A theoretical analysis of deep neural networks and parametric PDEs

G Kutyniok, P Petersen, M Raslan… - Constructive …, 2022 - Springer
We derive upper bounds on the complexity of ReLU neural networks approximating the
solution maps of parametric partial differential equations. In particular, without any …

Deep learning in high dimension: Neural network expression rates for generalized polynomial chaos expansions in UQ

C Schwab, J Zech - Analysis and Applications, 2019 - World Scientific
We estimate the expressive power of certain deep neural networks (DNNs for short) on a
class of countably-parametric, holomorphic maps u: U→ ℝ on the parameter domain U=[− 1 …

Sparse polynomial approximation of parametric elliptic PDEs. Part II: lognormal coefficients

M Bachmayr, A Cohen, R DeVore… - … Modelling and Numerical …, 2017 - numdam.org
Sparse polynomial approximation of parametric elliptic PDEs. Part II: lognormal coefficients∗
Page 1 ESAIM: M2AN 51 (2017) 341–363 ESAIM: Mathematical Modelling and Numerical …

Convergence rates of high dimensional Smolyak quadrature

J Zech, C Schwab - ESAIM: Mathematical Modelling and …, 2020 - esaim-m2an.org
We analyse convergence rates of Smolyak integration for parametric maps u: U→ X taking
values in a Banach space X, defined on the parameter domain U=[− 1, 1] N. For parametric …

Convergence of sparse collocation for functions of countably many Gaussian random variables (with application to elliptic PDEs)

OG Ernst, B Sprungk, L Tamellini - SIAM Journal on Numerical Analysis, 2018 - SIAM
We give a convergence proof for the approximation by sparse collocation of Hilbert-space-
valued functions depending on countably many Gaussian random variables. Such functions …

Reduced basis greedy selection using random training sets

A Cohen, W Dahmen, R DeVore… - … Modelling and Numerical …, 2020 - esaim-m2an.org
Reduced bases have been introduced for the approximation of parametrized PDEs in
applications where many online queries are required. Their numerical efficiency for such …

Fully discrete approximation of parametric and stochastic elliptic PDEs

M Bachmayr, A Cohen, D Dung, C Schwab - SIAM Journal on Numerical …, 2017 - SIAM
It has recently been demonstrated that locality of spatial supports in the parametrization of
coefficients in elliptic PDEs can lead to improved convergence rates of sparse polynomial …