org.apache.flink.ml.optimization

Interface LossFunction

All Superinterfaces:

Serializable

All Known Implementing Classes:

GenericLossFunction

public interface LossFunction
extends scala.Serializable

Abstract class that implements some of the functionality for common loss functions

A loss function determines the loss term $L(w) of the objective function $f(w) = L(w) + \lambda R(w)$ for prediction tasks, the other being regularization, $R(w)$.

The regularization is specific to the used optimization algorithm and, thus, implemented there.

We currently only support differentiable loss functions, in the future this class could be changed to DiffLossFunction in order to support other types, such as absolute loss.

Method Summary

Modifier and Type	Method and Description
WeightVector	gradient(LabeledVector dataPoint, WeightVector weightVector) Calculates the gradient of the loss function given a data point and weight vector
double	loss(LabeledVector dataPoint, WeightVector weightVector) Calculates the loss given the prediction and label value
scala.Tuple2<Object,WeightVector>	lossGradient(LabeledVector dataPoint, WeightVector weightVector) Calculates the gradient as well as the loss given a data point and the weight vector

Method Detail

loss

double loss(LabeledVector dataPoint,
            WeightVector weightVector)

Calculates the loss given the prediction and label value

Parameters:

dataPoint -

weightVector -

Returns:

gradient

WeightVector gradient(LabeledVector dataPoint,
                      WeightVector weightVector)

Calculates the gradient of the loss function given a data point and weight vector

Parameters:

dataPoint -

weightVector -

Returns:

lossGradient

scala.Tuple2<Object,WeightVector> lossGradient(LabeledVector dataPoint,
                                               WeightVector weightVector)

Calculates the gradient as well as the loss given a data point and the weight vector

Parameters:

dataPoint -

weightVector -

Returns: