Timezone: »

Improving Generalization with Physical Equations
Antoine Wehenkel · Jens Behrmann · Hsiang Hsu · Guillermo Sapiro · Gilles Louppe · Joern-Henrik Jacobsen

Hybrid modelling reduces the misspecification of expert physical models with a machine learning (ML) component learned from data. Similarly to many ML algorithms, hybrid model performance guarantees are limited to the training distribution. To address this limitation, here we introduce a hybrid data augmentation strategy, termed \textit{expert augmentation}. Based on a probabilistic formalization of hybrid modelling, we demonstrate that expert augmentation improves generalization. We validate the practical benefits of expert augmentation on a set of simulated and real-world systems described by classical mechanics.

Author Information

Antoine Wehenkel (ULiège/Apple)
Jens Behrmann (Apple)
Hsiang Hsu (Harvard University)

I am Hsiang Hsu, a Harvard Ph.D. student working with Flavio Calmon, and also a Meta Fellow. My research interests lie in promoting the interpretability of representations, improving privacy and fairness, and understanding prediction uncertainty in machine learning. I believe these are important issues in modern machine learning when trying to deploy the models in practice.

Guillermo Sapiro (Duke University)
Gilles Louppe (University of Liège)
Joern-Henrik Jacobsen (Apple)

More from the Same Authors