Multi-Marginal Stochastic Flow Matching for High-Dimensional Snapshot Data at Irregular Time Points

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Lee, Justin, Moradijamei, Behnaz, Shakeri, Heman
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866908480192905216
author Lee, Justin
Moradijamei, Behnaz
Shakeri, Heman
author_facet Lee, Justin
Moradijamei, Behnaz
Shakeri, Heman
contents Modeling the evolution of high-dimensional systems from limited snapshot observations at irregular time points poses a significant challenge in quantitative biology and related fields. Traditional approaches often rely on dimensionality reduction techniques, which can oversimplify the dynamics and fail to capture critical transient behaviors in non-equilibrium systems. We present Multi-Marginal Stochastic Flow Matching (MMSFM), a novel extension of simulation-free score and flow matching methods to the multi-marginal setting, enabling the alignment of high-dimensional data measured at non-equidistant time points without reducing dimensionality. The use of measure-valued splines enhances robustness to irregular snapshot timing, and score matching prevents overfitting in high-dimensional spaces. We validate our framework on several synthetic and benchmark datasets, including gene expression data collected at uneven time points and an image progression task, demonstrating the method's versatility.
format Preprint
id arxiv_https___arxiv_org_abs_2508_04351
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Multi-Marginal Stochastic Flow Matching for High-Dimensional Snapshot Data at Irregular Time Points
Lee, Justin
Moradijamei, Behnaz
Shakeri, Heman
Machine Learning
Neural and Evolutionary Computing
I.2
I.2.6
Modeling the evolution of high-dimensional systems from limited snapshot observations at irregular time points poses a significant challenge in quantitative biology and related fields. Traditional approaches often rely on dimensionality reduction techniques, which can oversimplify the dynamics and fail to capture critical transient behaviors in non-equilibrium systems. We present Multi-Marginal Stochastic Flow Matching (MMSFM), a novel extension of simulation-free score and flow matching methods to the multi-marginal setting, enabling the alignment of high-dimensional data measured at non-equidistant time points without reducing dimensionality. The use of measure-valued splines enhances robustness to irregular snapshot timing, and score matching prevents overfitting in high-dimensional spaces. We validate our framework on several synthetic and benchmark datasets, including gene expression data collected at uneven time points and an image progression task, demonstrating the method's versatility.
title Multi-Marginal Stochastic Flow Matching for High-Dimensional Snapshot Data at Irregular Time Points
topic Machine Learning
Neural and Evolutionary Computing
I.2
I.2.6
url https://arxiv.org/abs/2508.04351