Learnt Harmonic Mean Estimator for Bayesian Model Selection

Machine learning assisted computation of the marginal likelihood

Bayesian model comparison provides a principled statistical framework for selecting an appropriate model to describe observational data, naturally trading off model complexity and goodness of fit. However, it requires computation of the Bayesian model evidence, also called the marginal likelihood, which is computationally challenging. We present the learnt harmonic mean estimator to compute the model evidence, which is agnostic to sampling strategy, affording it great flexibility.

This article was co-authored by Alessio …

bayesian bayesian-statistics machine learning mean model-comparison model selection thoughts-and-theory