stat.MLMar 31, 2024

Gaussian-Channel Regularity and Distribution Learning with Flow Matching

Authors: Yuan Gao, Jian Huang, Yuling Jiao, Shurong Zheng

Organizations: Department of Applied Mathematics, The Hong Kong Polytechnic University, Hong Kong SAR, China · School of Mathematics and Statistics and Hubei Key Laboratory of Computational Science, Wuhan University, Wuhan, China · School of Mathematics and Statistics, Northeast Normal University, Changchun, China

Abstract

We study distribution learning by flow matching with linear interpolation from a Gaussian source under Gaussian-channel regularity, a condition on the target distribution. For an integer r≥2r\geq2, we establish spatial regularity of order rr for the population velocity, together with temporal Lipschitz continuity on the full interval and local time analyticity before the terminal time. We use these properties to construct a finite multiscale ReLU sieve with a spatial Lipschitz bound independent of the truncation radius. For an exact minimizer of the empirical flow matching risk over this sieve, we obtain an upper bound on the expected Wasserstein-22 error of order n−r/(d+2r)n^{-r/(d+2r)}, up to a logarithmic factor, where nn is the sample size and dd is the dimension. The bound includes Euler discretization up to time one, without early stopping. The conditions hold at r=2r=2 for targets with strongly convex C2C^2 potentials and two-sided Hessian bounds. They also hold at every fixed order r≥2r\geq2 for distributions obtained by convolving a law of bounded support with a nondegenerate isotropic Gaussian. For sufficiently large fixed constants defining the target class, we prove a minimax lower bound of order max⁡{n−1/2,n−(r+1)/(d+2r)}\max\{n^{-1/2},n^{-(r+1)/(d+2r)}\}.

Figures & tables

Explore similar work

CardsList
  1. Explicit Regularization for Flow Matching

    Nov 14, 2026Lars Ruthotto, Eran TreisterFlow MatchingFlow-Based Generative Modeling

  2. Generalization Bounds for Flow-matching Generative Models for Intrinsically Low-dimensional Data

    Oct 2, 2026Saptarshi Chakraborty, Quentin Berthet, Peter L. BartlettFlow MatchingFlow-Based Generative Modeling

  3. Flow Matching under Noisy Latent Structure: Beyond Exact Low-Dimensional Support

    Sep 30, 2026Lifeng Hao, Shaolin JiFlow MatchingFlow-Based Generative Modeling