Paperlane

no. 8 · Wednesday 4 November 2026

Point interpolation and distributional universality in flow-based generative models

Antonio Álvarez-López, Jingpu Cheng, Liyan Zhang and Qianxiao Li

math.OC · via stat.ML · 45 pp

Abstract

Motivated by the expressive power of neural ordinary differential equations in flow-based generative modeling, we study the approximation of probability measures by pushforwards generated by parameterized families of Lipschitz vector fields. For Wasserstein distances, we establish a quantitative relationship between finite-sample point interpolation and distributional approximation, and derive universality criteria based on $L^p$-approximation of transport maps. In particular, affine-invariant families containing a non-affine vector field are universal from compactly supported absolutely continuous base measures. For total variation, we show that coordinate-wise dynamics are insufficient in dimensions $d\geq 2$ and establish sufficient conditions based on one-dimensional Sobolev approximation and shear-type mixing. We further examine the role of point interpolation, establishing when different regimes relate to one another and when approximate interpolation can be made exact.

comments
45 pages, 3 figures
fields
Optimization and Control
pdf ↗ page arXiv:2611.04207 ↗