Collocation approximation by deep neural ReLU networks for parametric elliptic PDEs with lognormal inputs

Abstract

We obtained convergence rates of the collocation approximation by deep ReLU neural networks of solutions to elliptic PDEs with lognormal inputs, parametrized by $\mathbf{y}$ from the non-compact set ${\mathbb{R}}^{\infty }$. The approximation error is measured in the norm of the Bochner space $L_2({\mathbb{R}}^{\infty },V,\gamma )$, where $\gamma$ is the infinite tensor product standard Gaussian probability measure on ${\mathbb{R}}^{\infty }$ and $V$ is the energy space. We also obtained similar results for the case when the lognormal inputs are parametrized on ${\mathbb{R}}^M$ with very large dimension $M$, and the approximation error is measured in the $\sqrt{g_M}$-weighted uniform norm of the Bochner space $L_{\infty }^{\sqrt{g}}({\mathbb{R}}^M,V)$, where $g_M$ is the density function of the standard Gaussian probability measure on ${\mathbb{R}}^M$.

References in corpus (2)

• Adaptivity of deep ReLU network for learning in Besov and mixed smooth Besov spaces: optimal rate and curse of dimensionality
• Nonlinear Approximation and (Deep) ReLU Networks