irboost: Iteratively Reweighted Boosting for Robust Analysis

Fit a predictive model using iteratively reweighted boosting (IRBoost) to minimize robust loss functions within the CC-family (concave-convex). This constitutes an application of iteratively reweighted convex optimization (IRCO), where convex optimization is performed using the functional descent boosting algorithm. IRBoost assigns weights to facilitate outlier identification. Applications include robust generalized linear models and robust accelerated failure time models. Wang (2021) <doi:10.48550/arXiv.2101.07718>.

Version: 0.1-1.5
Depends: R (≥ 3.5.0)
Imports: mpath (≥ 0.4-2.21), xgboost
Suggests: R.rsp, DiagrammeR, survival, Hmisc
Published: 2024-04-18
DOI: 10.32614/CRAN.package.irboost
Author: Zhu Wang ORCID iD [aut, cre]
Maintainer: Zhu Wang <zhuwang at gmail.com>
License: GPL (≥ 3)
NeedsCompilation: no
Citation: irboost citation info
Materials: README NEWS
CRAN checks: irboost results

Documentation:

Reference manual: irboost.pdf
Vignettes: An Introduction to irboost

Downloads:

Package source: irboost_0.1-1.5.tar.gz
Windows binaries: r-devel: irboost_0.1-1.5.zip, r-release: irboost_0.1-1.5.zip, r-oldrel: irboost_0.1-1.5.zip
macOS binaries: r-release (arm64): irboost_0.1-1.5.tgz, r-oldrel (arm64): irboost_0.1-1.5.tgz, r-release (x86_64): irboost_0.1-1.5.tgz, r-oldrel (x86_64): irboost_0.1-1.5.tgz
Old sources: irboost archive

Linking:

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