collaborators

5 papers

math.NA2026

Sampling and reconstruction of convex functions

Andrea Bonito, Albert Cohen, Wolfgang Dahmen +3

We discuss optimal recovery for classes of multivariate convex functions from given point samples, as well as the sampling numbers of these classes, corresponding to optimal sample…

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…

math.NA2025

Variationally correct operator learning: Reduced basis neural operator with a posteriori error estimation

Yuan Qiu, Wolfgang Dahmen, Peng Chen

Minimizing PDE-residual losses is a common strategy to promote physical consistency in neural operators. However, standard formulations often lack variational correctness, meaning…

math.OC2025

Expansive Natural Neural Gradient Flows for Energy Minimization

Wolfgang Dahmen, Wuchen Li, Yuankai Teng +1

This paper develops expansive gradient dynamics in deep neural network-induced mapping spaces. Specifically, we generate tools and concepts for minimizing a class of energy functio…

math.NA2025

DPG loss functions for learning parameter-to-solution maps by neural networks

Pablo Cortés Castillo, Wolfgang Dahmen, Jay Gopalakrishnan

We develop, analyze, and experimentally explore residual-based loss functions for machine learning of parameter-to-solution maps in the context of parameter-dependent families of p…