Quantum generative adversarial networks

2018/04/30 by Pierre-Luc Dallaire-Demers, Nathan Killoran · 3 citations
Computer Science · Physics and Astronomy · #cs.LG #quant-ph

paper · pdf · doi:10.1103/physreva.98.012324

published as Phys. Rev. A 98, 012324 (2018) · 10 pages, 8 figures

arxiv created 2018/04/30 · arxiv updated 2018/08/01

Abstract

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.

Cited by

• Model selection in hybrid quantum neural networks with applications to quantum transformer architectures
• Qudit extension of parameterized IQP circuits: A generative quantum machine learning approach to integer data
• Optimal Quantum Differential Privacy via Fisher Information Spectral Analysis
• Quantum Image Loading: Hierarchical Learning and Block-Amplitude Encoding
• The inherent convolution property of quantum neural networks

Related

• Quantum Generative Adversarial Networks: Bridging Classical and Quantum Realms
• Towards a scalable discrete quantum generative adversarial neural network
• Recent Advances for Quantum Neural Networks in Generative Learning
• Generative Quantum Machine Learning
• A Survey of Quantum Generative Adversarial Networks: Architectures, Use Cases, and Real-World Implementations