The authors propose an iterative inversion scheme for Bayesian optimization to find optimal designs of nanophotonic devices. This improves the scalability of the approach and allows to apply it in situations where a larger number of iterations is required and where derivative information is available.
X. Garcia-Santiago, et al. Bayesian Optimization With Improved Scalability and Derivative Information for Efficient Design of Nanophotonic Structures. J. Lightwave Technol., 39, 167 (2021).