Assessing the Frontier: Active Learning, Model Accuracy, and Multi-objective Materials Discovery and Optimization
This work addresses the challenge of evaluating model suitability for iterative materials discovery, which is incremental as it builds on existing active learning methods.
The paper tackles the problem that standard global-scope error metrics are not predictive of discovery performance in active learning for materials discovery, and introduces Pareto shell-scope error as a diagnostic tool, showing insights for acquisition function design through synthetic cases and a thermoelectric dataset.
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.