Geometric Dynamic Variational Autoencoders (GD-VAEs) for learning embedding maps for nonlinear dynamics into general latent spaces. This includes methods for standard latent spaces or manifold latent spaces with specified geometry and topology. The manifold latent spaces can be based on analytic expressions or general point cloud representations.
machine-learning deep-learning point-cloud neural-networks dynamical-systems manifold-learning dimension-reduction geometric-algorithms topological-data-analysis variational-autoencoder parameterized-systems geometric-deep-learning pytorch-implementation autoencoder-neural-network latent-spaces
-
Updated
Apr 25, 2026 - TeX