Physics makes the difference: Bayesian optimization and active learning via augmented Gaussian process

TL;DR

This paper introduces a hybrid Bayesian optimization method that augments Gaussian processes with physical models, enabling more efficient exploration of parameter spaces by incorporating prior physical knowledge and past data.

Contribution

It presents a novel hybrid approach combining Gaussian processes with structured physical models for improved Bayesian optimization.

Findings

Enhanced optimization efficiency demonstrated on classical objective functions.

Extended methodology to physical lattice models.

Framework allows incorporation of prior physical knowledge into Bayesian optimization.

Abstract

Both experimental and computational methods for the exploration of structure, functionality, and properties of materials often necessitate the search across broad parameter spaces to discover optimal experimental conditions and regions of interest in the image space or parameter space of computational models. The direct grid search of the parameter space tends to be extremely time-consuming, leading to the development of strategies balancing exploration of unknown parameter spaces and exploitation towards required performance metrics. However, classical Bayesian optimization strategies based on the Gaussian process (GP) do not readily allow for the incorporation of the known physical behaviors or past knowledge. Here we explore a hybrid optimization/exploration algorithm created by augmenting the standard GP with a structured probabilistic model of the expected system's behavior. This approach balances the flexibility of the non-parametric GP approach with a rigid structure of physical knowledge encoded into the parametric model. The fully Bayesian treatment of the latter allows additional control over the optimization via the selection of priors for the model parameters. The method is demonstrated for a noisy version of the classical objective function used to evaluate optimization algorithms and further extended to physical lattice models. This methodology is expected to be universally suitable for injecting prior knowledge in the form of physical models and past data in the Bayesian optimization framework