Stephan Wojtowytsch

activity

20132026

most citedTowards a Mathematical Understanding of Neural Network-Based Machine Learning: what we know and what we don't

50 citations · 193 across the 27 of their papers we have counts for

collaborators

Showing 2025Show all

2 papers · 1 filter

math.NA2025

Convex-concave splitting for the Allen-Cahn equation leads to $ε^{2}$ -slow movement of interfaces

Patrick Dondl, Akwum Onwunta, Ludwig Striet +1

The convex-concave splitting discretization of the Allen-Cahn is easy to implement and guaranteed to be energy decreasing even for large time-steps. We analyze the time-stepping sc…

math.AP2025

Momentum-based minimization of the Ginzburg-Landau functional on Euclidean spaces and graphs

Oluwatosin Akande, Patrick Dondl, Kanan Gupta +2

We study the momentum-based minimization of a diffuse perimeter functional on Euclidean spaces and on graphs with applications to semi-supervised classification tasks in machine le…

Convex-concave splitting for the Allen-Cahn equation leads to ε2-slow movement of interfaces

Momentum-based minimization of the Ginzburg-Landau functional on Euclidean spaces and graphs

Convex-concave splitting for the Allen-Cahn equation leads to $ε^{2}$ -slow movement of interfaces