bst: Gradient Boosting

The package contains HingeBoost for binary and multi-class classification, with unequal misclassification costs for binary case. Functional gradient descent algorithm to optimize the hinge loss. The algorithm can fit linear and nonlinear classifiers.

Version: 0.3-3
Depends: rpart, gbm
Published: 2013-09-12
Author: Zhu Wang
Maintainer: Zhu Wang <zwang at connecticutchildrens.org>
License: GPL-2 | GPL-3 [expanded from: GPL (≥ 2)]
NeedsCompilation: no
Materials: NEWS
In views: MachineLearning
CRAN checks: bst results

Downloads:

Reference manual: bst.pdf
Package source: bst_0.3-3.tar.gz
MacOS X binary: bst_0.3-3.tgz
Windows binary: bst_0.3-3.zip
Old sources: bst archive

Reverse dependencies:

Reverse suggests: fscaret