de.jungblut.online.regularization

Interface WeightUpdater

All Known Implementing Classes:

AdaptiveFTRLRegularizer, GradientDescentUpdater, L1Regularizer, L2Regularizer

public interface WeightUpdater

Method Summary

Modifier and Type	Method and Description
de.jungblut.math.minimize.CostGradientTuple	computeGradient(de.jungblut.math.DoubleVector theta, de.jungblut.math.DoubleVector gradient, double learningRate, long iteration, double lambda, double cost) Computes the gradient.
CostWeightTuple	computeNewWeights(de.jungblut.math.DoubleVector theta, de.jungblut.math.DoubleVector gradient, double learningRate, long iteration, double lambda, double cost) Computes the update for the given weights.

Method Detail

computeNewWeights

CostWeightTuple computeNewWeights(de.jungblut.math.DoubleVector theta,
                                  de.jungblut.math.DoubleVector gradient,
                                  double learningRate,
                                  long iteration,
                                  double lambda,
                                  double cost)

Computes the update for the given weights.

Parameters:

theta - the old weights.

gradient - the gradient.

learningRate - the learning rate.

iteration - the number of the current iteration.

lambda - the regularization parameter.

cost - the computed cost for this gradient update.

Returns:

the already updated weights for a particular updated gradient.

computeGradient

de.jungblut.math.minimize.CostGradientTuple computeGradient(de.jungblut.math.DoubleVector theta,
                                                            de.jungblut.math.DoubleVector gradient,
                                                            double learningRate,
                                                            long iteration,
                                                            double lambda,
                                                            double cost)

Computes the gradient.

Parameters:

theta - the old weights.

gradient - the gradient.

learningRate - the learning rate.

iteration - the number of the current iteration.

lambda - the regularization parameter.

cost - the computed cost for this gradient update.

Returns:

the gradient vector that should be substracted from the weights and the updated cost.