Generative Neural Network Based Non-Convex Optimization Using Policy Gradients with an Application to Electromagnetic Design

Abstract

A generative neural network based non-convex optimization algorithm using a one-step implementation of the policy gradient method is introduced and applied to electromagnetic design. We demonstrate state-of-the-art performance of electromagnetic devices called grating couplers, with key advantages over local gradient-based optimization via the adjoint method.

PDF NeurIPSW OpenReview Semantic Scholar

Cite

Text

Hooten et al. "Generative Neural Network Based Non-Convex Optimization Using Policy Gradients with an Application to Electromagnetic Design." NeurIPS 2021 Workshops: AI4Science, 2021.

Markdown

[Hooten et al. "Generative Neural Network Based Non-Convex Optimization Using Policy Gradients with an Application to Electromagnetic Design." NeurIPS 2021 Workshops: AI4Science, 2021.](https://mlanthology.org/neuripsw/2021/hooten2021neuripsw-generative/)

BibTeX

@inproceedings{hooten2021neuripsw-generative,
  title     = {{Generative Neural Network Based Non-Convex Optimization Using Policy Gradients with an Application to Electromagnetic Design}},
  author    = {Hooten, Sean and Vadlamani, Sri Krishna` and Beausoleil, Raymond G. and Van Vaerenbergh, Thomas},
  booktitle = {NeurIPS 2021 Workshops: AI4Science},
  year      = {2021},
  url       = {https://mlanthology.org/neuripsw/2021/hooten2021neuripsw-generative/}
}