Benchmarking the Performance of Bayesian Optimization across Multiple Experimental Materials Science Domains

2021/05/23 by Qiaohao Liang, Liang, Qiaohao, Aldair E. Gongora +29 · 16 citations
Computer Science · Materials Science · Physics and Astronomy · #Artificial intelligence #Bayesian optimization #Benchmarking #Computer science #Data Analysis #FOS: Computer and information sciences #FOS: Physical sciences #Gaussian #Gaussian process #Machine Learning (cs.LG) #Machine Learning and Algorithms #Machine Learning and Data Classification #Machine Learning in Materials Science #Machine learning #Materials Science (cond-mat.mtrl-sci) #Materials science #Physics #Selection (genetic algorithm) #Statistics and Probability (physics.data-an) #Surrogate model #Throughput #cond-mat.mtrl-sci #cs.LG #physics.data-an

paper · pdf · doi:10.48550/arxiv.2106.01309

published in arXiv (Cornell University) (Cornell University)

arxiv created 2021/05/23 · openalex publication_date 2021/05/23 · arxiv updated 2021/06/03 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

In the field of machine learning (ML) for materials optimization, active learning algorithms, such as Bayesian Optimization (BO), have been leveraged for guiding autonomous and high-throughput experimentation systems. However, very few studies have evaluated the efficiency of BO as a general optimization algorithm across a broad range of experimental materials science domains. In this work, we evaluate the performance of BO algorithms with a collection of surrogate model and acquisition function pairs across five diverse experimental materials systems, namely carbon nanotube polymer blends, silver nanoparticles, lead-halide perovskites, as well as additively manufactured polymer structures and shapes. By defining acceleration and enhancement metrics for general materials optimization objectives, we find that for surrogate model selection, Gaussian Process (GP) with anisotropic kernels (automatic relevance detection, ARD) and Random Forests (RF) have comparable performance and both outperform the commonly used GP without ARD. We discuss the implicit distributional assumptions of RF and GP, and the benefits of using GP with anisotropic kernels in detail. We provide practical insights for experimentalists on surrogate model selection of BO during materials optimization campaigns.

Citations

• A Tutorial on Bayesian Optimization of Expensive Cost Functions, with Application to Active User Modeling and Hierarchical Reinforcement Learning
• Taking the Human Out of the Loop: A Review of Bayesian Optimization
• A Tutorial on Bayesian Optimization
• Batched High-dimensional Bayesian Optimization via Structural Kernel Learning

Cited by

• Bayesian Co-Navigation of a Computational Physical Model and AFM Experiment to Autonomously Survey a Combinatorial Materials Library
• Building Trustworthy AI for Materials Discovery: From Autonomous Laboratories to Z-scores
• Bayesian Optimization for Function-Valued Responses under Min-Max Criteria
• A Guide to Bayesian Optimization in Bioprocess Engineering
• Machine-learning-guided polymorph selection in molecular beam epitaxy of In2Se3
• Black-box optimization using factorization and Ising machines
• Position: Intelligent Science Laboratory Requires the Integration of Cognitive and Embodied AI
• Machine learning for in-situ composition mapping in a self-driving magnetron sputtering system
• Spectral Mixture Kernels for Bayesian Optimization
• DASH: Decoupled Adaptive Surrogate - Acquisition Harness for Automated Bayesian Optimization
• Interpretable SHAP-bounded Bayesian Optimization for Underwater Acoustic Metamaterial Coating Design
• Bgolearn: a Unified Bayesian Optimization Framework for Accelerating Materials Discovery
• Active Learning Guided Design Space Refinement for Scalable Multi-Objective Bayesian Optimization in Materials Discovery
• Multi-Variable Batch Bayesian Optimization in Materials Research: Synthetic Data Analysis of Noise Sensitivity and Problem Landscape Effects
• Adaptive AI decision interface for autonomous electronic material discovery
• Distilling and exploiting quantitative insights from Large Language Models for enhanced Bayesian optimization of chemical reactions

Related

• Bayesian Optimization in Materials Science: A Survey
• Multi-Variable Batch Bayesian Optimization in Materials Research: Synthetic Data Analysis of Noise Sensitivity and Problem Landscape Effects
• Data-Centric Mixed-Variable Bayesian Optimization For Materials Design
• Physics makes the difference: Bayesian optimization and active learning via augmented Gaussian process
• Accelerating material discovery with a threshold-driven hybrid acquisition policy-based Bayesian optimization