Search Results for author: Andrew Gracyk

Found 2 papers, 1 papers with code

Ricci flow-guided autoencoders in learning time-dependent dynamics

1 code implementation26 Jan 2024 Andrew Gracyk

We present a manifold-based autoencoder method for learning nonlinear dynamics in time, notably partial differential equations (PDEs), in which the manifold latent space evolves according to Ricci flow.

GeONet: a neural operator for learning the Wasserstein geodesic

no code implementations28 Sep 2022 Andrew Gracyk, Xiaohui Chen

Optimal transport (OT) offers a versatile framework to compare complex data distributions in a geometrically meaningful way.

Cannot find the paper you are looking for? You can Submit a new open access paper.