Performs Wasserstein projections from the predictive distributions of any model into the space of predictive distributions of linear models. We utilize L1 penalties to also reduce the complexity of the model space. This package employs the methods as described in Dunipace, Eric and Lorenzo Trippa (2020) <doi:10.48550/arXiv.2012.09999>.
Version: |
0.2.1 |
Depends: |
R (≥ 4.0) |
Imports: |
ggplot2, ggsci, ggridges, glmnet, oem, Rcpp, rlang, ROI, ROI.plugin.ecos, ROI.plugin.lpsolve, Matrix, rqPen, quantreg, doParallel, foreach, doRNG, dplyr, stats, magrittr, methods, slam, lifecycle |
LinkingTo: |
BH, Rcpp (≥ 1.0.0), RcppEigen (≥ 0.3.3.4.0), RcppProgress, RcppCGAL, RSpectra |
Suggests: |
testthat (≥ 2.1.0), transport, Rmosek, spelling, ECOSolveR |
Published: |
2024-02-02 |
DOI: |
10.32614/CRAN.package.WpProj |
Author: |
Eric Dunipace
[aut, cre],
Clemens Schmid
[ctb] (ETA progres bar is adapted from their code),
Espen Bernton [ctb] ('Hilbert Sort' adapted from their code),
Mathieu Gerber [ctb] ('Hilbert Sort' adapted from their code),
Pierre Jacob [ctb] ('Hilbert Sort' adapted from their code),
Bin Dai [ctb] (W2 projections adapted from their 'OEM' code),
Jared Huling
[ctb] (W2 projections adapted from their 'OEM' code),
Yixuan Qiu [ctb] (W2 projections adapted from their 'OEM' code),
Dominic Schuhmacher [ctb] ('Shortsimplex 'optimal transport method
adapted from their code),
Nicolas Bonneel [ctb] ('Network Simplex' algorithm adapted from their
code) |
Maintainer: |
Eric Dunipace <edunipace at mail.harvard.edu> |
BugReports: |
https://github.com/ericdunipace/WpProj/issues |
License: |
GPL (== 3.0) |
URL: |
https://github.com/ericdunipace/WpProj |
NeedsCompilation: |
yes |
Language: |
en-US |
Materials: |
README NEWS |
CRAN checks: |
WpProj results [issues need fixing before 2024-10-21] |