Patrick Finke

collaborators

2 papers

stat.ML2025

Near-optimal estimates for the $ℓ^{p}$ -Lipschitz constants of deep random ReLU neural networks

Sjoerd Dirksen, Patrick Finke, Paul Geuchen +2

This paper studies the $ℓ^{p}$ -Lipschitz constants of ReLU neural networks $I^¦ : R^{d} \to R$ with random parameters for $p \in [1, \infty]$ . The distribution of the…

stat.ML2024

Memorization With Neural Nets: Going Beyond the Worst Case

Sjoerd Dirksen, Patrick Finke, Martin Genzel

In practice, deep neural networks are often able to easily interpolate their training data. To understand this phenomenon, many works have aimed to quantify the memorization capaci…

Near-optimal estimates for the ℓp-Lipschitz constants of deep random ReLU neural networks

Memorization With Neural Nets: Going Beyond the Worst Case

Near-optimal estimates for the $ℓ^{p}$ -Lipschitz constants of deep random ReLU neural networks