Optimization of Functional Materials Design with Optimal Initial Data in Surrogate-Based Active Learning

TL;DR

This paper investigates how the size of initial data impacts the efficiency of surrogate-based active learning in optimizing complex functional materials, emphasizing the importance of adequate initial data for faster convergence and reduced costs.

Contribution

It introduces a method to determine optimal initial data sizes for different design space scales using averaged piecewise linear regression, improving optimization efficiency.

Findings

Optimal initial data sizes vary with design space complexity.

Adequate initial data significantly accelerates convergence.

The approach reduces computational costs in material optimization.

Abstract

The optimization of functional materials is important to enhance their properties, but their complex geometries pose great challenges to optimization. Data-driven algorithms efficiently navigate such complex design spaces by learning relationships between material structures and performance metrics to discover high-performance functional materials. Surrogate-based active learning, continually improving its surrogate model by iteratively including high-quality data points, has emerged as a cost-effective data-driven approach. Furthermore, it can be coupled with quantum computing to enhance optimization processes, especially when paired with a special form of surrogate model ($i.e.$, quadratic unconstrained binary optimization), formulated by factorization machine. However, current practices often overlook the variability in design space sizes when determining the initial data size for optimization. In this work, we investigate the optimal initial data sizes required for efficient convergence across various design space sizes. By employing averaged piecewise linear regression, we identify initiation points where convergence begins, highlighting the crucial role of employing adequate initial data in achieving efficient optimization. These results contribute to the efficient optimization of functional materials by ensuring faster convergence and reducing computational costs in surrogate-based active learning.