Quantum generative adversarial networks based on Rényi divergences

Ling Liu, Tingting Song, Zhiwei Sun and Jiancheng Lei

Physica A: Statistical Mechanics and its Applications, 2022, vol. 607, issue C

Abstract: Due to the development of quantum algorithms, kinds of quantum generative adversarial networks (QGANs) are proposed to generate suitable samples for different application scenarios. However, the training of QGANs is often not smooth as expected, and the results are unsatisfactory since of the barren plateau. To solve the problems, we propose a QGANs framework based on Rényi divergence (RyQGAN), which avoids the barren plateau phenomenon in the training of QGANs. The quantum circuits to estimate the gradients for the updating parameters are designed, which shows how the gradients can be evaluated by a quantum processor. Finally, based on RyQGAN, we generate 2-qubit, 3-qubit, and 4-qubit Gibbs states. The simulation results show that the barren plateau is eliminated in the RyQGAN, and the average fidelity of RyQGAN with 50 epochs is higher than 99.8%, while that of quantum Wasserstein GANs is no more than 50%. Thus, the RyQGAN can be trained effectively and has further applications in quantum machine learning.

Keywords: Quantum algorithm; Quantum machine learning; Quantum generative adversarial networks (search for similar items in EconPapers)
Date: 2022
References: View references in EconPapers View complete reference list from CitEc
Citations: View citations in EconPapers (1)

Downloads: (external link)
http://www.sciencedirect.com/science/article/pii/S0378437122007270
Full text for ScienceDirect subscribers only. Journal offers the option of making the article available online on Science direct for a fee of $3,000

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:eee:phsmap:v:607:y:2022:i:c:s0378437122007270

DOI: 10.1016/j.physa.2022.128169

Access Statistics for this article

Physica A: Statistical Mechanics and its Applications is currently edited by K. A. Dawson, J. O. Indekeu, H.E. Stanley and C. Tsallis

More articles in Physica A: Statistical Mechanics and its Applications from Elsevier
Bibliographic data for series maintained by Catherine Liu ().