PIE: A Partially Interpretable Model with Black-Box Refinement

Implements a novel predictive model, Partially Interpretable Estimators (PIE), which jointly trains an interpretable model and a black-box model to achieve high predictive performance as well as partial model. See the paper, Wang, Yang, Li, and Wang (2021) <doi:10.48550/arXiv.2105.02410>.

Version:	1.0.0
Depends:	R (≥ 3.5.0), gglasso, xgboost
Imports:	splines, stats
Suggests:	knitr, rmarkdown
Published:	2025-01-27
Author:	Tong Wang [aut], Jingyi Yang [aut, cre], Yunyi Li [aut], Boxiang Wang [aut]
Maintainer:	Jingyi Yang <jy4057 at stern.nyu.edu>
License:	GPL-2
NeedsCompilation:	no
Citation:	PIE citation info
CRAN checks:	PIE results

Documentation:

Reference manual:	PIE.html , PIE.pdf
Vignettes:	Introduction to PIE – A Partially Interpretable Model with Black-box Refinement (source)

Downloads:

Package source:	PIE_1.0.0.tar.gz
Windows binaries:	r-devel: PIE_1.0.0.zip, r-release: PIE_1.0.0.zip, r-oldrel: PIE_1.0.0.zip
macOS binaries:	r-release (arm64): PIE_1.0.0.tgz, r-oldrel (arm64): PIE_1.0.0.tgz, r-release (x86_64): PIE_1.0.0.tgz, r-oldrel (x86_64): PIE_1.0.0.tgz

Linking:

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