activity
20182022
most citedIdentifying Untrustworthy Predictions in Neural Networks by Geometric Gradient Analysis

2 citations · 4 across the 3 of their papers we have counts for

collaborators

7 papers

cs.LG20222 cited

Improving Robustness against Real-World and Worst-Case Distribution Shifts through Decision Region Quantification

Leo Schwinn, Leon Bungert, An Nguyen +5

The reliability of neural networks is essential for their use in safety-critical applications. Existing approaches generally aim at improving the robustness of neural networks to e…

cs.LG2021

Neural Architecture Search via Bregman Iterations

Leon Bungert, Tim Roith, Daniel Tenbrinck +1

We propose a novel strategy for Neural Architecture Search (NAS) based on Bregman iterations. Starting from a sparse neural network our gradient-based one-shot algorithm gradually…

cs.LG20212 cited

Identifying Untrustworthy Predictions in Neural Networks by Geometric Gradient Analysis

Leo Schwinn, An Nguyen, René Raab +5

The susceptibility of deep neural networks to untrustworthy predictions, including out-of-distribution (OOD) data and adversarial examples, still prevent their widespread use in sa…

math.NA2020

Variational regularisation for inverse problems with imperfect forward operators and general noise models

Leon Bungert, Martin Burger, Yury Korolev +1

We study variational regularisation methods for inverse problems with imperfect forward operators whose errors can be modelled by order intervals in a partial order of a Banach lat…

math.AP2020

Structural analysis of an -infinity variational problem and relations to distance functions

Leon Bungert, Yury Korolev, Martin Burger

In this work we analyse the functional defined on Lipschitz functions with homogeneous Dirichlet boundary conditions. Our analysis is performed di…

math.AP2019

Asymptotic Profiles of Nonlinear Homogeneous Evolution Equations of Gradient Flow Type

Leon Bungert, Martin Burger

This work is concerned with the gradient flow of absolutely -homogeneous convex functionals on a Hilbert space, which we show to exhibit finite () or infinite extinction ti…