5 papers
Scalable generative modeling of non-Gaussian spatio-temporal fields via autoregressive Gaussian processes
Carrie J. Lei-Cramer, Jian Cao, Matthias Katzfuss
Generative modeling of spatio-temporal fields is crucial for a variety of applications, including stochastic weather generators and climate-model surrogates. However, many such fie…
Sparse inverse Cholesky factorization of dense kernel matrices by greedy conditional selection
Stephen Huan, Joseph Guinness, Matthias Katzfuss +2
Dense kernel matrices resulting from pairwise evaluations of a kernel function arise naturally in machine learning and statistics. Previous work in constructing sparse approximate…
Vecchia Gaussian Process Ensembles on Internal Representations of Deep Neural Networks
Felix Jimenez, Matthias Katzfuss
For regression tasks, standard Gaussian processes (GPs) provide natural uncertainty quantification (UQ), while deep neural networks (DNNs) excel at representation learning. Determi…
Learning non-Gaussian spatial distributions via Bayesian transport maps with parametric shrinkage
Anirban Chakraborty, Matthias Katzfuss
Many applications, including climate-model analysis and stochastic weather generators, require learning or emulating the distribution of a high-dimensional and non-Gaussian spatial…
Probabilistic Skip Connections for Deterministic Uncertainty Quantification in Deep Neural Networks
Felix Jimenez, Matthias Katzfuss
Deterministic uncertainty quantification (UQ) in deep learning aims to estimate uncertainty with a single pass through a network by leveraging outputs from the network's feature ex…