Share Email Print

Proceedings Paper

Global optimization of complex optical structures using Bayesian optimization based on Gaussian processes
Author(s): Philipp-Immanuel Schneider; Xavier Garcia Santiago; Carsten Rockstuhl; Sven Burger
Format Member Price Non-Member Price
PDF $17.00 $21.00

Paper Abstract

Numerical simulation of complex optical structures enables their optimization with respect to specific objectives. Often, optimization is done by multiple successive parameter scans, which are time consuming and computationally expensive. We employ here Bayesian optimization with Gaussian processes in order to automatize and speed up the optimization process. As a toy example, we demonstrate optimization of the shape of a free-form reflective meta surface such that it diffracts light into a specific diffraction order. For this example, we compare the performance of six different Bayesian optimization approaches with various acquisition functions and various kernels of the Gaussian process.

Paper Details

Date Published: 26 June 2017
PDF: 9 pages
Proc. SPIE 10335, Digital Optical Technologies 2017, 103350O (26 June 2017); doi: 10.1117/12.2270609
Show Author Affiliations
Philipp-Immanuel Schneider, JCMwave GmbH (Germany)
Xavier Garcia Santiago, JCMwave GmbH (Germany)
Karlsruher Institut für Technologie (Germany)
Carsten Rockstuhl, Karlsruher Institut für Technologie (Germany)
Sven Burger, JCMwave GmbH (Germany)
Zuse Institute Berlin (ZIB) (Germany)

Published in SPIE Proceedings Vol. 10335:
Digital Optical Technologies 2017
Bernard C. Kress; Peter Schelkens, Editor(s)

© SPIE. Terms of Use
Back to Top
Sign in to read the full article
Create a free SPIE account to get access to
premium articles and original research
Forgot your username?