MetaPhysiCa: Improving OOD Robustness in Physics-informed Machine Learning
S Chandra Mouli, Muhammad Alam, Bruno Ribeiro
Abstract
A fundamental challenge in physics-informed machine learning (PIML) is the design of robust PIML methods for out-of-distribution (OOD) forecasting tasks. These OOD tasks require learning-to-learn from observations of the same (ODE) dynamical system with different unknown ODE parameters, and demand accurate forecasts even under out-of-support initial conditions and out-of-support ODE parameters. In this work we propose to improve the OOD robustness of PIML via a meta-learning procedure for causal structure discovery. Using three different OOD tasks, we empirically observe that the proposed approach significantly outperforms existing state-of-the-art PIML and deep learning methods (with $2\times$ to $28\times$ lower OOD errors).
BibTeX
@inproceedings{
mouli2024metaphysica,
title={MetaPhysiCa: Improving {OOD} Robustness in Physics-informed Machine Learning},
author={S Chandra Mouli and Muhammad Alam and Bruno Ribeiro},
booktitle={The Twelfth International Conference on Learning Representations},
year={2024},
url={https://openreview.net/forum?id=KrWuDiW4Qm}
}