Modularized Bayesian analyses and cutting feedback in likelihood-free inference

• Published in: Statistics and computing 2023-02, Vol.33 (1), Article 33
• Main Authors: Chakraborty, Atlanta, Nott, David J., Drovandi, Christopher C., Frazier, David T., Sisson, Scott A.
• Format: Article
• Language: English
• Subjects: Approximation; Artificial Intelligence; Bayesian analysis; Computation; Computer Science; Continuous time systems; Cutting; Feedback; Mathematical models; Mixtures; Modular structures; Modules; Parameters; Probability and Statistics in Computer Science; Statistical inference; Statistical Theory and Methods; Statistics and Computing/Statistics Programs
• ISSN: 0960-3174; 1573-1375
• DOI: 10.1007/s11222-023-10207-5

There has been much recent interest in modifying Bayesian inference for misspecified models so that it is useful for specific purposes. One popular modified Bayesian inference method is “cutting feedback” which can be used when the model consists of a number of coupled modules, with only some of the modules being misspecified. Cutting feedback methods represent the full posterior distribution in terms of conditional and sequential components, and then modify some terms in such a representation based on the modular structure for specification or computation of a modified posterior distribution. The main goal of this is to avoid contamination of inferences for parameters of interest by misspecified modules. Computation for cut posterior distributions is challenging, and here we consider cutting feedback for likelihood-free inference based on Gaussian mixture approximations to the joint distribution of parameters and data summary statistics. We exploit the fact that marginal and conditional distributions of a Gaussian mixture are Gaussian mixtures to give explicit approximations to marginal or conditional posterior distributions so that we can easily approximate cut posterior analyses. The mixture approach allows repeated approximation of posterior distributions for different data based on a single mixture fit. This is important for model checks which aid in the decision of whether to “cut”. A semi-modular approach to likelihood-free inference where feedback is partially cut is also developed. The benefits of the method are illustrated on two challenging examples, a collective cell spreading model and a continuous time model for asset returns with jumps.