← Search

Sander Hummerich

2 accepted papers

2024

Learning Distributions on Manifolds with Free-Form Flows

NeurIPS 2024poster

We propose Manifold Free-Form Flows (M-FFF), a simple new generative model for data on manifolds. The existing approaches to learning a distribution on arbitrary manifolds are expensive at inference time, since sampling requires solving a differential equation. Our method overcomes this limitation b…

2024

Lifting Architectural Constraints of Injective Flows

ICLR 2024poster

Normalizing Flows explicitly maximize a full-dimensional likelihood on the training data. However, real data is typically only supported on a lower-dimensional manifold leading the model to expend significant compute on modeling noise. Injective Flows fix this by jointly learning a manifold and the…

Cited by 11SourcePDFScholar