Robust Hybrid Learning With Expert AugmentationDownload PDF

Published: 20 Jun 2023, Last Modified: 18 Jul 2023AABI 2023Readers: Everyone
Keywords: Hybrid learning, expert models, robust, Bayesian inference
Abstract: 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 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 experi- ments 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.
0 Replies