Uncertainty-Aware Mixed-Variable Machine Learning for Materials Design

Abstract

Data-driven design shows the promise of accelerating materials discovery but is challenging due to the prohibitive cost of searching the vast design space of chemistry, structure, and synthesis methods. Bayesian Optimization (BO) employs uncertainty-aware machine learning models to select promising designs to evaluate, hence reducing the cost. However, BO with mixed numerical and categorical variables, which is of particular interest in materials design, has not been well studied. In this work, we survey frequentist and Bayesian approaches to uncertainty quantification of machine learning with mixed variables. We then conduct a systematic comparative study of their performances in BO using a popular representative model from each group, the random forest-based Lolo model (frequentist) and the latent variable Gaussian process model (Bayesian). We examine the efficacy of the two models in the optimization of mathematical functions, as well as properties of structural and functional materials, where we observe performance differences as related to problem dimensionality and complexity. By investigating the machine learning models' predictive and uncertainty estimation capabilities, we provide interpretations of the observed performance differences. Our results provide practical guidance on choosing between frequentist and Bayesian uncertainty-aware machine learning models for mixed-variable BO in materials design.

References in corpus (8)

• A Review of Uncertainty Quantification in Deep Learning: Techniques, Applications and Challenges
• On-the-fly Closed-loop Autonomous Materials Discovery via Bayesian Active Learning
• High-Dimensional Materials and Process Optimization using Data-driven Experimental Design with Well-Calibrated Uncertainty Estimates
• Gryffin: An algorithm for Bayesian optimization of categorical variables informed by expert knowledge
• Uncertainty Prediction for Machine Learning Models of Material Properties
• Autonomous Efficient Experiment Design for Materials Discovery with Bayesian Model Averaging
• Featureless adaptive optimization accelerates functional electronic materials design
• Uncertainty Quantification of DFT-predicted Finite Temperature Thermodynamic Properties within the Debye Model

Cited by in corpus (4)

• Data-Driven Design for Metamaterials and Multiscale Systems: A Review
• Data-Efficient Discovery of Hyperelastic TPMS Metamaterials with Extreme Energy Dissipation
• Benchmarking Inverse Optimization Algorithms for Materials Design
• Emerging Microelectronic Materials by Design: Navigating Combinatorial Design Space with Scarce and Dispersed Data