Discovering novel materials can be greatly accelerated by iterative machine learning-informed proposal of candidates---active learning. However, standard \emph{global-scope error} metrics for model quality are not predictive of discovery performance, and can be misleading. We introduce the notion of \emph{Pareto shell-scope error} to help judge the suitability of a model for proposing material candidates. Further, through synthetic cases and a thermoelectric dataset, we probe the relation between acquisition function fidelity and active learning performance. Results suggest novel diagnostic tools, as well as new insights for acquisition function design.
@article{arxiv.1911.03224,
title = {Assessing the Frontier: Active Learning, Model Accuracy, and Multi-objective Materials Discovery and Optimization},
author = {Zachary del Rosario and Matthias Rupp and Yoolhee Kim and Erin Antono and Julia Ling},
journal= {arXiv preprint arXiv:1911.03224},
year = {2020}
}