Distortion estimates for approximate Bayesian inference

2020/06/19 by Hanwen Xing, Xing, Hanwen, Geoff K. Nicholls +3
Computer Science · Mathematics · #Bayesian Methods and Mixture Models #Computation (stat.CO) #FOS: Computer and information sciences #Gaussian Processes and Bayesian Inference #Statistical Methods and Bayesian Inference #stat.CO

paper · pdf · doi:10.48550/arxiv.2006.11228

arxiv created 2020/06/19 · openalex publication_date 2020/06/19 · arxiv updated 2020/06/22 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

Current literature on posterior approximation for Bayesian inference offers many alternative methods. Does our chosen approximation scheme work well on the observed data? The best existing generic diagnostic tools treating this kind of question by looking at performance averaged over data space, or otherwise lack diagnostic detail. However, if the approximation is bad for most data, but good at the observed data, then we may discard a useful approximation. We give graphical diagnostics for posterior approximation at the observed data. We estimate a "distortion map" that acts on univariate marginals of the approximate posterior to move them closer to the exact posterior, without recourse to the exact posterior.

Citations

• Statistical inference for noisy nonlinear ecological dynamic systems
• An introduction to exponential random graph (p*) models for social networks
• Validating Bayesian Inference Algorithms with Simulation-Based Calibration
• Bergm: Bayesian Exponential Random Graphs in R
• Fast ε-free Inference of Simulation Models with Bayesian Conditional Density Estimation

Related

• Discovering Inductive Bias with Gibbs Priors: A Diagnostic Tool for Approximate Bayesian Inference
• Convergence of Regression Adjusted Approximate Bayesian Computation
• Approximate Bayesian Computation: a nonparametric perspective
• Diagnostics for Variational Bayes approximations
• Diagnostic tools of approximate Bayesian computation using the coverage property