English

Towards a scalable discrete quantum generative adversarial neural network

Quantum Physics 2022-09-29 v1

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.

Keywords

Cite

@article{arxiv.2209.13993,
  title  = {Towards a scalable discrete quantum generative adversarial neural network},
  author = {Smit Chaudhary and Patrick Huembeli and Ian MacCormack and Taylor L. Patti and Jean Kossaifi and Alexey Galda},
  journal= {arXiv preprint arXiv:2209.13993},
  year   = {2022}
}

Comments

11 pages, 11 figures, GitLab repository

R2 v1 2026-06-28T02:16:27.887Z