Can Deep Generative Models Reproduce Non-Stationary Gaussian Random Fields?
Daniel Kua, Yan Song
stat.ML, cs.LG
Submitted: 2026-07-28
Comments: 9 pages, 4 figures, 2 tables
Code: https://github.com/AntixK/PyTorch-VAE
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Terminology
Sources
- Predictive posterior sampling from non-stationnary Gaussian process priors via Diffusion models with application to climate data
- Flow Matching Guide and Code
- Review: Nonstationary Spatial Modeling, with Emphasis on Process Convolution and Covariate-Driven Approaches
- Neural Conditional Simulation for Complex Spatial Processes
- Latent Generative Modeling of Random Fields from Limited Training Data
Related papers
- Behavior of prediction performance metrics with rare events
- Optimal Estimation of Generic Dynamics by Path-Dependent Neural Jump ODEs
- A Posterior-Dynamics Framework for Imaging Inverse Problems with Pretrained Diffusion Priors
- Scalable Posterior Uncertainty for Flexible Density-Based Clustering
- A Transport Geometry of Benign Overfitting
- Efficient quadratic entropy with distance sketches