4.4k citations
- University of KasselDE5 papers
- Centre National de la Recherche ScientifiqueFR4 papers
- Humboldt-Universität zu BerlinDE4 papers
- University of FreiburgDE4 papers
- Laboratoire de Mathématiques de Bretagne AtlantiqueFR3 papers
- Ludwig-Maximilians-Universität MünchenDE3 papers
- Ostfalia University of Applied SciencesDE3 papers
- University of TübingenDE3 papers
- Astrophysique, Instrumentation et ModélisationFR2 papers
- Clausthal University of TechnologyDE2 papers
- Commissariat à l'Énergie Atomique et aux Énergies AlternativesFR2 papers
- Institut de Mathématiques de BordeauxFR2 papers
9 papers · 1 filter
Right-wing German Hate Speech on Twitter: Analysis and Automatic Detection
Sylvia Jaki, Tom De Smedt
Discussion about the social network Twitter often concerns its role in political discourse, involving the question of when an expression of opinion becomes offensive, immoral, and/…
Chameleon: Learning Model Initializations Across Tasks With Different Schemas
Lukas Brinkmeyer, Rafael Rego Drumond, Randolf Scholz +2
Parametric models, and particularly neural networks, require weight initialization as a starting point for gradient-based optimization. Recent work shows that a specific initial pa…
Asymptotic Independence ex machina -- Extreme Value Theory for the Diagonal BEKK-ARCH(1) Model
Sebastian Mentemeier, Olivier Wintenberger
We consider multivariate stationary processes satisfying a stochastic recurrence equation of the form $$ \boldsymbol{X}_t= \mathbb{ M}_t \boldsymbol{X}_{t-1} +…
Hyp-RL : Hyperparameter Optimization by Reinforcement Learning
Hadi S. Jomaa, Josif Grabocka, Lars Schmidt-Thieme
Hyperparameter tuning is an omnipresent problem in machine learning as it is an integral aspect of obtaining the state-of-the-art performance for any model. Most often, hyperparame…
Drawing Order Diagrams Through Two-Dimension Extension
Dominik Dürrschnabel, Tom Hanika, Gerd Stumme
Order diagrams are an important tool to visualize the complex structure of ordered sets. Favorable drawings of order diagrams, i.e., easily readable for humans, are hard to come by…
Learning Surrogate Losses
Josif Grabocka, Randolf Scholz, Lars Schmidt-Thieme
The minimization of loss functions is the heart and soul of Machine Learning. In this paper, we propose an off-the-shelf optimization approach that can minimize virtually any non-d…