pymc.gp.Latent.prior

Latent.prior(name, X, n_outputs=1, reparameterize=True, jitter=1e-06, **kwargs)

Returns the GP prior distribution evaluated over the input locations X.

This is the prior probability over the space of functions described by its mean and covariance function.

\[f \mid X \sim \text{MvNormal}\left( \mu(X), k(X, X') \right)\]

Parameters:

namestr

Name of the random variable

Xarray_like

Function input values. If one-dimensional, must be a column vector with shape (n, 1).

n_outputsint, default 1

Number of output GPs. If you’re using dims, make sure their size is equal to (n_outputs, X.shape[0]), i.e the number of output GPs by the number of input points. Example: gp.prior(“f”, X=X, n_outputs=3, dims=(“n_gps”, “x_dim”)), where len(n_gps) = 3 and len(x_dim = X.shape[0].

reparameterizebool, default True

Reparameterize the distribution by rotating the random variable by the Cholesky factor of the covariance matrix.

jitterfloat, default 1e-6

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

**kwargs

Extra keyword arguments that are passed to MvNormal distribution constructor.