no code implementations • 3 May 2024 • David Rügamer, Chris Kolb, Tobias Weber, Lucas Kook, Thomas Nagler
The complexity of black-box algorithms can lead to various challenges, including the introduction of biases.
1 code implementation • 16 Mar 2024 • David Rundel, Julius Kobialka, Constantin von Crailsheim, Matthias Feurer, Thomas Nagler, David Rügamer
The recently developed Prior-Data Fitted Networks (PFNs) have shown very promising results for applications in low-data regimes.
no code implementations • 30 Dec 2023 • Yusuf Sale, Paul Hofman, Lisa Wimmer, Eyke Hüllermeier, Thomas Nagler
Uncertainty quantification is a critical aspect of machine learning models, providing important insights into the reliability of predictions and aiding the decision-making process in real-world applications.
1 code implementation • 30 Oct 2023 • Nicolai Palm, Thomas Nagler
In this paper, we propose a novel bootstrap method that is designed to account for data dependencies and can be executed online, making it particularly suitable for real-time applications.
no code implementations • 18 May 2023 • Thomas Nagler
The pre-trained model is then used to infer class probabilities in-context on fresh training sets with arbitrary size and distribution.
no code implementations • 17 Feb 2023 • Julian Rodemann, Jann Goschenhofer, Emilio Dorigatti, Thomas Nagler, Thomas Augustin
We derive this selection criterion by proving Bayes optimality of the posterior predictive of pseudo-samples.
no code implementations • 12 Feb 2021 • Kjersti Aas, Thomas Nagler, Martin Jullum, Anders Løland
In this paper we propose two new approaches for modelling the dependence between the features.
1 code implementation • 16 Dec 2020 • David Meyer, Thomas Nagler, Robin J. Hogan
Can we improve machine-learning (ML) emulators with synthetic data?
1 code implementation • 13 Aug 2020 • Thomas Nagler, Daniel Krüger, Aleksey Min
Vine copulas are graphical models for the dependence and can conveniently capture both types of dependence in the same model.
Methodology
1 code implementation • 15 May 2017 • Thomas Nagler
We give an in-depth analysis of the jittering kernel density estimator, which reveals several appealing properties.
Methodology
4 code implementations • 24 Apr 2017 • Thomas Nagler
In this case, any estimator developed in a purely continuous framework extends naturally to the mixed data setting.
Methodology
2 code implementations • 4 Aug 2016 • Thibault Vatter, Thomas Nagler
Pair-copula constructions are flexible dependence models that use bivariate copulas as building blocks.
Methodology