Physics-Augmented Learning: A New Paradigm Beyond Physics-Informed Learning
This work addresses the need for more generalizable machine learning models in domains requiring physical constraints, though it appears incremental as it builds on an existing paradigm.
The authors tackled the problem of integrating physical inductive biases into machine learning by generalizing physics-informed learning into a new framework called physics-augmented learning, which handles generative properties and performs well in cases where the previous method is inapplicable or inefficient.
Integrating physical inductive biases into machine learning can improve model generalizability. We generalize the successful paradigm of physics-informed learning (PIL) into a more general framework that also includes what we term physics-augmented learning (PAL). PIL and PAL complement each other by handling discriminative and generative properties, respectively. In numerical experiments, we show that PAL performs well on examples where PIL is inapplicable or inefficient.