Bayesian diversity control for batch-based phase diagram determination

Abstract

Machine learning methods are increasingly used in experimental design in phase diagram determination. Some methods perform batch design, where multiple points are sampled from the design space. In this case, it is essential to diversify samples to avoid performing almost identical experiments, and control the diversity level appropriately. Manual diversity control is unintuitive and may require additional trial-and-error in prior to the experiments are started. We propose a Bayesian model called determinantal point process for phase diagram construction (DPP-PDC) that can perform batch design and automatic diversity control simultaneously. Central to this model is the uncertainty-weighted determinantal point process that samples a set of points with high uncertainty under diversity control. Experiments with Cu–Mg–Zn ternary system demonstrate that DPP-PDC can actively control the sample diversity to achieve high efficiency.