Point interpolation and distributional universality in flow-based generative models
Organizations: Nanyang Technological University, 50 Nanyang Avenue, Singapore 639798. · Department of Mathematics, National University of Singapore, 10 Lower Kent Ridge Road, Singapore 119076. · Institute for Functional Intelligent Materials, National University of Singapore, 10 Lower Kent Ridge Road, Singapore 119076.
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 -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 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.
Figures & tables
Flow-Based Generative Modeling
Flow-based generative modeling learns probability transports from simple noise to data for fast sampling, density estimation, and controllable generation.
See all 610 papers