Quantum generative adversarial networks

Generative adversarial networks (GANs) have shown an amazing potential for generating photorealistic images that even humans cannot distinguish from real images. To do this, GANs make two neural networks—a discriminator and a generator—learn by competing against each other in a zero-sum game.  We apply the same strategy to the context of quantum computers, where instead quantum devices compete to generate and discriminate quantum states.  


Quantum machine learning is expected to be one of the first potential general-purpose applications of near-term quantum devices. A major recent breakthrough in classical machine learning is the notion of generative adversarial training, where the gradients of a discriminator model are used to train a separate generative model. In this work and a companion paper, we extend adversarial training to the quantum domain and show how to construct generative adversarial networks using quantum circuits. Furthermore, we also show how to compute gradients – a key element in generative adversarial network training – using another quantum circuit. We give an example of a simple practical circuit ansatz to parametrize quantum machine learning models and perform a simple numerical experiment to demonstrate that quantum generative adversarial networks can be trained successfully.