Generalized Wasserstein Flow Matching: Transport Plans, Everywhere, All at Once

• URL: http://arxiv.org/abs/2605.08424v1
• Date: Fri, 08 May 2026 19:33:36 GMT
• Title: Generalized Wasserstein Flow Matching: Transport Plans, Everywhere, All at Once
• Abstract summary: We extend flow matching to the space of probability measures over probability measures, introducing a Wasserstein-on-Wasserstein (WoW) formulation.<n>We show that measures over transport plans naturally induce velocity fields that realize metameasure flows.<n>Our framework unifies and extends existing approaches to point cloud and set generation, providing a practical and theoretically grounded method for generative modelling in WoW spaces.
• Score: 7.200655637873445
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Flow matching has recently emerged as a flexible and efficient framework for generative modelling by learning deterministic transport dynamics between probability measures. In this work, we extend flow matching to the space of probability measures over probability measures, introducing a Wasserstein-on-Wasserstein (WoW) formulation. Leveraging the nested Wasserstein geometry, we show that measures over transport plans naturally induce velocity fields that realize metameasure flows. This yields a principled generalization of Wasserstein flow matching via coupled outer and inner transport plans. To address the substantial computational cost of WoW transport, we propose scalable approximations based on sliced and linear Wasserstein distances, enabling efficient training while promoting numerically stable, near-straight trajectories. Our framework unifies and extends existing approaches to point cloud and set generation, providing a practical and theoretically grounded method for generative modelling in WoW spaces.

Related papers

• $L^2$ over Wasserstein: Statistical Analysis for Optimal Transport [0.0]
  We introduce the $L2$ over Wasserstein space by characterising distances and geodesic geometry.<n>We ensemble statistical convergence results of the optimal transport machinery using the empirical measure within the $L2$ over Wasserstein framework.<n>We refine Schwartz's consistency theorem to the Wasserstein topology and deduce posterior convergence of the same machinery in the $L2$ over Wasserstein space.
  arXiv  Detail & Related papers  (2026-05-20T16:29:01Z)
• Lagrangian Flow Matching: A Least-Action Framework for Principled Path Design [14.77320535984857]
  Flow matching trains a neural velocity field by regression against a target velocity associated with a prescribed probability path.<n>We propose Lagrangian flow matching, a physics-based framework in which the probability path and velocity field are determined by minimizing the action of a general Lagrangian.
  arXiv  Detail & Related papers  (2026-05-14T21:05:03Z)
• A Few-Step Generative Model on Cumulative Flow Maps [25.03991490159211]
  We propose a unified, few-step generative modeling framework based on emphcumulative flow maps for long-range transport in probability space.<n>At its core is a cumulative-flow abstraction that connects local, instantaneous, updates with finite-time transport.<n>We demonstrate its effectiveness across diverse tasks, including image generation, geometric distribution modeling, joint prediction, and SDF generation.
  arXiv  Detail & Related papers  (2026-05-05T10:51:40Z)
• An Eulerian Perspective on Straight-Line Sampling [0.0]
  We study dynamic measure transport for generative modeling, specifically, flows induced by processes that bridge a specified source and target distribution.<n>We ask emphwhich processes produce straight-line flows -- i.e., flows whose pointwise acceleration vanishes and thus are exactly integrable with a first-order method?<n>We provide a concise PDE characterization of straightness as a balance between conditional acceleration and the divergence of a weighted covariance (Reynolds) tensor.
  arXiv  Detail & Related papers  (2025-10-13T17:33:58Z)
• Fast Estimation of Wasserstein Distances via Regression on Sliced Wasserstein Distances [70.94157767200342]
  We propose a fast estimation method based on regressing Wasserstein distance on sliced Wasserstein distances.<n>We show that accurate models can be learned from a small number of distribution pairs.<n>Our method consistently provides a better approximation of Wasserstein distance than the state-of-the-art Wasserstein embedding model, Wasserstein Wormhole.
  arXiv  Detail & Related papers  (2025-09-24T19:30:53Z)
• Dynamical Measure Transport and Neural PDE Solvers for Sampling [77.38204731939273]
  We tackle the task of sampling from a probability density as transporting a tractable density function to the target. We employ physics-informed neural networks (PINNs) to approximate the respective partial differential equations (PDEs) solutions. PINNs allow for simulation- and discretization-free optimization and can be trained very efficiently.
  arXiv  Detail & Related papers  (2024-07-10T17:39:50Z)
• Dynamic Conditional Optimal Transport through Simulation-Free Flows [12.976042923229466]
  We study the geometry of conditional optimal transport (COT) and prove a dynamical formulation which generalizes the Benamou-Brenier Theorem. We propose a simulation-free flow-based method for conditional generative modeling.
  arXiv  Detail & Related papers  (2024-04-05T17:41:52Z)
• Optimal Flow Matching: Learning Straight Trajectories in Just One Step [89.37027530300617]
  We develop and theoretically justify the novel textbf Optimal Flow Matching (OFM) approach. It allows recovering the straight OT displacement for the quadratic transport in just one FM step. The main idea of our approach is the employment of vector field for FM which are parameterized by convex functions.
  arXiv  Detail & Related papers  (2024-03-19T19:44:54Z)
• Neural Wasserstein Gradient Flows for Maximum Mean Discrepancies with Riesz Kernels [1.3654846342364308]
  Wasserstein gradient flows of maximum mean discrepancy (MMD) functionals with non-smooth Riesz kernels show a rich structure. We propose to approximate the backward scheme of Jordan, Kinderlehrer and Otto for computing such Wasserstein gradient flows. We provide analytic formulas for Wasserstein schemes starting at a Dirac measure and show their convergence as the time step size tends to zero.
  arXiv  Detail & Related papers  (2023-01-27T09:57:36Z)
• Manifold Interpolating Optimal-Transport Flows for Trajectory Inference [64.94020639760026]
  We present a method called Manifold Interpolating Optimal-Transport Flow (MIOFlow) MIOFlow learns, continuous population dynamics from static snapshot samples taken at sporadic timepoints. We evaluate our method on simulated data with bifurcations and merges, as well as scRNA-seq data from embryoid body differentiation, and acute myeloid leukemia treatment.
  arXiv  Detail & Related papers  (2022-06-29T22:19:03Z)
• Large-Scale Wasserstein Gradient Flows [84.73670288608025]
  We introduce a scalable scheme to approximate Wasserstein gradient flows. Our approach relies on input neural networks (ICNNs) to discretize the JKO steps. As a result, we can sample from the measure at each step of the gradient diffusion and compute its density.
  arXiv  Detail & Related papers  (2021-06-01T19:21:48Z)
• A Near-Optimal Gradient Flow for Learning Neural Energy-Based Models [93.24030378630175]
  We propose a novel numerical scheme to optimize the gradient flows for learning energy-based models (EBMs) We derive a second-order Wasserstein gradient flow of the global relative entropy from Fokker-Planck equation. Compared with existing schemes, Wasserstein gradient flow is a smoother and near-optimal numerical scheme to approximate real data densities.
  arXiv  Detail & Related papers  (2019-10-31T02:26:20Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.