sbi.inference.likelihood_estimator_based_potential

sbi.inference.likelihood_estimator_based_potential#

likelihood_estimator_based_potential(likelihood_estimator, prior, x_o, enable_transform=True)[source]#

Returns potential \(\log(p(x_o|\theta)p(\theta))\) for likelihood estimator.

It also returns a transformation that can be used to transform the potential into unconstrained space.

Parameters:
  • likelihood_estimator (ConditionalDensityEstimator) – The density estimator modelling the likelihood.

  • prior (Distribution) – The prior distribution.

  • x_o (Tensor | None) – The observed data at which to evaluate the likelihood.

  • enable_transform (bool) – Whether to transform parameters to unconstrained space. When False, an identity transform will be returned for theta_transform.

Returns:

The potential function \(p(x_o|\theta)p(\theta)\) and a transformation that maps to unconstrained space.

Return type:

Tuple[LikelihoodBasedPotential, Transform]