The SSE (Sum of Squared Errors) loss is a loss function to measure the quality of prediction of response values present in the node of each xgboost tree. More...

#include <sse_loss.hpp>

Public Member Functions
	SSELoss (const double alpha, const double lambda)

template<typename VecType >
VecType::elem_type	InitialPrediction (const VecType &values)
	Returns the initial predition for gradient boosting.

template<typename MatType , typename WeightVecType >
double	OutputLeafValue (const MatType &, const WeightVecType &)
	Returns the output value for the leaf in the tree.

double	Evaluate (const size_t begin, const size_t end)
	Calculates the gain from begin to end. More...

template<bool UseWeights, typename MatType , typename WeightVecType >
double	Evaluate (const MatType &input, const WeightVecType &)
	Calculates the gain of the node before splitting. More...

Detailed Description

The SSE (Sum of Squared Errors) loss is a loss function to measure the quality of prediction of response values present in the node of each xgboost tree.

It is also a good measure to compare the spread of two distributions. We will try to minimize this value while training.

Loss = 1 / 2 * (Observed - Predicted)^2

Member Function Documentation

◆ Evaluate() [1/2]

double mlpack::ensemble::SSELoss::Evaluate	(	const size_t	begin,
		const size_t	end
	)

inline

Calculates the gain from begin to end.

Parameters

begin	The begin index to calculate gain.
end	The end index to calculate gain.

◆ Evaluate() [2/2]

template<bool UseWeights, typename MatType , typename WeightVecType >

double mlpack::ensemble::SSELoss::Evaluate	(	const MatType &	input,
		const WeightVecType &
	)

inline

Calculates the gain of the node before splitting.

It also initializes the gradients and hessians used later for finding split. UseWeights and weights are ignored here. These are just to make the API consistent.

Parameters

input This is a 2D matrix. The first row stores the true observed values and the second row stores the prediction at the current step of boosting.

The documentation for this class was generated from the following file:

src/mlpack/methods/xgboost/loss_functions/sse_loss.hpp

Public Member Functions

Detailed Description

Member Function Documentation

◆ Evaluate() [1/2]

◆ Evaluate() [2/2]