A neural network compresses high-dimensional PDE coordinates into a low-dimensional latent space, where a PDE-constrained Gaussian process achieves accurate solutions and uncertainty estimates on test problems up to 50 dimensions.
Finite element method—the natural approach
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
PDE-DKL: PDE-constrained deep kernel learning in high dimensionality
A neural network compresses high-dimensional PDE coordinates into a low-dimensional latent space, where a PDE-constrained Gaussian process achieves accurate solutions and uncertainty estimates on test problems up to 50 dimensions.