Tessellations of Semi-Discrete Flow Matching

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Pierret, Emile, Hertrich, Johannes, Hurault, Samuel, Delon, Julie
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866913102449082368
author Pierret, Emile
Hertrich, Johannes
Hurault, Samuel
Delon, Julie
author_facet Pierret, Emile
Hertrich, Johannes
Hurault, Samuel
Delon, Julie
contents We study Flow Matching in a semi-discrete setting where a Gaussian source is transported toward a discrete target supported on finitely many points. This semi-discrete regime is the theoretical setting behind the use of Flow Matching for generative modeling, where the target distribution is represented by a finite dataset. In this semi-discrete regime, the exact Flow Matching velocity field is available in closed form, which makes it possible to analyze the geometry induced by the terminal flow map independently of optimization and approximation effects. We investigate the terminal assignment regions, namely the preimages of the target atoms under the terminal flow. We show that these regions are open, simply connected and, under an additional assumption, homeomorphic to the unit ball. At the same time, a planar four-point example shows that these cells can differ sharply from Laguerre cells arising in semi-discrete optimal transport: they may be non-convex, have curved boundaries, and exhibit different boundedness and adjacency patterns. These results clarify the geometry intrinsically induced by the exact semi-discrete Flow Matching objective before neural approximation enters the picture.
format Preprint
id arxiv_https___arxiv_org_abs_2605_07513
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Tessellations of Semi-Discrete Flow Matching
Pierret, Emile
Hertrich, Johannes
Hurault, Samuel
Delon, Julie
Machine Learning
We study Flow Matching in a semi-discrete setting where a Gaussian source is transported toward a discrete target supported on finitely many points. This semi-discrete regime is the theoretical setting behind the use of Flow Matching for generative modeling, where the target distribution is represented by a finite dataset. In this semi-discrete regime, the exact Flow Matching velocity field is available in closed form, which makes it possible to analyze the geometry induced by the terminal flow map independently of optimization and approximation effects. We investigate the terminal assignment regions, namely the preimages of the target atoms under the terminal flow. We show that these regions are open, simply connected and, under an additional assumption, homeomorphic to the unit ball. At the same time, a planar four-point example shows that these cells can differ sharply from Laguerre cells arising in semi-discrete optimal transport: they may be non-convex, have curved boundaries, and exhibit different boundedness and adjacency patterns. These results clarify the geometry intrinsically induced by the exact semi-discrete Flow Matching objective before neural approximation enters the picture.
title Tessellations of Semi-Discrete Flow Matching
topic Machine Learning
url https://arxiv.org/abs/2605.07513