coef.parboost

object

Optionally a subset of base learners to evaluate as an
integer or character vector.

which

a character specifying how to aggregate
predictions or coefficients of single base learners. The default
returns the prediction or coefficient for the final number of
boosting iterations. <code>"cumsum"</code> returns a matrix with the
predictions for all iterations simultaneously (in
columns). <code>"none"</code> returns a list with matrices where the
<em>j</em>th columns of the respective matrix contains the
predictions of the base learner of the <em>j</em>th boosting
iteration (and zero if the base learner is not selected in this
iteration).

aggregate


Extract coefficients from base learners that have a notion of coefficients


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.

coef.parboost: Print coefficients for base learners with a notion of coefficients

Description

Usage

Arguments

Value

Details

References