Distributed gradient boosting based on the mboost package. The parboost package is designed to scale up component-wise functional gradient boosting in a distributed memory environment by splitting the observations into disjoint subsets, or alternatively using bootstrap samples (bagging). Each cluster node then fits a boosting model to its subset of the data. These boosting models are combined in an ensemble, either with equal weights, or by fitting a (penalized) regression model on the predictions of the individual models on the complete data.
Version: | 0.1.4 |
Depends: | R (≥ 3.0.1), parallel, mboost, party, iterators |
Imports: | plyr, caret, glmnet, doParallel |
Published: | 2015-05-04 |
Author: | Ronert Obst |
Maintainer: | Ronert Obst <ronert.obst at gmail.com> |
License: | GPL-2 |
NeedsCompilation: | no |
Citation: | parboost citation info |
Materials: | README NEWS |
CRAN checks: | parboost results |
Reference manual: | parboost.pdf |
Package source: | parboost_0.1.4.tar.gz |
Windows binaries: | r-devel: parboost_0.1.4.zip, r-release: parboost_0.1.4.zip, r-oldrel: parboost_0.1.4.zip |
OS X El Capitan binaries: | r-release: parboost_0.1.4.tgz |
OS X Mavericks binaries: | r-oldrel: parboost_0.1.4.tgz |
Old sources: | parboost archive |
Please use the canonical form https://CRAN.R-project.org/package=parboost to link to this page.