no code implementations • 18 Apr 2024 • Anna Shalova, André Schlichting, Mark Peletier
In this regime the set of global minimizers of the loss is large, and when initialized in a neighbourhood of this zero-loss set a noisy gradient descent algorithm slowly evolves along this set.
no code implementations • 15 Feb 2021 • Víctor Navarro-Fernández, André Schlichting, Christian Seis
This paper contains two main contributions.
Analysis of PDEs