MIRA: A Score for Conditional Distribution Accuracy and Model Comparison
Sammy Sharief, Justine Zeghal, Gabriel Missael Barco, Pablo Lemos, Yashar Hezaveh, Laurence Perreault-Levasseur
Abstract
We present Mira, a method for estimating the expected probability that samples from a candidate conditional distribution match the true, unknown conditional distribution, for which only data-label pairs are available. We derive theoretical bounds obtained when the candidate distribution matches the true one and when the conditional distributions are independent. This framework thus enables model comparison by quantifying the alignment between the conditional distribution of a candidate model and the data-label pairs of the true model. Consequently, Mira enables Bayesian model comparison through direct posterior validation, bypassing the challenging evidence computation. We demonstrate its effectiveness across several toy problems and Bayesian inference tasks.
BibTeX
@inproceedings{
sharief2026mira,
title={{MIRA}: A Score for Conditional Distribution Accuracy and Model Comparison},
author={Sammy Nasser Sharief and Justine Zeghal and Gabriel Missael Barco and Pablo Lemos and Yashar Hezaveh and Laurence Perreault-Levasseur},
booktitle={Forty-third International Conference on Machine Learning},
year={2026},
url={https://openreview.net/forum?id=ra2t1V4nml}
}