activity
20242026
most citedVariationally Correct Neural Residual Regression for Parametric PDEs: On the Viability of Controlled Accuracy

3 citations · 3 across the 4 of their papers we have counts for

collaborators
Showing 2026 · math.NAShow all

1 paper · 2 filters

math.NA2026

Preconditioning and Numerical Stability in Neural Network Training for Parametric PDEs

Markus Bachmayr, Wolfgang Dahmen, Chenguang Duan +1

In the context of training neural network-based approximations of solutions of parameter-dependent PDEs, we investigate the effect of preconditioning via well-conditioned frame rep…