Convergence analysis of OT-Flow for sample generation

arXiv:2403.16208v1 Announce Type: cross
Abstract: Deep generative models aim to learn the underlying distribution of data and generate new ones. Despite the diversity of generative models and their high-quality generation performance in practice, most of them lack rigorous theoretical convergence proofs. In this work, we aim to establish some convergence results for OT-Flow, one of the deep generative models. First, by reformulating the framework of OT-Flow model, we establish the $\Gamma$-convergence of the formulation of OT-flow to the corresponding optimal …

abstract aim analysis arxiv convergence cs.lg cs.na data deep generative models distribution diversity flow generate generative generative models learn math.na performance practice quality results sample them type work