Metraipolis › archive › dc_1db367686e9d
Differentially Private Distributed Optimization via the Intrinsic Randomness of Zeroth-Order Estimators: Sampling Geometry, Convergence, and Privacy Guarantees — arXiv:2611.01373
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2611.01373
- License (as archived)
- CC0-1.0
- Archived
- 2026-11-03T18:45:24.395Z
- SHA-256 of the archived text
cceacf0a533fbecd13d66f16a4e9fe91c144cab4153a1b7cb79b0a1ed267c994- Stable URL of this page
https://metraipolis.com/documento/dc_1db367686e9d
How to cite
Differentially Private Distributed Optimization via the Intrinsic Randomness of Zeroth-Order Estimators: Sampling Geometry, Convergence, and Privacy Guarantees — arXiv:2611.01373 — arXiv (en), https://arxiv.org/abs/2611.01373 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_1db367686e9d (Metraipolis archive dc_1db367686e9d, sha256 cceacf0a533fbecd13d66f16a4e9fe91c144cab4153a1b7cb79b0a1ed267c994)
BibTeX
@misc{dc1db367686e9d,
title = {Differentially Private Distributed Optimization via the Intrinsic Randomness of Zeroth-Order Estimators: Sampling Geometry, Convergence, and Privacy Guarantees — arXiv:2611.01373},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2611.01373},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_1db367686e9d; sha256 cceacf0a533fbecd13d66f16a4e9fe91c144cab4153a1b7cb79b0a1ed267c994},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.01373. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Distributed zeroth-order optimization has gained increasing attention in applications where exact gradients are computationally expensive or unavailable. However, the iterative exchange of local decision variables makes distributed networks vulnerable to inference attacks. While differential privacy provides a rigorous framework for privacy protection, conventional approaches generally require additional random noise, which inevitably affects optimization accuracy. In this paper, we investigate whether the randomness inherent in zeroth-order estimation can itself provide privacy protection. We develop a distributed zeroth-order gradient descent method that integrates consensus updates with a ball-uniform two-point gradient estimator. Our theoretical analysis shows that our algorithm attains standard convergence guarantees in both online and offline optimization settings. We then characterize the relevant probability distributions of the associated privacy mechanism, and establish differential privacy guarantees for both the online and offline optimization settings. These results reveal the potential of intrinsic zeroth-order randomness for privacy protection. 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/2611.01373 — 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 2026-11-03T18:14:37.757Z dalla pagina https://arxiv.org/list/math.OC/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).