English

Optimizing Photonic Nanostructures via Multi-fidelity Gaussian Processes

Machine Learning 2018-11-20 v1 Machine Learning

Abstract

We apply numerical methods in combination with finite-difference-time-domain (FDTD) simulations to optimize transmission properties of plasmonic mirror color filters using a multi-objective figure of merit over a five-dimensional parameter space by utilizing novel multi-fidelity Gaussian processes approach. We compare these results with conventional derivative-free global search algorithms, such as (single-fidelity) Gaussian Processes optimization scheme, and Particle Swarm Optimization---a commonly used method in nanophotonics community, which is implemented in Lumerical commercial photonics software. We demonstrate the performance of various numerical optimization approaches on several pre-collected real-world datasets and show that by properly trading off expensive information sources with cheap simulations, one can more effectively optimize the transmission properties with a fixed budget.

Keywords

Cite

@article{arxiv.1811.07707,
  title  = {Optimizing Photonic Nanostructures via Multi-fidelity Gaussian Processes},
  author = {Jialin Song and Yury S. Tokpanov and Yuxin Chen and Dagny Fleischman and Kate T. Fountaine and Harry A. Atwater and Yisong Yue},
  journal= {arXiv preprint arXiv:1811.07707},
  year   = {2018}
}

Comments

NIPS 2018 Workshop on Machine Learning for Molecules and Materials. arXiv admin note: substantial text overlap with arXiv:1811.00755

R2 v1 2026-06-23T05:20:32.131Z