stat.MLNov 19, 2026

Flow Matching from Non-Gaussian Sources: A Theory of Efficient Sampling

Authors: Yuchen Zhou, Lili Zheng, Yuxin Chen, Gen Li

Organizations: Department of Statistics, University of Illinois Urbana-Champaign. · Department of Statistics and Data Science, the Wharton School, University of Pennsylvania. · Department of Statistics and Data Science, Chinese University of Hong Kong.

Abstract

Flow matching is a versatile framework for generative modeling that transports a source distribution to a target data distribution. A key advantage is its flexibility in the choice of source distribution, such as heavy-tailed and multimodal sources. Yet finite-step sampling guarantees for non-Gaussian sources remain limited. We establish a nonasymptotic convergence theory for Euler discretization of flow matching with linear interpolation. Suppose the source distribution on Rd\mathbb{R}^d has an everywhere positive, continuously differentiable density, finite total variance TotVarbase\mathsf{TotVar}_{\mathsf{base}}, and an LL-Lipschitz score. Using the population velocity field and a suitable time grid, this sampler achieves total variation error at most ε\varepsilon in O~(LdTotVarbase/ε)\widetilde{O}(Ld\mathsf{TotVar}_{\mathsf{base}}/\varepsilon) iterations, provided the target distribution satisfies a mild second-moment condition. These assumptions cover, among many examples, source distributions such as multivariate Student's tt distributions with more than two degrees of freedom and finite Gaussian mixtures with shared covariance, while accommodating target distributions with neither a smooth density nor bounded support.

Explore similar work

CardsList
  1. Generative Modeling with Continuous Flows: Sample Complexity of Flow Matching

    Nov 1, 2026Mudit Gaur, Prashant Trivedi, Shuchin Aeron +3Flow MatchingFlow-Based Generative Modeling

  2. Discrete Flow Matching: Convergence Guarantees Under Minimal Assumptions

    May 9, 2026Le-Tuyet-Nhi Pham, Giovanni Conforti, Zhenjie Ren +1Flow MatchingGenerative Modeling

  3. Correcting CondOT: Exact Finite-Step Sampling in Gaussian Flow Matching

    Sep 30, 2026Ron Levy, Michael EladFlow MatchingDiffusion Sampling