Deep learning methods for stochastic Galerkin approximations of random domain problems

DOI10.48550/arXiv.2609.32508MaRDI QIDQ7360690arXivFDO

Authors Fabio Musco, Andrea Barth

Publication date 26 September 2026

Published in arXiv

Tldr Deep learning techniques are applied to approximate solutions of random domain problems for elliptic PDEs by replacing traditional numerical solvers with neural networks. We compare physics-informed neural network (PINN) and Deep Ritz methods, both using surrogate deterministic spectral coefficients.

Full work available at URL https://doi.org/10.48550/arXiv.2609.32508

arXiv classification

math.NA

Cites work

• A hybrid collocation-perturbation approach for PDEs with random domains
• A Sparse Grid Stochastic Collocation Method for Partial Differential Equations with Random Input Data
• A Stochastic Collocation Method for Elliptic Partial Differential Equations with Random Input Data
• Analysis of the domain mapping method for elliptic diffusion problems on random domains
• Analytic regularity and collocation approximation for elliptic PDEs with random domain deformations
• Application of quasi-Monte Carlo methods to elliptic PDEs with random diffusion coefficients: a survey of analysis and implementation
• Approximation by superpositions of a sigmoidal function
• Approximation properties of a multilayered feedforward artificial neural network
• Assessment of collocation and Galerkin approaches to linear diffusion equations with random data
• Automated solution of differential equations by the finite element method. The FEniCS book
• Convergence rates for sparse chaos approximations of elliptic problems with stochastic coefficients
• Convergence rates of best \(N\)-term Galerkin approximations for a class of elliptic SPDEs
• Deep learning
• Deep learning methods for stochastic Galerkin approximations of elliptic random PDEs
• DGM: a deep learning algorithm for solving partial differential equations
• Enforcing Dirichlet boundary conditions in physics-informed neural networks and variational physics-informed neural networks
• Exact imposition of boundary conditions with distance functions in physics-informed deep neural networks
• FastVPINNs: tensor-driven acceleration of VPINNs for complex geometries
• Finite elements for elliptic problems with stochastic coefficients
• Foundations of Modern Probability
• Machine learning approximation algorithms for high-dimensional fully nonlinear partial differential equations and second-order backward stochastic differential equations
• Matrix Analysis
• Measure theory
• Modeling uncertainty in steady state diffusion problems via generalized polynomial chaos
• Multi-level Monte Carlo finite element method for elliptic PDEs with stochastic coefficients
• Multilayer feedforward networks are universal approximators
• Multilevel quadrature for elliptic problems on random domains by the coupling of FEM and BEM
• Numerical Methods for Differential Equations in Random Domains
• On elliptic partial differential equations with random coefficients
• On homogeneous chaos
• On the convergence of the stochastic Galerkin method for random elliptic partial differential equations
• On the distribution of points in a cube and the approximate evaluation of integrals
• Physics-informed PointNet: a deep learning solver for steady-state incompressible flows and thermal fields on multiple sets of irregular geometries
• Scientific Machine Learning through Physics-Informed Neural Networks: Where we are and What's next
• Solution of stochastic partial differential equations using Galerkin finite element techniques
• Solving elliptic boundary value problems with uncertain coefficients by the finite element method: the stochastic formulation
• Solving high-dimensional partial differential equations using deep learning
• Sparse tensor discretizations of high-dimensional parametric and stochastic PDEs
• Stochastic finite elements of discretely parameterized random systems on domains with boundary uncertainty
• The Deep Ritz Method for Parametric $p$-Dirichlet Problems
• The deep Ritz method: a deep learning-based numerical algorithm for solving variational problems
• The Wiener--Askey Polynomial Chaos for Stochastic Differential Equations
• Three ways to solve partial differential equations with neural networks — A review
• Uncertainty quantification for random domains using periodic random variables
• Variational Physics Informed Neural Networks: the role of quadratures and test functions
• Variational Physics-Informed Neural Networks For Solving Partial Differential Equations

This page was built for publication: Deep learning methods for stochastic Galerkin approximations of random domain problems

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q7360690)