A new Gaussian process kernel, derived from a stochastic PDE with boundary conditions, enforces Dirichlet, Neumann, or Robin boundaries on irregular domains with smoothness control and provable approximation error.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
stat.ME 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
The BdryMat\'ern GP: Reliable incorporation of boundary information on irregular domains for Gaussian process modeling
A new Gaussian process kernel, derived from a stochastic PDE with boundary conditions, enforces Dirichlet, Neumann, or Robin boundaries on irregular domains with smoothness control and provable approximation error.