Blending Diverse Physical Priors with Neural Networks
This work addresses the problem of robust inference in physical systems for researchers in physics-based machine learning, representing an incremental advance by applying NAS to PBL.
The paper tackles the challenge of generalizing physics-based learning (PBL) methods across diverse physical problems by introducing PhysicsNAS, a neural architecture search approach that adapts to variations in physical model correctness and data quality, achieving top performance in benchmarks.
Machine learning in context of physical systems merits a re-examination of the learning strategy. In addition to data, one can leverage a vast library of physical prior models (e.g. kinematics, fluid flow, etc) to perform more robust inference. The nascent sub-field of \emph{physics-based learning} (PBL) studies the blending of neural networks with physical priors. While previous PBL algorithms have been applied successfully to specific tasks, it is hard to generalize existing PBL methods to a wide range of physics-based problems. Such generalization would require an architecture that can adapt to variations in the correctness of the physics, or in the quality of training data. No such architecture exists. In this paper, we aim to generalize PBL, by making a first attempt to bring neural architecture search (NAS) to the realm of PBL. We introduce a new method known as physics-based neural architecture search (PhysicsNAS) that is a top-performer across a diverse range of quality in the physical model and the dataset.