Benchmarking the performance of Bayesian optimization across multiple experimental materials science domains
Name
s41524-021-00656-9.pdf
Description
Published version
Size
1.83 MB
Format
Adobe PDF
Checksum (MD5)
449c9886ccc1695a834bffd5a553d197
Author(s)
Liang, Qiaohao
Gongora, Aldair E
Ren, Zekun
Tiihonen, Armi
Liu, Zhe
Sun, Shijing
Deneault, James R
Bash, Daniil
Mekki-Berrada, Flore
Khan, Saif A
Date Issued
December 2021
Journal
npj Computational Materials
Publisher
Springer Science and Business Media LLC
Citation
Liang, Qiaohao, Gongora, Aldair E, Ren, Zekun, Tiihonen, Armi, Liu, Zhe et al. 2021. "Benchmarking the performance of Bayesian optimization across multiple experimental materials science domains." npj Computational Materials, 7 (1).
Version
Final published version
Abstract
AbstractBayesian optimization (BO) has been leveraged for guiding autonomous and high-throughput experiments in materials science. However, few have evaluated the efficiency of BO across a broad range of experimental materials domains. In this work, we quantify the performance of BO with a collection of surrogate model and acquisition function pairs across five diverse experimental materials systems. By defining acceleration and enhancement metrics for materials optimization objectives, we find that surrogate models such as Gaussian Process (GP) with anisotropic kernels and Random Forest (RF) have comparable performance in BO, and both outperform the commonly used GP with isotropic kernels. GP with anisotropic kernels has demonstrated the most robustness, yet RF is a close alternative and warrants more consideration because it is free from distribution assumptions, has smaller time complexity, and requires less effort in initial hyperparameter selection. We also raise awareness about the benefits of using GP with anisotropic kernels in future materials optimization campaigns.
MIT Department
Massachusetts Institute of Technology. Department of Materials Science and Engineering
Massachusetts Institute of Technology. Research Laboratory of Electronics
Massachusetts Institute of Technology. Department of Mechanical Engineering
Singapore-MIT Alliance in Research and Technology (SMART)
Terms of Use
Creative Commons Attribution 4.0 International license
Persistent DSpace Link
DOI of Published Version
https://doi.org/10.1038/s41524-021-00656-9
