AI RESEARCH
Finite-Particle Convergence Rates for Conservative and Non-Conservative Drifting Models
arXiv CS.AI
•
ArXi:2605.22795v1 Announce Type: cross We propose and analyze a conservative drifting method for one-step generative modeling. The method replaces the original displacement-based drifting velocity by a kernel density estimator (KDE)-gradient velocity, namely the difference of the kernel-smoothed data score and the kernel-smoothed model score. This velocity is a gradient field, addressing the non-conservatism issue identified for general displacement-based drifting fields.