Paul Geuchen
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Paul Geuchen has a total of 3 co-authors. Here are the top co-authors by number of shared publications:
- Dominik Stöger
Department of Mathematics and Mathematical Institute for Machine Learning and Data Science (MIDS) KU Eichstätt- Ingolstadt
1 shared publication Felix Voigtlaender
MIDS, KU Eichstätt-Ingolstadt , Auf der Schanz 49, 85049 Ingolstadt
1 shared publicationThomas Telaar
Chair of Mathematics—Statistics, KU Eichstätt-Ingolstadt , Ostenstraße 28, 85072 Eichstätt
1 shared publication
Latest Publications
- 26 March 2025
- Published by Oxford University Press (OUP) in Information and Inference: A Journal of the IMA
- Vol. 14 (2)
Upper and lower bounds for the Lipschitz constant of random neural networks
Empirical studies have widely demonstrated that neural networks are highly sensitive to small, adversarial perturbations of the input. The worst-case robustness against these so-called adversarial examples can be quantified by the Lipschitz constant of the neural network. In this paper, we study upper and lower bounds for the Lipschitz constant of random ReLU neural networks. Specifically, we assume that the weights and biases follow a generalization of the He initialization, where general symmetric distributions for the biases are permitted. For deep networks of fixed depth and sufficiently large width, our established upper bound is larger than the lower bound by a factor that is logarithmic in the width. In contrast, for shallow neural networks we characterize the Lipschitz constant up to an absolute numerical constant that is independent of all parameters.
- 26 March 2025
- Published by Oxford University Press (OUP) in Information and Inference: A Journal of the IMA
- Vol. 14 (2)
Upper and lower bounds for the Lipschitz constant of random neural networks
Empirical studies have widely demonstrated that neural networks are highly sensitive to small, adversarial perturbations of the input. The worst-case robustness against these so-called adversarial examples can be quantified by the Lipschitz constant of the neural network. In this paper, we study upper and lower bounds for the Lipschitz constant of random ReLU neural networks. Specifically, we assume that the weights and biases follow a generalization of the He initialization, where general symmetric distributions for the biases are permitted. For deep networks of fixed depth and sufficiently large width, our established upper bound is larger than the lower bound by a factor that is logarithmic in the width. In contrast, for shallow neural networks we characterize the Lipschitz constant up to an absolute numerical constant that is independent of all parameters.