Antoine Wehenkel
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Antoine Wehenkel has a total of 5 co-authors. Here are the top co-authors by number of shared publications:
- Gilles Louppe
University of Liège
1 shared publication - Guillermo Sapiro
University of Liège
1 shared publication - Hsiang Hsu
Instituto de Investigaciones en Matemáticas Aplicadas y en Sistemas (IIMAS) Harvard University Universidad Nacional Autónoma de México
1 shared publication - Jens Behrmann
University of Liège
1 shared publication - Jörn-Henrik Jacobsen
University of Liège
1 shared publication
Latest Publications
- Open Access
Robust Hybrid Learning With Expert Augmentation
Hybrid modelling reduces the misspecification of expert models by combining them with machine learning (ML) components learned from data. Similarly to many ML algorithms, hybrid model performance guarantees are limited to the training distribution. Leveraging the insight that the expert model is usually valid even outside the training domain, we overcome this limitation by introducing a hybrid data augmentation strategy termed \textit{expert augmentation}. Based on a probabilistic formalization of hybrid modelling, we demonstrate that expert augmentation, which can be incorporated into existing hybrid systems, improves generalization. We empirically validate the expert augmentation on three controlled experiments modelling dynamical systems with ordinary and partial differential equations. Finally, we assess the potential real-world applicability of expert augmentation on a dataset of a real double pendulum.
Open AccessRobust Hybrid Learning With Expert Augmentation
Hybrid modelling reduces the misspecification of expert models by combining them with machine learning (ML) components learned from data. Similarly to many ML algorithms, hybrid model performance guarantees are limited to the training distribution. Leveraging the insight that the expert model is usually valid even outside the training domain, we overcome this limitation by introducing a hybrid data augmentation strategy termed \textit{expert augmentation}. Based on a probabilistic formalization of hybrid modelling, we demonstrate that expert augmentation, which can be incorporated into existing hybrid systems, improves generalization. We empirically validate the expert augmentation on three controlled experiments modelling dynamical systems with ordinary and partial differential equations. Finally, we assess the potential real-world applicability of expert augmentation on a dataset of a real double pendulum.