Journal article · 2026 · Open access

Theoretical insights into CycleGAN: Analyzing approximation and estimation errors in unpaired data generation

Luwei Sun, Dongrui Shen, Feng Han

Artificial Intelligence, 355, 104526 · Published 24 March 2026 · DOI 10.1016/j.artint.2026.104526

Open PDFView at the publisherCite this paper

In brief

“Theoretical insights into CycleGAN: Analyzing approximation and estimation errors in unpaired data generation” is a 2026 journal article by Luwei Sun and 2 co-authors, published in Artificial Intelligence. OpenAlex counts 7 citations as of 17 November 2026, which puts it in the top 5% of works published in 2026 by citations. It is open access: the full text is free to read at arXiv (Cornell University).

Citations
7
Most cited in
2025 (4)
Field-weighted impact
4.41
References
38
Authors
3

Cite this paper

Formatted from the catalogue record. Check names, capitals and page numbers against the paper before you submit.

APA 7

Sun, L., Shen, D., & Han, F. (2026). Theoretical insights into CycleGAN: Analyzing approximation and estimation errors in unpaired data generation. Artificial Intelligence, 355, 104526. https://doi.org/10.1016/j.artint.2026.104526

MLA 9

Sun, Luwei, et al. “Theoretical insights into CycleGAN: Analyzing approximation and estimation errors in unpaired data generation.” Artificial Intelligence, vol. 355, 2026, p. 104526. https://doi.org/10.1016/j.artint.2026.104526.

Chicago

Sun, Luwei, Dongrui Shen, and Feng Han. 2026. “Theoretical insights into CycleGAN: Analyzing approximation and estimation errors in unpaired data generation.” Artificial Intelligence 355: 104526. https://doi.org/10.1016/j.artint.2026.104526.

Harvard

Sun, L., Shen, D. and Han, F. (2026) ‘Theoretical insights into CycleGAN: Analyzing approximation and estimation errors in unpaired data generation’, Artificial Intelligence, 355, p. 104526. doi:10.1016/j.artint.2026.104526.

IEEE

L. Sun, D. Shen, and F. Han, “Theoretical insights into CycleGAN: Analyzing approximation and estimation errors in unpaired data generation,” Artificial Intelligence, vol. 355, p. 104526, 2026, doi: 10.1016/j.artint.2026.104526.

BibTeX

@article{sun2026theoretical,
  title     = {{Theoretical insights into CycleGAN: Analyzing approximation and estimation errors in unpaired data generation}},
  author    = {Sun, Luwei and Shen, Dongrui and Han, Feng},
  journal   = {Artificial Intelligence},
  year      = {2026},
  volume    = {355},
  pages     = {104526},
  doi       = {10.1016/j.artint.2026.104526},
  url       = {https://doi.org/10.1016/j.artint.2026.104526}
}

Download for a reference manager: BibTeX (.bib) · RIS for Zotero, Mendeley and EndNote (.ris)

Topic and keywords

Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Generative Adversarial Networks and Image Synthesis

  • CycleGAN
  • cycle consistency
  • excess risk
  • approximation error
  • estimation error
  • optimal transport maps
  • Rademacher complexity
  • generative adversarial networks

Work with this paper

Most-cited papers in Computer Science

All highly cited Computer Science papers

Questions about this paper

How do I cite this paper in APA style?

Sun, L., Shen, D., & Han, F. (2026). Theoretical insights into CycleGAN: Analyzing approximation and estimation errors in unpaired data generation. Artificial Intelligence, 355, 104526. https://doi.org/10.1016/j.artint.2026.104526

How many times has this paper been cited?

7 times, according to OpenAlex on 17 November 2026. Google Scholar and Scopus count different sets of sources, so their numbers differ.

Is this paper free to read?

Yes. It is open access at arXiv (Cornell University): sign in and open the PDF from this page.

Who wrote this paper?

Luwei Sun, Dongrui Shen, Feng Han.

What is the DOI of this paper?

10.1016/j.artint.2026.104526, permanently at https://doi.org/10.1016/j.artint.2026.104526. Sign in and open it from this page.

Bibliographic data from OpenAlex (CC0), last checked 17 November 2026. ResearchGuru does not host this paper; once you are signed in, the links open it at the publisher or the repository that does.