Flow Matching from Non-Gaussian Sources: A Theory of Efficient Sampling
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 has an everywhere positive, continuously differentiable density, finite total variance , and an -Lipschitz score. Using the population velocity field and a suitable time grid, this sampler achieves total variation error at most in iterations, provided the target distribution satisfies a mild second-moment condition. These assumptions cover, among many examples, source distributions such as multivariate Student's 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.
Flow Matching
Flow matching learns continuous-time vector fields that transport simple noise distributions into data for efficient generative modeling.
See all 707 papers