approximators#

A collection of Approximators, which embody the inference task and the neural network components used to perform it.

Classes

Approximator(*args, **kwargs)

Base class for all BayesFlow approximators.

ContinuousApproximator(*args, **kwargs)

Defines a wrapper for estimating arbitrary continuous distributions of the form: p(inference_variables | summary(summary_variables), inference_conditions)

EnsembleApproximator(*args, **kwargs)

Combines multiple approximators into a single ensemble.

ModelComparisonApproximator(*args, **kwargs)

Defines an approximator for model (simulator) comparison, where the (discrete) posterior model probabilities are learned with a classifier.

RatioApproximator(*args, **kwargs)

Implements contrastive neural likelihood-to-evidence ratio estimation (NRE-C) as described in https://arxiv.org/pdf/2210.06170.

ScoringRuleApproximator(*args, **kwargs)

A workflow for fast amortized Bayes risk minimization for arbitrary scoring rules.