Leveraging Interpolation Models and Error Bounds for Verifiable Scientific Machine Learning

arXiv:2404.03586v1 Announce Type: new
Abstract: Effective verification and validation techniques for modern scientific machine learning workflows are challenging to devise. Statistical methods are abundant and easily deployed, but often rely on speculative assumptions about the data and methods involved. Error bounds for classical interpolation techniques can provide mathematically rigorous estimates of accuracy, but often are difficult or impractical to determine computationally. In this work, we present a best-of-both-worlds approach to verifiable scientific machine learning by demonstrating that (1) multiple standard …

abstract arxiv assumptions cs.lg data error machine machine learning machine learning workflows modern scientific statistical stat.ml type validation verification workflows