首页 > AI前沿 > Flow Matching from Non-Gaussian Sources: A Theory of Efficient Sampling

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

arXiv机器学习 2026-11-20 00:54 11 阅读 查看原文

Flow Matching的框架与优势

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.

收敛理论与结果

We establish a nonasymptotic convergence theory for Euler discretization of flow matching with linear interpolation.

Suppose the source distribution on $\mathbb{R}^d$ has an everywhere positive, continuously differentiable density, finite total variance $\mathsf{TotVar}_{\mathsf{base}}$, and an $L$-Lipschitz score.

Using the population velocity field and a suitable time grid, this sampler achieves total variation error at most $\varepsilon$ in $\widetilde{O}(Ld\mathsf{TotVar}_{\mathsf{base}}/\varepsilon)$ iterations, provided the target distribution satisfies a mild second-moment condition.

These assumptions cover, among many examples, source distributions such as multivariate Student's $t$ 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.