APS Logo

Towards a scalable discrete quantum generative adversarial neural network

ORAL

Abstract

We introduce a fully quantum generative adversarial network intended for use with binary data. The architecture incorporates several features found in other classical and quantum machine learning models, which up to this point had not been used in conjunction. In particular, we incorporate noise reuploading in the generator, auxiliary qubits in the discriminator to enhance expressivity, and a direct connection between the generator and discriminator circuits, obviating the need to access the generator's probability distribution. We show that, as separate components, the generator and discriminator perform as desired. We empirically demonstrate the expressive power of our model on both synthetic data as well as low energy states of an Ising model. Our demonstrations suggest that the model is not only capable of reproducing discrete training data, but also of potentially generalizing from it.

Publication: arXiv:2209.13993

Presenters

  • Patrick Huembeli

    Menten AI

Authors

  • Alexey Galda

    Menten AI, Menten AI, Inc

  • Smit Chaudhary

    TU Delft

  • Patrick Huembeli

    Menten AI

  • Ian MacCormack

    Menten AI

  • Jean Kossaifi

    NVIDIA

  • Taylor Patty

    NVIDIA