Quantum generative adversarial learning

TL;DR

This paper introduces quantum generative adversarial networks (QuGANs), demonstrating their potential for exponential advantage over classical GANs when handling high-dimensional quantum data.

Contribution

The paper extends classical GANs to quantum systems, providing theoretical proof of convergence and highlighting potential exponential advantages in high-dimensional quantum data scenarios.

Findings

Quantum GANs converge to the true data distribution.

Quantum systems simplify the proof of convergence.

Potential exponential advantage over classical GANs with high-dimensional data.

Abstract

Generative adversarial networks (GANs) represent a powerful tool for classical machine learning: a generator tries to create statistics for data that mimics those of a true data set, while a discriminator tries to discriminate between the true and fake data. The learning process for generator and discriminator can be thought of as an adversarial game, and under reasonable assumptions, the game converges to the point where the generator generates the same statistics as the true data and the discriminator is unable to discriminate between the true and the generated data. This paper introduces the notion of quantum generative adversarial networks (QuGANs), where the data consists either of quantum states, or of classical data, and the generator and discriminator are equipped with quantum information processors. We show that the unique fixed point of the quantum adversarial game also occurs when the generator produces the same statistics as the data. Since quantum systems are intrinsically probabilistic the proof of the quantum case is different from - and simpler than - the classical case. We show that when the data consists of samples of measurements made on high-dimensional spaces, quantum adversarial networks may exhibit an exponential advantage over classical adversarial networks.