Vis enkel innførsel

dc.contributor.authorGratton, Cristiano
dc.contributor.authorKumar Dasanadoddi Venkategowda, Naveen
dc.contributor.authorArablouei, Reza
dc.contributor.authorWerner, Stefan
dc.date.accessioned2022-04-21T12:53:12Z
dc.date.available2022-04-21T12:53:12Z
dc.date.created2022-02-08T09:25:21Z
dc.date.issued2022
dc.identifier.citationIEEE Transactions on Information Forensics and Security. 2022, 17 265-279.en_US
dc.identifier.issn1556-6013
dc.identifier.urihttps://hdl.handle.net/11250/2992040
dc.description.abstractWe develop a privacy-preserving distributed algorithm to minimize a regularized empirical risk function when the first-order information is not available and data is distributed over a multi-agent network. We employ a zeroth-order method to minimize the associated augmented Lagrangian function in the primal domain using the alternating direction method of multipliers (ADMM). We show that the proposed algorithm, named distributed zeroth-order ADMM (D-ZOA), has intrinsic privacy-preserving properties. Most existing privacy-preserving distributed optimization/estimation algorithms exploit some perturbation mechanism to preserve privacy, which comes at the cost of reduced accuracy. Contrarily, by analyzing the inherent randomness due to the use of a zeroth-order method, we show that D-ZOA is intrinsically endowed with (ϵ,δ)− differential privacy. In addition, we employ the moments accountant method to show that the total privacy leakage of D-ZOA grows sublinearly with the number of ADMM iterations. D-ZOA outperforms the existing differentially-private approaches in terms of accuracy while yielding similar privacy guarantee. We prove that D-ZOA reaches a neighborhood of the optimal solution whose size depends on the privacy parameter. The convergence analysis also reveals a practically important trade-off between privacy and accuracy. Simulation results verify the desirable privacy-preserving properties of D-ZOA and its superiority over the state-of-the-art algorithms as well as its network-wide convergence.en_US
dc.language.isoengen_US
dc.publisherInstitute of Electrical and Electronics Engineers (IEEE)en_US
dc.titlePrivacy-Preserved Distributed Learning With Zeroth-Order Optimizationen_US
dc.typePeer revieweden_US
dc.typeJournal articleen_US
dc.description.versionacceptedVersionen_US
dc.rights.holder© IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.en_US
dc.source.pagenumber265-279en_US
dc.source.volume17en_US
dc.source.journalIEEE Transactions on Information Forensics and Securityen_US
dc.identifier.doi10.1109/TIFS.2021.3139267
dc.identifier.cristin1998881
dc.relation.projectNorges forskningsråd: 300102en_US
cristin.ispublishedtrue
cristin.fulltextpostprint
cristin.qualitycode2


Tilhørende fil(er)

Thumbnail

Denne innførselen finnes i følgende samling(er)

Vis enkel innførsel