Deep Learning Methods for Stochastic Galerkin Approximations of Random Domain Problems
My rating
The paper studies strong and weak stochastic Galerkin approximations for random elliptic partial differential equations. It uses a sufficiently regular random-domain mapping to transform the problem onto a deterministic reference domain, then applies deep learning techniques in place of a traditional numerical solver for the resulting high-dimensional coupled stochastic Galerkin systems.
Tags: