LossAbsolute: Absolute loss for regression tasks.

In compboost: C++ Implementation of Component-Wise Boosting

Description

This loss can be used for regression with y \in \mathrm{R}.

Format

S4 object.

Details

Loss Function:

L(y, f(x)) = | y - f(x)|

Gradient:

\frac{δ}{δ f(x)}\ L(y, f(x)) = \mathrm{sign}( f(x) - y)

Initialization:

\hat{f}^{[0]}(x) = \mathrm{arg~min}_{c\in R}\ \frac{1}{n}∑\limits_{i=1}^n L(y^{(i)}, c) = \mathrm{median}(y)

Usage

LossAbsolute$new()
LossAbsolute$new(offset)

Arguments

offset [numeric(1)]

Numerical value which can be used to set a custom offset. If so, this value is returned instead of the loss optimal initialization.

Details

This class is a wrapper around the pure C++ implementation. To see the functionality of the C++ class visit https://schalkdaniel.github.io/compboost/cpp_man/html/classloss_1_1_absolute_loss.html.

Examples

# Create new loss object:
absolute.loss = LossAbsolute$new()
absolute.loss

compboost documentation built on May 2, 2019, 6:40 a.m.