An optimal transport-based generative model for Bayesian posterior sampling
Authors
Research Topics
Paper Information
-
Journal:
Journal of the Royal Statistical Society Series B -
DOI:
10.1093/jrsssb/qkag126 -
Published:
September 29, 2026 -
Added to Tracker:
Sep 29, 2026
Abstract
Abstract We investigate the problem of sampling from posterior distributions with intractable normalizing constants in Bayesian inference. Building on transport map-based generative models for posterior sampling, we propose an optimal transport (OT)-constrained transport map class that learns a deterministic map from a reference distribution to the target posterior through constrained optimization. The proposed class exploits structural properties of OT maps and allows efficient generation of many independent, high-quality posterior samples. The framework supports both continuous and mixed discrete–continuous parameter spaces, with specific adaptations for latent variable models and near-Gaussian posteriors. Beyond computational benefits, it also enables new inferential tools based on OT-derived multivariate ranks and quantiles for Bayesian exploratory analysis and visualization. We demonstrate the effectiveness of our approach through multiple simulation studies and a real-world data analysis.
Author Details
Yun Yang
AuthorYuexi Wang
AuthorKe Li
AuthorWei Han
AuthorResearch Topics & Keywords
Bayesian Statistics
Research AreaCitation Information
APA Format
Yun Yang
,
Yuexi Wang
,
Ke Li
&
Wei Han
(2026)
.
An optimal transport-based generative model for Bayesian posterior sampling.
Journal of the Royal Statistical Society Series B
, 10.1093/jrsssb/qkag126.
BibTeX Format
@article{paper1724,
title = { An optimal transport-based generative model for Bayesian posterior sampling },
author = {
Yun Yang
and Yuexi Wang
and Ke Li
and Wei Han
},
journal = { Journal of the Royal Statistical Society Series B },
year = { 2026 },
doi = { 10.1093/jrsssb/qkag126 },
url = { https://doi.org/10.1093/jrsssb/qkag126 }
}