Dominik Stöger

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 $Φ : R^{d} \to R$ with random parameters for $p \in [1, \infty]$ . The distribution of the…

cs.IT2023

How robust is randomized blind deconvolution via nuclear norm minimization against adversarial noise?

Julia Kostin, Felix Krahmer, Dominik Stöger

In this paper, we study the problem of recovering two unknown signals from their convolution, which is commonly referred to as blind deconvolution. Reformulation of blind deconvolu…

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

How robust is randomized blind deconvolution via nuclear norm minimization against adversarial noise?

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