bayespy.inference.vmp.nodes.beta.BetaDistribution.compute_gradient

BetaDistribution.compute_gradient(g, u, phi)

Compute the moments and g(\phi).

psi(phi_1) - psi(sum_d phi_{1,d})

Standard gradient given the gradient with respect to the moments, that is, given the Riemannian gradient \tilde{\nabla}:

\nabla &= \begin{bmatrix} (\psi^{(1)}(\phi_1) - \psi^{(1)}(\sum_d \phi_{1,d}) \nabla_1 \end{bmatrix}