Authors
Meredig, Bryce; Antono, Erin; Church, Carena ; Hutchinson, Maxwell; Ling, Julia; Paradiso, Sean; Blaiszik, Ben; Foster, Ian; Gibbons, Brenna; Hattrick-Simpers, Jason; Mehta, Apurva; Ward, Logan
Abstract
Traditional machine learning (ML) metrics overestimate model performance for materials discovery. We introduce (1) leave-onecluster-out cross-validation (LOCO CV) and (2) a simple nearestneighbor benchmark to show that model performance in discovery applications strongly depends on the problem, data sampling, and extrapolation. Our results suggest that ML-guided iterative experimentation may outperform standard high-throughput screening for discovering breakthrough materials like high-Tc superconductors with ML.