Mapping pareto fronts for efficient multi-objective materials discovery

With advancements in automation and high-throughput techniques, we can tackle more complex multi-objective materials discovery problems requiring a higher evaluation budget. Given that experimentation is greatly limited by evaluation budget, maximizing sample efficiency of optimization becomes cruci...

Full description

Saved in:
Bibliographic Details
Main Authors: Low, Andre Kai Yuan, Vissol-Gaudin, Eleonore, Lim, Yee-Fun, Hippalgaonkar, Kedar
Other Authors: School of Materials Science and Engineering
Format: Article
Language:English
Published: 2024
Subjects:
Online Access:https://hdl.handle.net/10356/175894
Tags: Add Tag
No Tags, Be the first to tag this record!
Institution: Nanyang Technological University
Language: English
id sg-ntu-dr.10356-175894
record_format dspace
spelling sg-ntu-dr.10356-1758942024-05-10T15:51:40Z Mapping pareto fronts for efficient multi-objective materials discovery Low, Andre Kai Yuan Vissol-Gaudin, Eleonore Lim, Yee-Fun Hippalgaonkar, Kedar School of Materials Science and Engineering Institute of Materials Research and Engineering, A*STAR Engineering Machine learning High-throughput experimentation With advancements in automation and high-throughput techniques, we can tackle more complex multi-objective materials discovery problems requiring a higher evaluation budget. Given that experimentation is greatly limited by evaluation budget, maximizing sample efficiency of optimization becomes crucial. We discuss the limitations of using hypervolume as a performance indicator and propose new metrics relevant to materials experimentation: such as the ability to perform well for complex high-dimensional problems, minimizing wastage of evaluations, consistency/robustness of optimization, and ability to scale well to high throughputs. With these metrics, we perform an empirical study of two conceptually different and state-of-the-art algorithms (Bayesian and Evolutionary) on synthetic and real-world datasets. We discuss the merits of both approaches with respect to exploration and exploitation, where fully resolving the Pareto Front provides more knowledge of the best material. Agency for Science, Technology and Research (A*STAR) National Research Foundation (NRF) Published version The authors acknowledge funding from AME Programmatic Funds by the Agency for Science, Technology and Research under Grant (No. A1898b0043) and Grant (No. A20G9b0135). Hippalgaonkar K also acknowledges funding from the NRF Fellowship (NRF-NRFF13-2021-0011). 2024-05-09T02:19:51Z 2024-05-09T02:19:51Z 2023 Journal Article Low, A. K. Y., Vissol-Gaudin, E., Lim, Y. & Hippalgaonkar, K. (2023). Mapping pareto fronts for efficient multi-objective materials discovery. Journal of Materials Informatics, 3(2), 11-. https://dx.doi.org/10.20517/jmi.2023.02 2770-372X https://hdl.handle.net/10356/175894 10.20517/jmi.2023.02 2 3 11 en A1898b0043 A20G9b0135 NRF-NRFF13-2021-0011 Journal of Materials Informatics © 2023 The Author(s). This article is licensed under a Creative Commons Attribution 4.0 International License (https://creativecommons.org/licenses/by/4.0/), which permits unrestricted use, sharing, adaptation, distribution and reproduction in any medium or format, for any purpose, even commercially, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license, and indicate if changes were made. application/pdf
institution Nanyang Technological University
building NTU Library
continent Asia
country Singapore
Singapore
content_provider NTU Library
collection DR-NTU
language English
topic Engineering
Machine learning
High-throughput experimentation
spellingShingle Engineering
Machine learning
High-throughput experimentation
Low, Andre Kai Yuan
Vissol-Gaudin, Eleonore
Lim, Yee-Fun
Hippalgaonkar, Kedar
Mapping pareto fronts for efficient multi-objective materials discovery
description With advancements in automation and high-throughput techniques, we can tackle more complex multi-objective materials discovery problems requiring a higher evaluation budget. Given that experimentation is greatly limited by evaluation budget, maximizing sample efficiency of optimization becomes crucial. We discuss the limitations of using hypervolume as a performance indicator and propose new metrics relevant to materials experimentation: such as the ability to perform well for complex high-dimensional problems, minimizing wastage of evaluations, consistency/robustness of optimization, and ability to scale well to high throughputs. With these metrics, we perform an empirical study of two conceptually different and state-of-the-art algorithms (Bayesian and Evolutionary) on synthetic and real-world datasets. We discuss the merits of both approaches with respect to exploration and exploitation, where fully resolving the Pareto Front provides more knowledge of the best material.
author2 School of Materials Science and Engineering
author_facet School of Materials Science and Engineering
Low, Andre Kai Yuan
Vissol-Gaudin, Eleonore
Lim, Yee-Fun
Hippalgaonkar, Kedar
format Article
author Low, Andre Kai Yuan
Vissol-Gaudin, Eleonore
Lim, Yee-Fun
Hippalgaonkar, Kedar
author_sort Low, Andre Kai Yuan
title Mapping pareto fronts for efficient multi-objective materials discovery
title_short Mapping pareto fronts for efficient multi-objective materials discovery
title_full Mapping pareto fronts for efficient multi-objective materials discovery
title_fullStr Mapping pareto fronts for efficient multi-objective materials discovery
title_full_unstemmed Mapping pareto fronts for efficient multi-objective materials discovery
title_sort mapping pareto fronts for efficient multi-objective materials discovery
publishDate 2024
url https://hdl.handle.net/10356/175894
_version_ 1806059782811942912