כתבה
arXiv cs.LG ·
Diffusion Flow Matching: Dimension-Improved KL Bounds and Wasserstein Guarantees
נשיאים חדשים להבטחות קונברגנס של Diffusion Flow Matching
תקציר מקורי באנגליתarXiv:2606.16610v2 Announce Type: replace-cross Abstract: Diffusion Flow Matching (DFM) has recently emerged as a versatile framework for generative modeling, yet its theoretical convergence properties remain only partially understood. In this work, we provide refined and novel convergence guarantees for Brownian motion based DFMs, focusing on the discretization error. Our analysis is conducted under the Kullback-Leibler (KL) divergence and the 2-Wasserstein distance. Under finite-moment conditions and a mild score integrability assumption, we derive KL convergence bounds with improved dimensional dependence compared to prior work, achieving, up to our knowledge, state-of-the-art scaling under minimal conditions. We further extend the analysis to the 2-Wasserstein distance: under an additi
קרא במקור המקורי
arxiv.org
פתח כתבה מקורית