English

Bayesian Target-Vector Optimization for Efficient Parameter Reconstruction

Computational Physics 2022-10-17 v2 Data Analysis, Statistics and Probability Machine Learning

Abstract

Parameter reconstructions are indispensable in metrology. Here, the objective is to to explain KK experimental measurements by fitting to them a parameterized model of the measurement process. The model parameters are regularly determined by least-square methods, i.e., by minimizing the sum of the squared residuals between the KK model predictions and the KK experimental observations, χ2\chi^2. The model functions often involve computationally demanding numerical simulations. Bayesian optimization methods are specifically suited for minimizing expensive model functions. However, in contrast to least-square methods such as the Levenberg-Marquardt algorithm, they only take the value of χ2\chi^2 into account, and neglect the KK individual model outputs. We present a Bayesian target-vector optimization scheme with improved performance over previous developments, that considers all KK contributions of the model function and that is specifically suited for parameter reconstruction problems which are often based on hundreds of observations. Its performance is compared to established methods for an optical metrology reconstruction problem and two synthetic least-squares problems. The proposed method outperforms established optimization methods. It also enables to determine accurate uncertainty estimates with very few observations of the actual model function by using Markov chain Monte Carlo sampling on a trained surrogate model.

Keywords

Cite

@article{arxiv.2202.11559,
  title  = {Bayesian Target-Vector Optimization for Efficient Parameter Reconstruction},
  author = {Matthias Plock and Kas Andrle and Sven Burger and Philipp-Immanuel Schneider},
  journal= {arXiv preprint arXiv:2202.11559},
  year   = {2022}
}
R2 v1 2026-06-24T09:51:21.388Z