Uniform Convergence Guarantees for the Deep Ritz Method for Nonlinear Problems

11/10/2021

∙

We provide convergence guarantees for the Deep Ritz Method for abstract variational energies. Our results cover non-linear variational problems such as the p-Laplace equation or the Modica-Mortola energy with essential or natural boundary conditions. Under additional assumptions, we show that the convergence is uniform across

READ FULL TEXT

Uniform Convergence Guarantees for the Deep Ritz Method for Nonlinear Problems

Abstract error analysis for Cahn–Hilliard type equations with dynamic boundary conditions

Error Estimates for the Variational Training of Neural Networks with Boundary Penalty

A variational neural network approach for glacier modelling with nonlinear rheology

A Smoothness Energy without Boundary Distortion for Curved Surfaces

Spiral capacitor calculation using FEniCS

Non-probabilistic Supervised Learning for Non-linear Convex Variational Problems

Convergence Analysis For Non Linear System Of Parabolic Variational Inequalities

Uniform Convergence Guarantees for the Deep Ritz Method for Nonlinear Problems

Related Research

Abstract error analysis for Cahn–Hilliard type equations with dynamic boundary conditions

Error Estimates for the Variational Training of Neural Networks with Boundary Penalty

A variational neural network approach for glacier modelling with nonlinear rheology

A Smoothness Energy without Boundary Distortion for Curved Surfaces

Spiral capacitor calculation using FEniCS

Non-probabilistic Supervised Learning for Non-linear Convex Variational Problems

Convergence Analysis For Non Linear System Of Parabolic Variational Inequalities