no code implementations • 23 Jan 2024 • Daniel Dold, David Rügamer, Beate Sick, Oliver Dürr
To this end, we extend subspace inference for joint posterior sampling from a full parameter space for structured effects and a subspace for unstructured effects.
1 code implementation • 24 Aug 2023 • Kai Brach, Beate Sick, Oliver Dürr
We demonstrate that our single-shot MC dropout approximation resembles the point estimate and the uncertainty estimate of the predictive distribution that is achieved with an MC approach, while being fast enough for real-time deployments of BNNs.
no code implementations • 25 May 2022 • Lucas Kook, Andrea Götschi, Philipp FM Baumann, Torsten Hothorn, Beate Sick
We propose a novel transformation ensemble which aggregates probabilistic predictions with the guarantee to preserve interpretability and yield uniformly better predictions than the ensemble members on average.
2 code implementations • 29 Apr 2022 • Marcel Arpogaus, Marcus Voss, Beate Sick, Mark Nigge-Uricher, Oliver Dürr
The transition to a fully renewable energy grid requires better forecasting of demand at the low-voltage level to increase efficiency and ensure reliable control.
1 code implementation • 11 Feb 2022 • Oliver Dürr, Stephan Hörling, Daniel Dold, Ivonne Kovylov, Beate Sick
Variational inference (VI) is a technique to approximate difficult to compute posteriors by optimization.
1 code implementation • 1 Jun 2021 • Sefan Hörtling, Daniel Dold, Oliver Dürr, Beate Sick
In Bayesian neural networks, variational inference is widely used to approximate difficult-to-compute posteriors by variational distributions.
1 code implementation • 20 Jan 2021 • Lucas Kook, Beate Sick, Peter Bühlmann
In a causally inspired perspective on OOD generalization, the test data arise from a specific class of interventions on exogenous random variables of the DGP, called anchors.
Methodology
1 code implementation • 16 Oct 2020 • Lucas Kook, Lisa Herzog, Torsten Hothorn, Oliver Dürr, Beate Sick
We present ordinal neural network transformation models (ONTRAMs), which unite DL with classical ordinal regression approaches.
2 code implementations • 13 Aug 2020 • Lisa Herzog, Elvis Murina, Oliver Dürr, Susanne Wegener, Beate Sick
For patient-level diagnoses, different aggregation methods are proposed and evaluated, which combine the single image-level predictions.
1 code implementation • 7 Jul 2020 • Kai Brach, Beate Sick, Oliver Dürr
We demonstrate that our single shot MC dropout approximation resembles the point estimate and the uncertainty estimate of the predictive distribution that is achieved with an MC approach, while being fast enough for real-time deployments of BDNNs.
2 code implementations • 1 Apr 2020 • Beate Sick, Torsten Hothorn, Oliver Dürr
Deep learning is known for outstandingly accurate predictions on complex data but in regression tasks, it is predominantly used to just predict a single number.