Other Functions and Classes

tf.contrib.bayesflow.variational_inference.register_prior(variational, prior)

Associate a variational DistributionTensor with a Distribution prior.

This is a helper function used in conjunction with elbo that allows users to specify the mapping between variational distributions and their priors without having to pass in variational_with_prior explicitly.

Args:
  • variational: DistributionTensor q(Z). Approximating distribution.
  • prior: Distribution p(Z). Prior distribution.
Returns:

None

Raises:
  • ValueError: if variational is not a DistributionTensor or prior is not a Distribution.