/// <summary>
/// Calculates the KL-divergence between this Dirichlet random variable and another
/// </summary>
/// <param name="other">The other Dirichlet distribution.</param>
/// <param name="beta">The two dimensional array of cross-counts.</param>
/// <returns>The KL divergence</returns>
public double KLDivergence(Dirichlet other, double[][] beta)
{
_2_gammafamily g = new _2_gammafamily();
double kl = this.InformationEntropy();
for (int i = 0; i < other.Alpha.Length; i++)
{
kl += g.Gammaln(other.Alpha[i]);
}
kl -= g.Gammaln(other.SumAlpha);
double crossTerm;
for (int i = 0; i < this.Alpha.Length; i++)
{
crossTerm = 0;
for (int j = 0; j < other.Alpha.Length; j++)
{
crossTerm -= (beta[i][j] - 1) * (g.Digamma(beta[i][j]) - g.Digamma(other.Alpha[j]));
}
kl -= crossTerm * this.Alpha[i] / this.SumAlpha;
}
return(kl);
}
/// <summary>
/// Based on the formula for total information entropy given here - https://en.wikipedia.org/wiki/Dirichlet_distribution.
/// </summary>
/// <param name="alpha">The parameters of the Dirichlet distribution. These correspond to a histogram with counts.</param>
/// <returns>The Entropy of a Dirichlet distribution.</returns>
public double InformationEntropy(double[] alpha)
{
_2_gammafamily g = new _2_gammafamily();
double alpha_0 = 0, H = 0;//The sum of coefficients (normalizing factor) and final entropy term respectively.
int K = alpha.Length;
for (int i = 0; i < K; i++)
{
alpha[i] += regularizer; //Before doing anything else, we regularize the parameters which is equivalent to a uniform prior.
alpha_0 += alpha[i];
H += g.Gammaln(alpha[i]); //Positive part of normalization constant (which is the log of a multivariate beta distribution).
H -= (alpha[i] - 1) * g.Digamma(alpha[i]); //The contribution from each of the alphas.
}
H -= g.Gammaln(alpha_0); //Negative part of normalization constant.
H += (alpha_0 - K) * g.Digamma(alpha_0); //The contribution from the normalizing factor.
return(H);
}