1 code implementation • 11 Oct 2021 • Sebastian Angrick, Ben Bals, Niko Hastrich, Maximilian Kleissl, Jonas Schmidt, Vanja Doskoč, Maximilian Katzmann, Louise Molitor, Tobias Friedrich
Human lives are increasingly influenced by algorithms, which therefore need to meet higher standards not only in accuracy but also with respect to explainability.
no code implementations • 12 Feb 2021 • Francesco Quinzan, Vanja Doskoč, Andreas Göbel, Tobias Friedrich
Our algorithm is suitable to maximize a non-monotone submodular function under a $p$-system side constraint, and it achieves a $(p + O(\sqrt{p}))$-approximation for this problem, after only poly-logarithmic adaptive rounds and polynomial queries to the valuation oracle function.
no code implementations • 15 Oct 2020 • Julian Berger, Maximilian Böther, Vanja Doskoč, Jonathan Gadea Harder, Nicolas Klodt, Timo Kötzing, Winfried Lötzsch, Jannik Peters, Leon Schiller, Lars Seifert, Armin Wells, Simon Wietheger
We study learning of indexed families from positive data where a learner can freely choose a hypothesis space (with uniformly decidable membership) comprising at least the languages to be learned.
no code implementations • 15 Oct 2020 • Vanja Doskoč, Timo Kötzing
Such results are key to understanding the, yet undiscovered, mutual relation between various important learning paradigms when learning behaviourally correctly.
no code implementations • 15 Oct 2020 • Vanja Doskoč, Timo Kötzing
In particular, we show that explanatory monotone learners, although known to be strictly stronger, do (almost) preserve the pairwise relation as seen in strongly monotone learning.
no code implementations • 15 Oct 2020 • Julian Berger, Maximilian Böther, Vanja Doskoč, Jonathan Gadea Harder, Nicolas Klodt, Timo Kötzing, Winfried Lötzsch, Jannik Peters, Leon Schiller, Lars Seifert, Armin Wells, Simon Wietheger
This so-called $W$-index allows for naming arbitrary computably enumerable languages, with the drawback that even the membership problem is undecidable.
1 code implementation • 15 Jul 2020 • Felix Mujkanovic, Vanja Doskoč, Martin Schirneck, Patrick Schäfer, Tobias Friedrich
Modern time series classifiers display impressive predictive capabilities, yet their decision-making processes mostly remain black boxes to the user.
no code implementations • 15 Nov 2019 • Vanja Doskoč, Tobias Friedrich, Andreas Göbel, Frank Neumann, Aneta Neumann, Francesco Quinzan
We show that our proposed algorithm competes with the state-of-the-art in static settings.