/// <summary>
/// Performs gradient descent to optomise theta parameters.
/// </summary>
/// <param name="theta">Initial Theta (Zeros)</param>
/// <param name="x">Training set</param>
/// <param name="y">Training labels</param>
/// <param name="maxIterations">Maximum number of iterations to run gradient descent</param>
/// <param name="learningRateAlpha">The learning rate (Alpha)</param>
/// <param name="costFunction">Cost function to use for gradient descent</param>
/// <param name="lambda">The regularization constant to apply</param>
/// <param name="regularizer">The regularization function to apply</param>
/// <returns></returns>
public static Tuple<double, Vector> Run(
Vector theta,
Matrix x,
Vector y,
int maxIterations,
double learningRateAlpha,
ICostFunction costFunction,
double lambda,
IRegularizer regularizer)
{
var bestTheta = theta.Copy();
var bestCost = double.PositiveInfinity;
double currentCost = 0;
var currentGradient = theta.Copy();
for (var i = 0; i <= maxIterations; i++)
{
currentCost = costFunction.ComputeCost(bestTheta, x, y, lambda, regularizer);
currentGradient = costFunction.ComputeGradient(bestTheta, x, y, lambda, regularizer);
if (currentCost < bestCost)
{
bestTheta = bestTheta - learningRateAlpha * currentGradient;
bestCost = currentCost;
}
else
{
learningRateAlpha = learningRateAlpha * 0.99;
}
}
return new Tuple<double, Vector>(bestCost, bestTheta);
}
/// <summary>
/// Performs gradient descent to optomise theta parameters.
/// </summary>
/// <param name="theta">Initial Theta (Zeros)</param>
/// <param name="x">Training set</param>
/// <param name="y">Training labels</param>
/// <param name="maxIterations">Maximum number of iterations to run gradient descent</param>
/// <param name="learningRateAlpha">The learning rate (Alpha)</param>
/// <param name="costFunction">Cost function to use for gradient descent</param>
/// <param name="lambda">The regularization constant to apply</param>
/// <param name="regularizer">The regularization function to apply</param>
/// <returns></returns>
public static Tuple <double, Vector> Run(Vector theta, Matrix x, Vector y, int maxIterations, double learningRateAlpha,
ICostFunction costFunction, double lambda, IRegularizer regularizer)
{
Vector bestTheta = theta.Copy();
double bestCost = double.PositiveInfinity;
double currentCost = 0;
Vector currentGradient = theta.Copy();
for (int i = 0; i <= maxIterations; i++)
{
currentCost = costFunction.ComputeCost(bestTheta, x, y, lambda, regularizer);
currentGradient = costFunction.ComputeGradient(bestTheta, x, y, lambda, regularizer);
if (currentCost < bestCost)
{
bestTheta = bestTheta - learningRateAlpha * currentGradient;
bestCost = currentCost;
}
else
{
learningRateAlpha = learningRateAlpha * 0.99;
}
}
return(new Tuple <double, Vector>(bestCost, bestTheta));
}
/// <summary>
/// Update and return the Cost.
/// </summary>
/// <param name="costFunction">The cost function to optimize.</param>
/// <param name="properties">Properties for the optimization routine.</param>
/// <returns>Double</returns>
public virtual double UpdateCost(ICostFunction costFunction, OptimizerProperties properties)
{
return costFunction.ComputeCost(properties.Theta);
}
/// <summary>
/// Update and return the Cost.
/// </summary>
/// <param name="costFunction">The cost function to optimize.</param>
/// <param name="properties">Properties for the optimization routine.</param>
/// <returns>Double</returns>
public virtual double UpdateCost(ICostFunction costFunction, OptimizerProperties properties)
{
return(costFunction.ComputeCost(properties.Theta));
}
