distributions#

A collection of Distributions, which represent the latent space for InferenceNetworks or the summary space of SummaryNetworks.

Classes

DiagonalNormal(*args, **kwargs)

Implements a backend-agnostic diagonal Gaussian distribution.

DiagonalStudentT(*args, **kwargs)

Implements a backend-agnostic diagonal Student-t distribution.

Distribution(*args, **kwargs)

Mixture(*args, **kwargs)

Utility class for a backend-agnostic mixture distributions.