Data-Efficient Neural Operator Training via Physics-Based Active Learning

arXiv:2605.21348v1 Announce Type: cross Abstract: Solving partial differential equations with neural operators significantly reduces computational costs but remains bottlenecked by high training data requirements. Active learning offers a natural framework to mitigate this by selectively acquiring the most informative samples in an iterative manner. We introduce physics-based acquisition - a novel physics-informed active learning algorithm that leverages the partial differential equation residua