Skip to content

Probabilistic Geodesic Flow Matching on Location-Scale Families

Sep 2026 · 0 citations · 32 references
Mathematics Computer Science

TL;DR

This work generalizes FM to the broader class of location-scale families for handling data inhomogeneity and introduces a novel class of probability paths defined as geodesics on the manifold of probability distributions, called probabilistic geodesic flow matching.

Abstract

Flow matching (FM) has recently emerged as a promising framework for generative modeling due to its conceptual simplicity and strong empirical performance. In FM, samples are transported along a vector field parameterized by a neural network, inducing a probability path that evolves from a simple noise distribution to the target data distribution, governed by an ordinary differential equation (ODE). However, existing FM approaches predominantly rely on probability paths derived from optimal transport (OT) between Gaussian distributions, which may be suboptimal for capturing complex data with inhomogeneous structures such as heavy tail or sharp contrast. In this work, we generalize FM to the broader class of location-scale families for handling data inhomogeneity and introduce a novel class of probability paths defined as geodesics on the manifold of probability distributions. We name this approach probabilistic geodesic flow matching to distinguish it from prior geodesic (Riemannian) FM methods defined in input space. We argue that Euclidean OT-based paths are not necessarily optimal in probability space and may limit modeling flexibility. Through synthetic benchmarks and scientific datasets at different scales, we demonstrate that the proposed method more effectively captures complex distributions, leading to improved or comparable performance compared with SOTA geometry-motivated generative models.

View source

Similar papers

#machine learning Preprint Oct 2026

Euclidean Distance-Based Flow Matching

Flow Matching has recently become popular as a technique for generative modeling with applications in many domains. In the standard Flow Matching formulation, we interpret the vector field as the solution of a least-squares regression problem, which is known to be sensitive to contamination. Therefore we leverage the v...

Paul-Henrik Heilmann, Peter Ochs · 0 citations
Preprint Sep 2026

Stochastic Processes as Non-Metric Geodesics in Information Geometry

It is shown that the work-minimizing optimal protocol in the slow-driving limit coincides precisely with an expectation geodesic of the statistical manifold with non-metricity equipped with $(g, {}^{(1/2)}\Gamma, {}^{(-1/2)}\Gamma)$, highlighting the active physical role of non-metricity in information geometry.

T. Koide, A. van de Venn · 0 citations
#machine learning Preprint Sep 2026

When Riemann flows with Wasserstein: Generative Modeling of Probability Distributions on Manifolds

Riemannian Wasserstein Entropic Flow Matching (RWEFM) is introduced, a generative framework on the Wasserstein space of a Riemannian manifold that can generate whole single-cell samples in hyperspherical latent spaces and protein conformational ensembles on the torus by respecting the intrinsic geometry of the data.

D. Haviv, E. De Brouwer, Rishabh Anand et al. · 0 citations
#artificial intelligence Preprint Oct 2026

ReSFlow: Rectifying Categorical Flows on Statistical Manifolds for One-Step Generation

Generative modeling for discrete data has been significantly advanced by learning continuous vector fields on the statistical manifolds to transport simple priors to target discrete distributions. However, because these continuous-time flows are not constrained to follow geodesics on the statistical manifold, thereby r...

Xiao-Huan Jia, Renzhe Xu, Xiao Wang et al. · 0 citations
Preprint Aug 2026

Weighted Laplacian Flow: A Deterministic Particle Flow with Exponential Convergence

We introduce weighted Laplacian flow (WLF), a deterministic particle-flow framework for sampling from a target distribution known only up to normalization. The proposed method evolves the logarithmic density ratio through a transport equation and determines the particle velocity from a target-weighted Poisson problem,...

Wei-Ye Gan, Tang-Jun Wang, Zuo-Qiang Shi · 0 citations
#machine learning Preprint Sep 2026

Manifold-Stable Flow Matching

This work introduces manifold-stable flow matching (MSFM), which can start from an arbitrary ambient prior, not necessarily supported on the manifold, and guarantees manifold invariance and transverse convergence to the manifold within a desired time window.

Amirhossein Nazerian, A. Pezeshki, Jian-Guo Zhao · 0 citations

Related blog posts

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.