Recent advances in Bayesian optimization with applications to parameter reconstruction in optical nano-metrology

TL;DR

This paper introduces a Bayesian Target Vector Optimization method that combines Bayesian optimization and curve fitting for efficient parameter reconstruction in optical nano-metrology, reducing model evaluations.

Contribution

The paper presents a novel Bayesian Target Vector Optimization approach that outperforms existing methods in efficiency for nano-metrology parameter reconstruction.

Findings

Fewer model function calls needed for similar accuracy.

Outperforms Levenberg-Marquardt and other algorithms in efficiency.

Effective on NIST benchmark problem.

Abstract

Parameter reconstruction is a common problem in optical nano metrology. It generally involves a set of measurements, to which one attempts to fit a numerical model of the measurement process. The model evaluation typically involves to solve Maxwell's equations and is thus time consuming. This makes the reconstruction computationally demanding. Several methods exist for fitting the model to the measurements. On the one hand, Bayesian optimization methods for expensive black-box optimization enable an efficient reconstruction by training a machine learning model of the squared sum of deviations. On the other hand, curve fitting algorithms, such as the Levenberg-Marquardt method, take the deviations between all model outputs and corresponding measurement values into account which enables a fast local convergence. In this paper we present a Bayesian Target Vector Optimization scheme which combines these two approaches. We compare the performance of the presented method against a standard Levenberg-Marquardt-like algorithm, a conventional Bayesian optimization scheme, and the L-BFGS-B and Nelder-Mead simplex algorithms. As a stand-in for problems from nano metrology, we employ a non-linear least-square problem from the NIST Standard Reference Database. We find that the presented method generally uses fewer calls of the model function than any of the competing schemes to achieve similar reconstruction performance.