EUVIMEDEUVIMED entdecken
Crossref

Dynamics based privacy preservation in decentralized optimization

Huan Gao, Yongqiang Wang, Angelia Nedić

Automatica · 2023-05 · 151 · 110878

DOI: 10.1016/j.automatica.2023.110878 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Automatica, 2023-05. Verfasst von Huan Gao und 2 weiteren Autor:innen. Die Arbeit wurde bisher 36-mal zitiert (Crossref) und nennt 52 Literaturangaben. Gefördert von: National Science Foundation, NSF.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

With decentralized optimization having increased applications in various domains ranging from machine learning, control, sensor networks, to robotics, its privacy is also receiving increased attention. Existing privacy-preserving approaches for decentralized optimization achieve privacy preservation by patching decentralized optimization with information-technology privacy mechanisms such as differential privacy or homomorphic encryption, which either sacrifices optimization accuracy or incurs heavy computation/communication overhead. We propose an inherently privacy-preserving decentralized optimization algorithm by exploiting the robustness of decentralized optimization to uncertainties in optimization dynamics. More specifically, we present a general decentralized optimization framework, based on which we show that privacy can be enabled in decentralized optimization by adding randomness in optimization parameters. We further show that the added randomness has no influence on the accuracy of optimization, and prove that our inherently privacy-preserving algorithm has $R$-linear convergence when the global objective function is smooth and strongly convex. We also rigorously prove that the proposed algorithm can avoid the gradient of a node from being inferable by other nodes. Numerical simulation results confirm the theoretical predictions.

Förderung

  • National Science Foundation
  • NSF

Zitieren

APA

Gao, H., Wang, Y., & Nedić, A. (2023). Dynamics based privacy preservation in decentralized optimization. Automatica, 151, 110878. https://doi.org/10.1016/j.automatica.2023.110878

Vancouver

Gao H, Wang Y, Nedić A. Dynamics based privacy preservation in decentralized optimization. Automatica. 2023;151:110878. doi:10.1016/j.automatica.2023.110878

BibTeX
@article{Gao2023,
  author = {Gao, Huan and Wang, Yongqiang and Nedić, Angelia},
  title = {Dynamics based privacy preservation in decentralized optimization},
  journal = {Automatica},
  year = {2023},
  volume = {151},
  pages = {110878},
  doi = {10.1016/j.automatica.2023.110878}
}
Kostenlos starten →