Quantum generative adversarial networks
This work introduces quantum GANs, potentially advancing quantum machine learning for near-term devices, but it is incremental as it adapts classical methods to the quantum domain.
The authors extended generative adversarial networks (GANs) to quantum computing by constructing them with quantum circuits and demonstrating gradient computation via quantum circuits, showing successful training in a simple numerical experiment.
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.