Showing cs.LGShow all
3 papers · 1 filter
cs.LG2023
On the Convergence Rate of Gaussianization with Random Rotations
Felix Draxler, Lars Kühmichel, Armand Rousselot +3
Gaussianization is a simple generative model that can be trained without backpropagation. It has shown compelling performance on low dimensional data. As the dimension increases, h…
cs.LG2023
Finding Competence Regions in Domain Generalization
Jens Müller, Stefan T. Radev, Robert Schmier +3
We investigate a "learning to reject" framework to address the problem of silent failures in Domain Generalization (DG), where the test distribution differs from the training distr…
cs.LG2020
Learning Robust Models Using The Principle of Independent Causal Mechanisms
Jens Müller, Robert Schmier, Lynton Ardizzone +2
Standard supervised learning breaks down under data distribution shift. However, the principle of independent causal mechanisms (ICM, Peters et al. (2017)) can turn this weakness i…