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

Models#

`OILMMModel`	Orthogonal Instantaneous Linear Mixing Model.
`OILMMPosterior`	Posterior distribution for OILMM.
`OrthogonalMixingMatrix`	Mixing matrix H = U S^(1/2) with orthogonal columns.
`create_oilmm`	Create OILMM model with shared kernel across latents.
`create_oilmm_from_data`	Create OILMM with data-informed initialization of mixing matrix.
`create_oilmm_with_kernels`	Create OILMM with custom kernel per latent GP.
`oilmm_mll`	Log marginal likelihood for the OILMM.