AI RESEARCH
A Unified Framework for Data-Free One-Step Sampling via Wasserstein Gradient Flows
arXiv CS.LG
•
ArXi:2605.17808v1 Announce Type: new We develop a unified theoretical framework for data-free one-step sampling from unnormalized target distributions based on Wasserstein gradient flows. For a broad class of standard f-divergence objectives, we show that the induced velocity field admits the universal form $\mathbf{V}(x)=w(r(x))\,\beta(x)$, where $\beta(x)=\nabla \log (p(x)/q(x))$ is shared across objectives and $w$ is determined solely by the choice of divergence.