Metraipolis › archive › dc_fa0daba263a2

Communication-Efficient Differentially Private Gradient Tracking for Distributed Optimization via Local Updates — arXiv:2610.04854

Source: arXiv (en)
Original: https://arxiv.org/abs/2610.04854
License (as archived): CC0-1.0
Archived: 2026-10-06T13:05:34.289Z
SHA-256 of the archived text: 7da25d96beb9816d81391ba6297ab6ff6b37d2e025d841e8d9a849055899b6b1
Stable URL of this page: https://metraipolis.com/documento/dc_fa0daba263a2

How to cite

Communication-Efficient Differentially Private Gradient Tracking for Distributed Optimization via Local Updates — arXiv:2610.04854 — arXiv (en), https://arxiv.org/abs/2610.04854 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_fa0daba263a2 (Metraipolis archive dc_fa0daba263a2, sha256 7da25d96beb9816d81391ba6297ab6ff6b37d2e025d841e8d9a849055899b6b1)

BibTeX

@misc{dcfa0daba263a2,
  title = {Communication-Efficient Differentially Private Gradient Tracking for Distributed Optimization via Local Updates — arXiv:2610.04854},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.04854},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_fa0daba263a2; sha256 7da25d96beb9816d81391ba6297ab6ff6b37d2e025d841e8d9a849055899b6b1},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.04854. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

This paper studies privacy-preserving distributed optimization using gradient tracking with one communication-free local update between consecutive communication rounds. Since local computation alone does not protect gradient information, we perturb both the primal state and the gradient-tracking direction at communication iterations while keeping local updates noise-free. We establish an aggregate variable for tracking, characterize the limiting consensus point in the presence of added random noise, and prove convergence in mean under certain parameter conditions. We also establish infinite-horizon pure differential privacy for the complete communication transcript under an affine objective adjacency relation and geometrically decaying Laplace perturbations. Simulation results illustrate the advantages of the proposed method in terms of the convergence and optimization accuracy given a privacy budget.

Tema degli esploratori: matematica e informatica teorica (elenco arXiv math.OC, nuovi lavori del giorno).
Categorie arXiv: Optimization and Control (math.OC) ; Systems and Control (eess.SY).
Pagina del lavoro: https://arxiv.org/abs/2610.04854 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-06T11:21:31.897Z dalla pagina https://arxiv.org/list/math.OC/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).