pymc.gp.LatentKron.prior

LatentKron.prior(name, Xs, jitter=1e-06, **kwargs)

Return the prior distribution evaluated over the input locations Xs.

Parameters:

namestr

Name of the random variable

Xslist of array_like

Function input values for each covariance function. Each entry must be passable to its respective covariance without error. The total covariance function is measured on the full grid cartesian(*Xs).

jitterfloat, default 1e-6

A small correction added to the diagonal of positive semi-definite covariance matrices to ensure numerical stability.

dimsstr or tuple of str, optional

Dimension name(s) for the GP random variable, passed to Deterministic(). Allows the GP to be identified by named coordinates in the model, consistent with Latent and HSGP.

**kwargs

Extra keyword arguments that are passed to the internal Normal rotated variable.