Towards Trustworthy Amortized Bayesian Model Comparison

Šimon Kucharský, Aayush Mishra, Daniel Habermann, Stefan T. Radev, Paul-Christian Bürkner
8/28/2025
stat.MLcs.LGstat.CO

No confident code implementation found for this paper.

Abstract

Amortized Bayesian model comparison (BMC) enables fast probabilistic ranking of models via simulation-based training of neural surrogates. However, the reliability of neural surrogates deteriorates when simulation models are misspecified - the very case where model comparison is most needed. Thus, we supplement simulation-based training with a self-consistency (SC) loss on unlabeled real data to improve BMC estimates under empirical distribution shifts. Using a numerical experiment and two case studies with real data, we compare amortized evidence estimates with and without SC against analytic or bridge sampling benchmarks. SC improves calibration under model misspecification when having access to analytic likelihoods. However, it offers limited gains with neural surrogate likelihoods, making it most practical for trustworthy BMC when likelihoods are exact.

View on arXivView PDF

Code Implementations

No confident code match yet

We couldn't find an author-owned or strongly-evidenced community implementation for this paper. Any repos shown below are weak matches — verify before relying on them.

No code implementations found yet.

Know of an implementation? Let us know in the comments below!

Similar Papers

Improving the Accuracy of Amortized Model Comparison with Self-Consistency

94% match2025

Leveraging Self-Consistency for Data-Efficient Amortized Bayesian Inference

83% match1 repo12023

Leveraging Self-Consistency for Data-Efficient Amortized Bayesian Inference

83% match1 repo12026

Neural Methods for Amortized Inference

83% match2024

A Statistical Assessment of Amortized Inference Under Signal-to-Noise Variation and Distribution Shift

83% match2026

Does Unsupervised Domain Adaptation Improve the Robustness of Amortized Bayesian Inference? A Systematic Evaluation

82% match1 repo22025

Cite this paper

@article{kucharsk2025towards,
  title  = {Towards Trustworthy Amortized Bayesian Model Comparison},
  author = {Šimon Kucharský and Aayush Mishra and Daniel Habermann and Stefan T. Radev and Paul-Christian Bürkner},
  year   = {2025},
  eprint = {2508.20614},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2508.20614v1}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2508.20614.svg)](https://codeofpaper.com/paper/2508.20614)

Discussion