensional predictive modeling (regression and classification). SAM is short for sparse additive modeling, and adopts the computationally efficient basis spline technique. We solve the optimization problems by various computational algorithms including the block coordinate descent algorithm, fast iterative soft-thresholding algorithm, and newton method. The computation is further accelerated by warm-start and active-set tricks.

Version:	1.3
Depends:	R (≥ 2.14), splines
LinkingTo:	Rcpp, RcppEigen
Published:	2026-03-13
DOI:	10.32614/CRAN.package.SAM
Author:	Haoming Jiang [aut], Yukun Ma [aut], Han Liu [aut], Kathryn Roeder [aut], Xingguo Li [aut], Tuo Zhao [aut, cre]
Maintainer:	Tuo Zhao <tourzhao at gatech.edu>
License:	GPL-2
NeedsCompilation:	yes
Materials:	README, NEWS
CRAN checks:	SAM results

Documentation:

Reference manual:

SAM.html , SAM.pdf

Downloads:

Package source:	SAM_1.3.tar.gz
Windows binaries:	r-devel: SAM_1.3.zip, r-release: SAM_1.2.zip, r-oldrel: SAM_1.3.zip
macOS binaries:	r-release (arm64): SAM_1.3.tgz, r-oldrel (arm64): SAM_1.3.tgz, r-release (x86_64): SAM_1.3.tgz, r-oldrel (x86_64): SAM_1.3.tgz
Old sources:	SAM archive

Reverse dependencies:

Reverse imports:

DLL, GSelection, pgraph, varEst

Linking:

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