AI RESEARCH

Expressivity of Bi-Lipschitz Normalizing Flows: A Score-Based Diffusion Perspective

arXiv CS.LG

ArXi:2605.06172v1 Announce Type: cross Many normalizing flow architectures impose regularity constraints, yet their distributional approximation properties are not fully characterized. We study the expressivity of bi-Lipschitz normalizing flows through the lens of score-based diffusion models. For the probability flow ODE of a variance-preserving diffusion, Lipschitz regularity of the score induces a flow of bi-Lipschitz diffeomorphic transport maps.