TR2023-036

Bayesian Optimization for Nested Adversarial Variational Autoencoder in Tunable Nanophotonic Device Design


    •  Koike-Akino, T., Jung, M., Chakrabarty, A., Wang, Y., Kojima, K., Brand, M., "Bayesian Optimization for Nested Adversarial Variational Autoencoder in Tunable Nanophotonic Device Design", Conference on Lasers and Electro-Optics (CLEO), May 2023.
      BibTeX TR2023-036 PDF
      • @inproceedings{Koike-Akino2023may,
      • author = {Koike-Akino, Toshiaki and Jung, Minwoo and Chakrabarty, Ankush and Wang, Ye and Kojima, Keisuke and Brand, Matthew},
      • title = {Bayesian Optimization for Nested Adversarial Variational Autoencoder in Tunable Nanophotonic Device Design},
      • booktitle = {Conference on Lasers and Electro-Optics (CLEO)},
      • year = 2023,
      • month = may,
      • url = {https://www.merl.com/publications/TR2023-036}
      • }
  • MERL Contacts:
  • Research Areas:

    Communications, Electronic and Photonic Devices, Machine Learning, Optimization, Signal Processing

Abstract:

We propose a new device optimization framework based on Bayesian optimization for efficient latent sampling of adversarial generative neural networks to expedite a complex inverse design of tunable nanophotonic wavelength splitters. Our design, at broadband telecomm-wavelengths, is electrically switchable via liquid crystal tuning.