1 code implementation • 24 Feb 2024 • Fan Yang, Pierre Le Bodic, Michael Kamp, Mario Boley
Gradient boosting of prediction rules is an efficient approach to learn potentially interpretable yet accurate probabilistic models.
no code implementations • 27 Nov 2023 • Mario Boley, Felix Luong, Simon Teshuva, Daniel F Schmidt, Lucas Foppa, Matthias Scheffler
Materials discovery driven by statistical property models is an iterative decision process, during which an initial data collection is extended with new data proposed by a model-informed acquisition function--with the goal to maximize a certain "reward" over time, such as the maximum property value discovered so far.
1 code implementation • 21 Jan 2021 • Mario Boley, Simon Teshuva, Pierre Le Bodic, Geoffrey I Webb
Rule ensembles are designed to provide a useful trade-off between predictive accuracy and model interpretability.
no code implementations • 6 Sep 2020 • Kailash Budhathoki, Mario Boley, Jilles Vreeken
Moreover, to discover reliable causal rules from a sample, we propose a conservative and consistent estimator of the causal effect, and derive an efficient and exact algorithm that maximises the estimator.
1 code implementation • NeurIPS 2021 • Henning Petzka, Michael Kamp, Linara Adilova, Cristian Sminchisescu, Mario Boley
Flatness of the loss curve is conjectured to be connected to the generalization ability of machine learning models, in particular neural networks.
no code implementations • 28 Nov 2019 • Michael Kamp, Mario Boley, Michael Mock, Daniel Keren, Assaf Schuster, Izchak Sharfman
The learning performance of such a protocol is intuitively optimal if approximately the same loss is incurred as in a hypothetical serial setting.
no code implementations • 28 Nov 2019 • Michael Kamp, Sebastian Bothe, Mario Boley, Michael Mock
It extends a previously presented protocol to kernelized online learners that represent their models by a support vector expansion.
1 code implementation • 30 Aug 2019 • Panagiotis Mandros, Mario Boley, Jilles Vreeken
This raises many questions, such as how to reliably and interpretably measure correlation between a multivariate set of attributes, how to do so without having to make assumptions on distribution of the data or the type of correlation, and, how to efficiently discover the top-most reliably correlated attribute sets from data.
no code implementations • NeurIPS 2017 • Michael Kamp, Mario Boley, Olana Missura, Thomas Gärtner
We present a novel parallelisation scheme that simplifies the adaptation of learning algorithms to growing amounts of data as well as growing needs for accurate and confident predictions in critical applications.
1 code implementation • 14 Sep 2018 • Panagiotis Mandros, Mario Boley, Jilles Vreeken
The reliable fraction of information is an attractive score for quantifying (functional) dependencies in high-dimensional data.
no code implementations • 22 Sep 2017 • Janis Kalofolias, Mario Boley, Jilles Vreeken
That is, these sub-populations are exceptional with regard to the global distribution.
no code implementations • 25 May 2017 • Panagiotis Mandros, Mario Boley, Jilles Vreeken
As we want to be agnostic on the form of the dependence, we adopt an information-theoretic approach, and construct a reliable, bias correcting score that can be efficiently computed.
no code implementations • 26 Jan 2017 • Mario Boley, Bryan R. Goldsmith, Luca M. Ghiringhelli, Jilles Vreeken
Existing algorithms for subgroup discovery with numerical targets do not optimize the error or target variable dispersion of the groups they find.