EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Statistical Privacy-Preserving Distributed Online Aggregative Games via Mirror Descent with Correlated Perturbations

Meng Yuan, Rui Yu

Mathematics · 18.05.2026 · 14 (10) · 1731

DOI: 10.3390/math14101731 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Mathematics, online erschienen am 18.05.2026. Verfasst von Meng Yuan und 1 weiteren Autor:innen. Die Arbeit nennt 29 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Distributed online aggregative games are widely used to model sequential decision-making problems in dynamic networked systems. However, the repeated information exchange required by distributed algorithms may disclose players’ sensitive local data. This paper investigates a privacy-preserving distributed online aggregative game over multi-agent networks. A distributed online mirror descent algorithm with correlated perturbations is developed to protect local private information. Under standard assumptions, an expected dynamic regret bound and a statistical privacy guarantee are established for the proposed algorithm. Numerical results demonstrate the effectiveness of the proposed algorithm and reveal the tradeoff between privacy protection and algorithmic performance.

Zitieren

APA

Yuan, M., & Yu, R. (2026). Statistical Privacy-Preserving Distributed Online Aggregative Games via Mirror Descent with Correlated Perturbations. Mathematics, 14(10), 1731. https://doi.org/10.3390/math14101731

Vancouver

Yuan M, Yu R. Statistical Privacy-Preserving Distributed Online Aggregative Games via Mirror Descent with Correlated Perturbations. Mathematics. 2026;14(10):1731. doi:10.3390/math14101731

BibTeX
@article{Yuan2026,
  author = {Yuan, Meng and Yu, Rui},
  title = {Statistical Privacy-Preserving Distributed Online Aggregative Games via Mirror Descent with Correlated Perturbations},
  journal = {Mathematics},
  year = {2026},
  volume = {14},
  number = {10},
  pages = {1731},
  doi = {10.3390/math14101731}
}
Kostenlos starten →