A Privacy-Masking Learning Algorithm for Online Distributed Optimization over Time-Varying Unbalanced Digraphs

This paper investigates a constrained distributed optimization problem enabled by differential privacy where the underlying network is time-changing with unbalanced digraphs. To solve such a problem, we first propose a differentially private online distributed algorithm by injecting adaptively adjus...

Full description

Saved in:
Bibliographic Details
Main Authors: Rong Hu, Binru Zhang
Format: Article
Language:English
Published: Wiley 2021-01-01
Series:Journal of Mathematics
Online Access:http://dx.doi.org/10.1155/2021/6115451
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849696170666885120
author Rong Hu
Binru Zhang
author_facet Rong Hu
Binru Zhang
author_sort Rong Hu
collection DOAJ
description This paper investigates a constrained distributed optimization problem enabled by differential privacy where the underlying network is time-changing with unbalanced digraphs. To solve such a problem, we first propose a differentially private online distributed algorithm by injecting adaptively adjustable Laplace noises. The proposed algorithm can not only protect the privacy of participants without compromising a trusted third party, but also be implemented on more general time-varying unbalanced digraphs. Under mild conditions, we then show that the proposed algorithm can achieve a sublinear expected bound of regret for general local convex objective functions. The result shows that there is a trade-off between the optimization accuracy and privacy level. Finally, numerical simulations are conducted to validate the efficiency of the proposed algorithm.
format Article
id doaj-art-cc4f81876be3408eacb60c3a1f4a9268
institution DOAJ
issn 2314-4785
language English
publishDate 2021-01-01
publisher Wiley
record_format Article
series Journal of Mathematics
spelling doaj-art-cc4f81876be3408eacb60c3a1f4a92682025-08-20T03:19:32ZengWileyJournal of Mathematics2314-47852021-01-01202110.1155/2021/6115451A Privacy-Masking Learning Algorithm for Online Distributed Optimization over Time-Varying Unbalanced DigraphsRong Hu0Binru Zhang1School of MathematicsSchool of Finance and EconomicsThis paper investigates a constrained distributed optimization problem enabled by differential privacy where the underlying network is time-changing with unbalanced digraphs. To solve such a problem, we first propose a differentially private online distributed algorithm by injecting adaptively adjustable Laplace noises. The proposed algorithm can not only protect the privacy of participants without compromising a trusted third party, but also be implemented on more general time-varying unbalanced digraphs. Under mild conditions, we then show that the proposed algorithm can achieve a sublinear expected bound of regret for general local convex objective functions. The result shows that there is a trade-off between the optimization accuracy and privacy level. Finally, numerical simulations are conducted to validate the efficiency of the proposed algorithm.http://dx.doi.org/10.1155/2021/6115451
spellingShingle Rong Hu
Binru Zhang
A Privacy-Masking Learning Algorithm for Online Distributed Optimization over Time-Varying Unbalanced Digraphs
Journal of Mathematics
title A Privacy-Masking Learning Algorithm for Online Distributed Optimization over Time-Varying Unbalanced Digraphs
title_full A Privacy-Masking Learning Algorithm for Online Distributed Optimization over Time-Varying Unbalanced Digraphs
title_fullStr A Privacy-Masking Learning Algorithm for Online Distributed Optimization over Time-Varying Unbalanced Digraphs
title_full_unstemmed A Privacy-Masking Learning Algorithm for Online Distributed Optimization over Time-Varying Unbalanced Digraphs
title_short A Privacy-Masking Learning Algorithm for Online Distributed Optimization over Time-Varying Unbalanced Digraphs
title_sort privacy masking learning algorithm for online distributed optimization over time varying unbalanced digraphs
url http://dx.doi.org/10.1155/2021/6115451
work_keys_str_mv AT ronghu aprivacymaskinglearningalgorithmforonlinedistributedoptimizationovertimevaryingunbalanceddigraphs
AT binruzhang aprivacymaskinglearningalgorithmforonlinedistributedoptimizationovertimevaryingunbalanceddigraphs
AT ronghu privacymaskinglearningalgorithmforonlinedistributedoptimizationovertimevaryingunbalanceddigraphs
AT binruzhang privacymaskinglearningalgorithmforonlinedistributedoptimizationovertimevaryingunbalanceddigraphs