hal9001: The Scalable Highly Adaptive Lasso

A scalable implementation of the highly adaptive lasso algorithm, including routines for constructing sparse matrices of basis functions of the observed data, as well as a custom implementation of Lasso regression tailored to enhance efficiency when the matrix of predictors is composed exclusively of indicator functions. For ease of use and increased flexibility, the Lasso fitting routines invoke code from the 'glmnet' package by default. The highly adaptive lasso was first formulated and described by MJ van der Laan (2017) <doi:10.1515/ijb-2015-0097>, with practical demonstrations of its performance given by Benkeser and van der Laan (2016) <doi:10.1109/DSAA.2016.93>.

Version: 0.2.5
Depends: R (≥ 3.1.0), Rcpp
Imports: Matrix, stats, utils, methods, assertthat, origami (≥ 0.8.1), glmnet
LinkingTo: Rcpp, RcppEigen
Suggests: testthat, knitr, rmarkdown, microbenchmark, future, ggplot2, dplyr, tidyr, stringr, survival, data.table, SuperLearner
Published: 2020-03-05
Author: Jeremy Coyle ORCID iD [aut, cre], Nima Hejazi ORCID iD [aut], David Benkeser ORCID iD [ctb], Oleg Sofrygin [ctb], Weixin Cai ORCID iD [ctb], Mark van der Laan ORCID iD [aut, cph, ths]
Maintainer: Jeremy Coyle <jeremyrcoyle at gmail.com>
BugReports: https://github.com/tlverse/hal9001/issues
License: GPL-3
URL: https://github.com/tlverse/hal9001
NeedsCompilation: yes
Citation: hal9001 citation info
Materials: README NEWS
CRAN checks: hal9001 results

Downloads:

Reference manual: hal9001.pdf
Vignettes: Introduction to the HAL estimator
Package source: hal9001_0.2.5.tar.gz
Windows binaries: r-devel: hal9001_0.2.5.zip, r-devel-gcc8: hal9001_0.2.5.zip, r-release: hal9001_0.2.5.zip, r-oldrel: hal9001_0.2.5.zip
OS X binaries: r-release: hal9001_0.2.5.tgz, r-oldrel: hal9001_0.2.5.tgz

Reverse dependencies:

Reverse imports: haldensify

Linking:

Please use the canonical form https://CRAN.R-project.org/package=hal9001 to link to this page.