boost_control {mboost}R Documentation

Control Hyper-parameters for Boosting Algorithms

Description

Definition of the initial number of boosting iterations, step size and other hyper-parameters for boosting algorithms.

Usage

boost_control(mstop = 100, nu = 0.1, constraint = FALSE,
              risk = c("inbag", "oobag", "none"),
              savedata = TRUE, center = FALSE, trace = FALSE,
              save_ensembless=TRUE)

Arguments

mstop an integer giving the number of initial boosting iterations.
nu a double (between 0 and 1) defining the step size or shrinkage parameter.
constraint a logical indicating whether the working responses should be restricted to (-1, +1).
risk a character indicating how the empirical risk should be computed for each boosting iteration. inbag leads to risks computed for the learning sample (i.e., all non-zero weights), oobag to risks based on the out-of-bag (all observations with zero weights) and none to no risk computations at all.
savedata a logical, should the data be saved in the returned object?
center a logical indicating if the numerical covariates should be mean centered before fitting. Only implemented for glmboost. In gamboost and blackboost centering is not needed.
trace a logical triggering printout of status information during the fitting process.
save_ensembless a logical indicating if the list of baselearners should be saved and returned. This list is generally needed but can be suppressed to reduce memory usage (not recommended).

Details

Objects returned by this function specify hyper-parameters of the boosting algorithms implemented in glmboost, gamboost and blackboost (via the control argument).

Value

An object of class boost_control, a list.


[Package mboost version 1.1-0 Index]