Thrill  0.1
Static Public Member Functions | List of all members
LeastSquaresGradient< Vector > Class Template Reference

Detailed Description

template<typename Vector>
class examples::stochastic_gradient_descent::LeastSquaresGradient< Vector >

simple implementation of a gradient computation class using a least squares cost function and a linear model (y = w*x)

Definition at line 86 of file stochastic_gradient_descent.hpp.

#include <stochastic_gradient_descent.hpp>

Static Public Member Functions

static GradientResult< Vector > Compute (const Vector &data, double label, const Vector &weights)
 

Member Function Documentation

◆ Compute()

static GradientResult<Vector> Compute ( const Vector &  data,
double  label,
const Vector &  weights 
)
inlinestatic

Definition at line 89 of file stochastic_gradient_descent.hpp.

References DataPoint< Vector >::data, Vector< D, Type >::dot(), examples::logistic_regression::gradient(), and DataPoint< Vector >::label.

Referenced by StochasticGradientDescent< Vector >::optimize().

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