Author

Holger Rauhut

2 papers indexed here

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

Preprint Oct 2026

Implicit Bias of (Stochastic) Gradient Descent on Deep Linear Diagonal Networks

Modern machine learning models are often overparameterized, i.e., have more parameters than training data. This typically implies that the loss function admits multiple minimizers so that training methods (and their hyperparameter choices) have significant influence on the computed solution. We study this so-called imp...

Wiebke Bartolomaeus, Holger Rauhut · 1 citation

Preprint Oct 2026

Convergence of stochastic gradient descent for learning linear neural networks

Stochastic gradient descent (SGD) is the cornerstone of modern deep learning, yet its theoretical convergence properties remain poorly understood in non-convex settings. To address this gap, we study SGD dynamics in deep linear neural networks - simplified models that retain key non-convex characteristics while remaini...

Gabin Maxime Nguegnang, B. Bah, Holger Rauhut et al. · 0 citations