arf: Adversarial Random Forests

Adversarial random forests (ARFs) recursively partition data into fully factorized leaves, where features are jointly independent. The procedure is iterative, with alternating rounds of generation and discrimination. Data becomes increasingly realistic at each round, until original and synthetic samples can no longer be reliably distinguished. This is useful for several unsupervised learning tasks, such as density estimation and data synthesis. Methods for both are implemented in this package. ARFs naturally handle unstructured data with mixed continuous and categorical covariates. They inherit many of the benefits of random forests, including speed, flexibility, and solid performance with default parameters. For details, see Watson et al. (2022) <doi:10.48550/arXiv.2205.09435>.

Version: 0.2.0
Imports: data.table, ranger, foreach, truncnorm
Suggests: ggplot2, doParallel, mlbench, knitr, rmarkdown, tibble, testthat (≥ 3.0.0)
Published: 2024-01-24
DOI: 10.32614/CRAN.package.arf
Author: Marvin N. Wright ORCID iD [aut, cre], David S. Watson ORCID iD [aut], Kristin Blesch ORCID iD [aut], Jan Kapar ORCID iD [aut]
Maintainer: Marvin N. Wright <cran at>
License: GPL (≥ 3)
NeedsCompilation: no
Materials: README NEWS
CRAN checks: arf results


Reference manual: arf.pdf
Vignettes: Density Estimation


Package source: arf_0.2.0.tar.gz
Windows binaries: r-devel:, r-release:, r-oldrel:
macOS binaries: r-release (arm64): arf_0.2.0.tgz, r-oldrel (arm64): arf_0.2.0.tgz, r-release (x86_64): arf_0.2.0.tgz, r-oldrel (x86_64): arf_0.2.0.tgz
Old sources: arf archive


Please use the canonical form to link to this page.