⚠️There's a newer version (0.3-24) of this package.Take me there.

bst (version 0.3-17)

Gradient Boosting

Description

Functional gradient descent algorithm for a variety of convex and non-convex loss functions, for both classical and robust regression and classification problems. See Wang (2011) , Wang (2012) , Wang (2018) , Wang (2018) .

Copy Link

Version

Install

install.packages('bst')

Monthly Downloads

3,759

Version

0.3-17

License

GPL (>= 2)

Maintainer

Zhu Wang

Last Published

February 27th, 2019

Functions in bst (0.3-17)

cv.mada

Cross-Validation for one-vs-all AdaBoost with multi-class problem

cv.mbst

Cross-Validation for Multi-class Boosting

cv.rbst

Cross-Validation for Nonconvex Loss Boosting

cv.rmbst

Cross-Validation for Nonconvex Multi-class Loss Boosting

bfunc

Compute upper bound of second derivative of loss

loss

Internal Function

bst

Boosting for Classification and Regression

bst.sel

Function to select number of predictors

nsel

Find Number of Variables In Multi-class Boosting Iterations

rbst

Robust Boosting for Robust Loss Functions

mada

Multi-class AdaBoost

bst_control

Control Parameters for Boosting

mbst

Boosting for Multi-Classification

cv.bst

Cross-Validation for Boosting

rbstpath

Robust Boosting Path for Nonconvex Loss Functions

evalerr

Compute prediction errors

ex1data

Generating Three-class Data with 50 Predictors

rmbst

Robust Boosting for Multi-class Robust Loss Functions

cv.mhingebst

Cross-Validation for Multi-class Hinge Boosting

cv.mhingeova

Cross-Validation for one-vs-all HingeBoost with multi-class problem

mhingebst

Boosting for Multi-class Classification

mhingeova

Multi-class HingeBoost