# Experimental Quantum Generative Adversarial Networks for Image Generation

@article{Huang2021ExperimentalQG, title={Experimental Quantum Generative Adversarial Networks for Image Generation}, author={He-Liang Huang and Yuxuan Du and Ming Gong and Youwei Zhao and Yulin Wu and Chaoyue Wang and Shaowei Li and Futian Liang and Jin Lin and Yu Xu and Rui Yang and Tongliang Liu and Min-Hsiu Hsieh and Hui Deng and Hao Rong and Cheng-Zhi Peng and Chao Lu and Yu-Ao Chen and Dacheng Tao and Xiaobo Zhu and Jian-Wei Pan}, journal={ArXiv}, year={2021}, volume={abs/2010.06201} }

Quantum machine learning is expected to be one of the first practical applications of near-term quantum devices. Pioneer theoretical works suggest that quantum generative adversarial networks (GANs) may exhibit a potential exponential advantage over classical GANs, thus attracting widespread attention. However, it remains elusive whether quantum GANs implemented on near-term quantum devices can actually solve real-world learning tasks. Here, we devise a flexible quantum GAN scheme to narrow…

## 25 Citations

QuGAN: A Quantum State Fidelity based Generative Adversarial Network

- Computer Science2021 IEEE International Conference on Quantum Computing and Engineering (QCE)
- 2021

The proposed QuGAN architecture is a quantum GAN architecture that provides stable convergence, quantum-states based gradients and significantly reduced parameter sets, and outperforms state-of-the-art quantum based GANs in the literature.

Generation of High Resolution Handwritten Digits with an Ion-Trap Quantum Computer.

- Physics, Computer Science
- 2020

This work implements a quantum-circuit based generative model to sample the prior distribution of a Generative Adversarial Network (GAN), and introduces a multi-basis technique which leverages the unique possibility of measuring quantum states in different bases, hence enhancing the expressibility of the prior distributions to be learned.

Anomaly detection with variational quantum generative adversarial networks

- Physics, Computer ScienceQuantum Science and Technology
- 2021

This model replaces the generator of WGANs with a hybrid quantum–classical neural net and leaves the classical discriminative model unchanged, which means high-dimensional classical data only enters the classical model and need not be prepared in a quantum circuit.

Recent advances for quantum classifiers

- Physics, Computer ScienceScience China Physics, Mechanics & Astronomy
- 2021

This review gives a relatively comprehensive overview of quantum classifiers, including a number of quantum classification algorithms, including quantum support vector machine, quantum kernel methods, quantum decision tree, and quantum nearest neighbor algorithm.

The dilemma of quantum neural networks

- Computer Science, PhysicsArXiv
- 2021

Through systematic numerical experiments, it is observed that current quantum neural networks fail to provide any benefit over classical learning models and are forced to rethink the role of current QNNs and to design novel protocols for solving real-world problems with quantum advantages.

Quantum semi-supervised generative adversarial network for enhanced data classification

- Medicine, Computer ScienceScientific reports
- 2021

The quantum semi-supervised generative adversarial network (qSGAN) is proposed, composed of a quantum generator and a classical discriminator/classifier that is expected to serve as a stronger adversary than a classical one thanks to its rich expressibility.

On exploring practical potentials of quantum auto-encoder with advantages

- Computer Science, PhysicsArXiv
- 2021

This work proves that QAE can be used to efficiently calculate the eigenvalues and prepare the corresponding eigenvectors of a high-dimensional quantum state with the low-rank property and proves that the error bounds of the proposed QAE-based methods outperform those in previous literature.

F-Divergences and Cost Function Locality in Generative Modelling with Quantum Circuits

- Computer Science, PhysicsEntropy
- 2021

This work generalises existing algorithms for estimating the Kullback–Leibler divergence and the total variation distance to obtain a fault-tolerant quantum algorithm for estimating another f-divergence, namely, the Pearson divergence.

Towards understanding the power of quantum kernels in the NISQ era

- Computer Science, PhysicsQuantum
- 2021

This work proves that the advantage of quantum kernels is vanished for large size of datasets, few number of measurements, and large system noise and provides theoretical guidance of exploring advanced quantum kernels to attain quantum advantages on NISQ devices.

Generative Quantum Learning of Joint Probability Distribution Functions

- Physics
- 2021

Modeling joint probability distributions is an important task in a wide variety of fields. One popular technique for this employs a family of multivariate distributions with uniform marginals called…

## References

SHOWING 1-10 OF 99 REFERENCES

Quantum generative adversarial learning in a superconducting quantum circuit

- Physics, Computer ScienceScience Advances
- 2019

It is demonstrated that, after several rounds of adversarial learning, a quantum-state generator can be trained to replicate the statistics of the quantum data output from a quantum channel simulator, with a high fidelity so that the discriminator cannot distinguish between the true and the generated data.

Quantum generative adversarial networks

- Computer Science, PhysicsPhysical Review A
- 2018

This work extends adversarial training to the quantum domain and shows how to construct generative adversarial networks using quantum circuits, as well as showing how to compute gradients -- a key element in generatives adversarial network training -- using another quantum circuit.

Differentiable Learning of Quantum Circuit Born Machine

- Physics, Computer ScienceArXiv
- 2018

This work devise an efficient gradient-based learning algorithm for the quantum circuit Born machine by minimizing the kerneled maximum mean discrepancy loss and simulated generative modeling of the Bars-and-Stripes dataset and Gaussian mixture distributions using deep quantum circuits.

Quantum Generative Adversarial Networks for learning and loading random distributions

- Computer Science, Physics
- 2019

This work uses quantum Generative Adversarial Networks (qGANs) to facilitate efficient learning and loading of generic probability distributions - implicitly given by data samples - into quantum states and can enable the use of potentially advantageous quantum algorithms, such as Quantum Amplitude Estimation.

Variational Quantum Generators: Generative Adversarial Quantum Machine Learning for Continuous Distributions

- Physics, Computer Science
- 2019

The framework presented here for the design and implementation of variational quantum generators can serve as a blueprint for designing hybrid quantum-classical architectures for other machine learning tasks on near-term quantum devices.

A generative modeling approach for benchmarking and training shallow quantum circuits

- Computer Science, Mathematicsnpj Quantum Information
- 2019

A quantum circuit learning algorithm that can be used to assist the characterization of quantum devices and to train shallow circuits for generative tasks is proposed and it is demonstrated that this approach can learn an optimal preparation of the Greenberger-Horne-Zeilinger states.

Quantum convolutional neural networks

- Computer Science, PhysicsNature Physics
- 2019

A quantum circuit-based algorithm inspired by convolutional neural networks is shown to successfully perform quantum phase recognition and devise quantum error correcting codes when applied to arbitrary input quantum states.

Towards Quantum Machine Learning with Tensor Networks

- Computer Science, PhysicsQuantum Science and Technology
- 2019

This work proposes a unified framework in which classical and quantum computing can benefit from the same theoretical and algorithmic developments, and the same model can be trained classically then transferred to the quantum setting for additional optimization.

The Expressive Power of Parameterized Quantum Circuits

- Computer Science, PhysicsPhysical Review Research
- 2020

It is proved that PQCs with a simple structure already outperform any classical neural network for generative tasks, unless the polynomial hierarchy collapses, and they are employed as an application for Bayesian learning.

Quantum Generative Adversarial Learning.

- Medicine, Computer SciencePhysical review letters
- 2018

The notion of quantum generative adversarial networks is introduced, where the data consist either of quantum states or of classical data, and the generator and discriminator are equipped with quantum information processors, and it is shown that the unique fixed point of the quantum adversarial game also occurs when the generator produces the same statistics as the data.