bayespy.inference.vmp.nodes.gaussian.GaussianARDDistribution¶

class bayespy.inference.vmp.nodes.gaussian.GaussianARDDistribution(shape)[source]¶

…

Log probability density function:

$\log p(x|\mu, \alpha) = -\frac{1}{2} x^T \mathrm{diag}(\alpha) x + x^T \mathrm{diag}(\alpha) \mu - \frac{1}{2} \mu^T \mathrm{diag}(\alpha) \mu + \frac{1}{2} \sum_i \log \alpha_i - \frac{D}{2} \log(2\pi)$

Parent has moments:

$\begin{bmatrix} \alpha \circ \mu \\ \alpha \circ \mu \circ \mu \\ \alpha \\ \log(\alpha) \end{bmatrix}$

__init__(shape)[source]¶: Initialize self. See help(type(self)) for accurate signature.

Methods

`__init__`(shape)	Initialize self.
`compute_cgf_from_parents`(u_mu_alpha)	Compute the value of the cumulant generating function.
`compute_fixed_moments_and_f`(x[, mask])	Compute u(x) and f(x) for given x.
`compute_gradient`(g, u, phi)	Compute the standard gradient with respect to the natural parameters.
`compute_logpdf`(u, phi, g, f, ndims)	Compute E[log p(X)] given E[u], E[phi], E[g] and E[f].
`compute_message_to_parent`(parent, index, u, …)	…
`compute_moments_and_cgf`(phi[, mask])
`compute_phi_from_parents`(u_mu_alpha[, mask])
`compute_weights_to_parent`(index, weights)	Maps the mask to the plates of a parent.
`plates_from_parent`(index, plates)	Resolve the plate mapping from a parent.
`plates_to_parent`(index, plates)	Resolves the plate mapping to a parent.
`random`(*phi[, plates])	Draw a random sample from the Gaussian distribution.