Entangling Quantum Generative Adversarial Networks

TL;DR

This paper introduces EQ-GAN, a quantum generative adversarial network leveraging entanglement to improve convergence and robustness, demonstrated experimentally on a superconducting quantum processor for quantum data representation.

Contribution

The paper proposes a novel entangling quantum GAN architecture that overcomes limitations of previous models and demonstrates its effectiveness on real quantum hardware.

Findings

EQ-GAN guarantees convergence to Nash equilibrium.

EQ-GAN shows increased robustness against coherent errors.

Successfully demonstrates quantum data representation and QRAM applications.

Abstract

Generative adversarial networks (GANs) are one of the most widely adopted semisupervised and unsupervised machine learning methods for high-definition image, video, and audio generation. In this work, we propose a new type of architecture for quantum generative adversarial networks (entangling quantum GAN, EQ-GAN) that overcomes some limitations of previously proposed quantum GANs. Leveraging the entangling power of quantum circuits, EQ-GAN guarantees the convergence to a Nash equilibrium under minimax optimization of the discriminator and generator circuits by performing entangling operations between both the generator output and true quantum data. We show that EQ-GAN has additional robustness against coherent errors and demonstrate the effectiveness of EQ-GAN experimentally in a Google Sycamore superconducting quantum processor. By adversarially learning efficient representations of quantum states, we prepare an approximate quantum random access memory (QRAM) and demonstrate its use in applications including the training of quantum neural networks.