Best practices for multi-fidelity Bayesian optimization in materials and molecular research
- 23 July 2025
- journal article
- Published by Springer Nature in Nature Computational Science
- Vol. 5 (7) , 572-581
Abstract
Multi-fidelity Bayesian optimization (MFBO) is a promising framework to speed up materials and molecular discovery as sources of information of different accuracies are at hand at increasing cost. Despite its potential use in chemical tasks, there is a lack of systematic evaluation of the many parameters playing a role in MFBO. Here we provide guidelines and recommendations to decide when to use MFBO in experimental settings. We investigate MFBO methods applied to molecules and materials problems. First, we test two different families of acquisition functions in two synthetic problems and study the effect of the informativeness and cost of the approximate function. We use our implementation and guidelines to benchmark three real discovery problems and compare them against their single-fidelity counterparts. Our results may help guide future efforts to implement MFBO as a routine tool in the chemical sciences.Keywords
All Related Versions
This publication has 26 references indexed in Scilit:
- A Holistic Data-Driven Approach to Synthesis Predictions of Colloidal Nanocrystal ShapesJournal of the American Chemical Society, 2025
- Bayesian Optimization over Multiple Experimental Fidelities Accelerates Automated Discovery of Drug MoleculesACS Central Science, 2025
- Cost-Aware Bayesian Optimization for Self-Driven Condition Screening of Flow ElectrosynthesisACS Electrochemistry, 2024
- Combining multi-fidelity modelling and asynchronous batch Bayesian OptimizationComputers & Chemical Engineering, 2023
- Bayesian Optimization2023
- Low-field and benchtop NMRJournal of Magnetic Resonance, 2019
- Phoenics: A Bayesian Optimizer for ChemistryACS Central Science, 2018
- FreeSolv: a database of experimental and calculated hydration free energies, with input filesJournal of Computer-Aided Molecular Design, 2014
- Sequential kriging optimization using multiple-fidelity evaluationsStructural and Multidisciplinary Optimization, 2006
- Efficient Global Optimization of Expensive Black-Box FunctionsJournal of Global Optimization, 1998