Curvature-flow-regularized latent spaces improve mean out-of-distribution errors for Burger's equation relative to a plain autoencoder, but the flows are heuristic and the evidence is limited.
GD-VAEs: Geometric Dynamic Variational Autoencoders for Learning Nonlinear Dynamics and Dimension Reductions
1 Pith paper cite this work. Polarity classification is still indexing.
abstract
We develop data-driven methods incorporating geometric and topological information to learn parsimonious representations of nonlinear dynamics from observations. The approaches learn nonlinear state-space models of the dynamics for general manifold latent spaces using training strategies related to Variational Autoencoders (VAEs). Our methods are referred to as Geometric Dynamic (GD) Variational Autoencoders (GD-VAEs). We learn encoders and decoders for the system states and evolution based on deep neural network architectures that include general Multilayer Perceptrons (MLPs), Convolutional Neural Networks (CNNs), and other architectures. Motivated by problems arising in parameterized PDEs and physics, we investigate the performance of our methods on tasks for learning reduced dimensional representations of the nonlinear Burgers Equations, Constrained Mechanical Systems, and spatial fields of Reaction-Diffusion Systems. GD-VAEs provide methods that can be used to obtain representations in manifold latent spaces for diverse learning tasks involving dynamics.
citation-role summary
citation-polarity summary
fields
math.NA 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
unclear 1representative citing papers
citing papers explorer
-
Geometric flow regularization in latent spaces for smooth dynamics with the efficient variations of curvature
Curvature-flow-regularized latent spaces improve mean out-of-distribution errors for Burger's equation relative to a plain autoencoder, but the flows are heuristic and the evidence is limited.