Search Results for author: Marius Zeinhofer

Found 2 papers, 0 papers with code

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

no code implementations1 Mar 2021 Johannes Müller, Marius Zeinhofer

For non-essential boundary conditions the error of the Ritz method decays with the same rate as the approximation rate of the ansatz classes.

Deep Ritz revisited

no code implementations9 Dec 2019 Johannes Müller, Marius Zeinhofer

In this notes we use the notion of $\Gamma$-convergence to show that ReLU networks of growing architecture that are trained with respect to suitably regularised Dirichlet energies converge to the true solution of the Poisson problem.

Cannot find the paper you are looking for? You can Submit a new open access paper.