COMBO: An efficient Bayesian optimization library for materials science

[Display omitted] In many subfields of chemistry and physics, numerous attempts have been made to accelerate scientific discovery using data-driven experimental design algorithms. Among them, Bayesian optimization has been proven to be an effective tool. A standard implementation (e.g., scikit-learn...

Full description

Saved in:
Bibliographic Details
Published in:Materials discovery Vol. 4; pp. 18 - 21
Main Authors: Ueno, Tsuyoshi, Rhone, Trevor David, Hou, Zhufeng, Mizoguchi, Teruyasu, Tsuda, Koji
Format: Journal Article
Language:English
Published: Elsevier Ltd 01.06.2016
Subjects:
Bayesian optimization
Global optimization
Materials design
Python library
Global optimization
Bayesian optimization
Python library
Materials design
ISSN:2352-9245, 2352-9245
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:[Display omitted] In many subfields of chemistry and physics, numerous attempts have been made to accelerate scientific discovery using data-driven experimental design algorithms. Among them, Bayesian optimization has been proven to be an effective tool. A standard implementation (e.g., scikit-learn), however, can accommodate only small training data. We designed an efficient protocol for Bayesian optimization that employs Thompson sampling, random feature maps, one-rank Cholesky update and automatic hyperparameter tuning, and implemented it as an open-source python library called COMBO (COMmon Bayesian Optimization library). Promising results using COMBO to determine the atomic structure of a crystalline interface are presented. COMBO is available at https://github.com/tsudalab/combo.
ISSN:2352-9245
2352-9245
DOI:10.1016/j.md.2016.04.001