mgplvm.rdist.GP_diag module

class mgplvm.rdist.GP_diag.GP_diag(manif, m, n_samples, ts, _scale=0.9, ell=None)

Bases: mgplvm.rdist.GPbase.GPbase

I_v(v, sample_idxs=None)

Compute I @ v for some vector v. Here I = S = diag(scale). v is (n_samples x d x m x n_mc) where n_samples is the number of sample_idxs

kl(batch_idxs=None, sample_idxs=None)

Compute KL divergence between prior and posterior. This should be implemented for each class separately

name = 'GP_diag'

training: bool