Bayesian optimization with improved scalability and derivative information for efficient design of nanophotonic structures
This work improves the scalability of Bayesian optimization for engineers designing nanophotonic structures, particularly when derivative information can be leveraged, making the optimization process more efficient.
The paper addresses the scalability issues in Bayesian optimization for nanophotonic device design by integrating forward shape derivatives and an iterative inversion scheme. This allows for a greater number of iterations, making the method practical for scenarios where derivative information is available and the computational cost of identifying the next evaluation point previously outweighed the objective function evaluation. The method is demonstrated by optimizing a waveguide edge coupler.
We propose the combination of forward shape derivatives and the use of an iterative inversion scheme for Bayesian optimization to find optimal designs of nanophotonic devices. This approach widens the range of applicability of Bayesian optmization to situations where a larger number of iterations is required and where derivative information is available. This was previously impractical because the computational efforts required to identify the next evaluation point in the parameter space became much larger than the actual evaluation of the objective function. We demonstrate an implementation of the method by optimizing a waveguide edge coupler.