GD-VAEs: Geometric Dynamic Variational Autoencoders for Learning Nonlinear Dynamics and Dimension Reductions
Paper
•
2206.05183
•
Published
Paul J. Atzberger
atzberg
AI & ML interests
Geometric Deep Learning, Foundation Models, Scientific Machine Learning, Learning Theory, Applications in the Sciences and Engineering
Recent Activity
authored
a paper
1 day ago
GD-VAEs: Geometric Dynamic Variational Autoencoders for Learning Nonlinear Dynamics and Dimension Reductions
authored
a paper
1 day ago
Sparse $L^1$-Autoencoders for Scientific Data Compression
Organizations
None yet
authored
10
papers
1 day ago
Transferable Foundation Models for Geometric Tasks on Point Cloud Representations: Geometric Neural Operators
Paper
•
2503.04649
•
Published
Sparse $L^1$-Autoencoders for Scientific Data Compression
Paper
•
2405.14270
•
Published
SDYN-GANs: Adversarial Learning Methods for Multistep Generative Models for General Order Stochastic Dynamics
Paper
•
2302.03663
•
Published
MLMOD: Machine Learning Methods for Data-Driven Modeling in LAMMPS
Paper
•
2107.14362
•
Published
Variational Autoencoders for Learning Nonlinear Dynamics of Physical Systems
Paper
•
2012.03448
•
Published
Meshfree Methods on Manifolds for Hydrodynamic Flows on Curved Surfaces: A Generalized Moving Least-Squares (GMLS) Approach
Paper
•
1905.10469
•
Published
GMLS-Nets: A framework for learning from unstructured data
Paper
•
1909.05371
•
Published
Importance of the Mathematical Foundations of Machine Learning Methods for Scientific and Engineering Applications
Paper
•
1808.02213
•
Published
Geometric Neural Operators (GNPs) for Data-Driven Deep Learning of Non-Euclidean Operators
Paper
•
2404.10843
•
Published