Targeting Bayes factors with direct-path non-equilibrium thermodynamic integration

03/21/2017
by   Marco Grzegorczyk, et al.
0

Thermodynamic integration (TI) for computing marginal likelihoods is based on an inverse annealing path from the prior to the posterior distribution. In many cases, the resulting estimator suffers from high variability, which particularly stems from the prior regime. When comparing complex models with differences in a comparatively small number of parameters, intrinsic errors from sampling fluctuations may outweigh the differences in the log marginal likelihood estimates. In the present article, we propose a thermodynamic integration scheme that directly targets the log Bayes factor. The method is based on a modified annealing path between the posterior distributions of the two models compared, which systematically avoids the high variance prior regime. We combine this scheme with the concept of non-equilibrium TI to minimise discretisation errors from numerical integration. Results obtained on Bayesian regression models applied to standard benchmark data, and a complex hierarchical model applied to biopathway inference, demonstrate a significant reduction in estimator variance over state-of-the-art TI methods.

READ FULL TEXT
research
05/25/2018

Accurate Computation of Marginal Data Densities Using Variational Bayes

Bayesian model selection and model averaging rely on estimates of margin...
research
03/02/2022

Fast and accurate approximation to informed Bayes factors for focal parameters

We outline an approximation to informed Bayes factors for a focal parame...
research
11/11/2020

Neural Empirical Bayes: Source Distribution Estimation and its Applications to Simulation-Based Inference

We revisit empirical Bayes in the absence of a tractable likelihood func...
research
06/11/2020

A Bridge between Cross-validation Bayes Factors and Geometric Intrinsic Bayes Factors

Model Selections in Bayesian Statistics are primarily made with statisti...
research
07/18/2023

A Bayesian Framework for Multivariate Differential Analysis accounting for Missing Data

Current statistical methods in differential proteomics analysis generall...
research
11/24/2021

Machine learning assisted Bayesian model comparison: learnt harmonic mean estimator

We resurrect the infamous harmonic mean estimator for computing the marg...
research
06/23/2022

A Bayesian Approach to Atmospheric Circulation Regime Assignment

The standard approach when studying atmospheric circulation regimes and ...

Please sign up or login with your details

Forgot password? Click here to reset