Quantum generative adversarial network for generating discrete distribution

TL;DR

This paper introduces a quantum GAN architecture capable of generating classical discrete distributions, leveraging simple quantum circuits and a hybrid structure to overcome classical GAN limitations and enhance quantum data processing.

Contribution

It proposes a novel quantum GAN with a hybrid architecture that efficiently generates discrete data and avoids common quantum input/output bottlenecks.

Findings

Capable of generating discrete data like text.

Avoids quantum input/output bottlenecks.

Uses simple quantum gates compatible with current devices.

Abstract

Quantum machine learning has recently attracted much attention from the community of quantum computing. In this paper, we explore the ability of generative adversarial networks (GANs) based on quantum computing. More specifically, we propose a quantum GAN for generating classical discrete distribution, which has a classical-quantum hybrid architecture and is composed of a parameterized quantum circuit as the generator and a classical neural network as the discriminator. The parameterized quantum circuit only consists of simple one-qubit rotation gates and two-qubit controlled-phase gates that are available in current quantum devices. Our scheme has the following characteristics and potential advantages: (i) It is intrinsically capable of generating discrete data (e.g., text data), while classical GANs are clumsy for this task due to the vanishing gradient problem. (ii) Our scheme avoids the input/output bottlenecks embarrassing most of the existing quantum learning algorithms that either require to encode the classical input data into quantum states, or output a quantum state corresponding to the solution instead of giving the solution itself, which inevitably compromises the speedup of the quantum algorithm. (iii) The probability distribution implicitly given by data samples can be loaded into a quantum state, which may be useful for some further applications.