Oral
in
Workshop: Deep Generative Model in Machine Learning: Theory, Principle and Efficacy
Towards Variational Flow Matching on General Geometries
Olga Zaghen · Floor Eijkelboom · Alison Pouplin · Erik Bekkers
Keywords: [ generative modeling ] [ flow matching ] [ variational inference ] [ general manifolds ]
We introduce Riemannian Gaussian Variational Flow Matching (RG-VFM), an extension of Variational Flow Matching (VFM) that leverages Riemannian Gaussian distributions for generative modeling on structured manifolds. We derive a variational objective for probability flows on manifolds with closed-form geodesics, making RG-VFM comparable -- though fundamentally different to Riemannian Flow Matching (RFM) in this geometric setting. Experiments on a checkerboard dataset wrapped on the sphere demonstrate that RG-VFM captures geometric structure more effectively than Euclidean VFM and baseline methods, establishing it as a robust framework for manifold-aware generative modeling.