Notes on generative modeling: flow matching, diffusion, optimal transport and Schr{ö}dinger bridge
Machine Learning
2026-06-29 v1 Machine Learning
Abstract
These notes recapitulate the high level mathematical principles behind different techniques for generative modeling. I show the connections between optimal transport and standard techniques such as Schr{\"o}dinger bridge and flow matching.
Cite
@article{arxiv.2606.30053,
title = {Notes on generative modeling: flow matching, diffusion, optimal transport and Schr{ö}dinger bridge},
author = {Titouan Vayer},
journal= {arXiv preprint arXiv:2606.30053},
year = {2026}
}