Smoke render: optimisation and MCMC are shrunk for CI speed, so figures and diagnostics are not publication-fidelity. The production docs are built with full-length inference.

GPJax

CoregionalizationMatrix#

class gpjax.parameters.CoregionalizationMatrix(num_outputs, rank, key)[source]#

Bases: Module

Parameterises a PSD output-correlation matrix B = WW^T + diag(kappa).

Parameters:

num_outputs (int)
rank (int)
key (Array)