← Search

Josua Sassen

2 accepted papers

2026

Geodesic Calculus on Implicitly Defined Latent Manifolds

ICML 2026poster

Latent manifolds of autoencoders provide low-dimensional representations of data, which can be studied from a geometric perspective. We propose to describe these latent manifolds as implicit submanifolds of some ambient latent space. Based on this, we develop tools for a discrete Riemannian calculus…

Cited by 0SourceScholar
2023

Parametrizing Product Shape Manifolds by Composite Networks

ICLR 2023top-25%

Parametrizations of data manifolds in shape spaces can be computed using the rich toolbox of Riemannian geometry. This, however, often comes with high computational costs, which raises the question if one can learn an efficient neural network approximation. We show that this is indeed possible for s…