Matches in SemOpenAlex for { <https://semopenalex.org/work/W4226341485> ?p ?o ?g. }
Showing items 1 to 55 of
55
with 100 items per page.
- W4226341485 abstract "Decentralized optimization is gaining increased traction due to its widespread applications in large-scale machine learning and multi-agent systems. The same mechanism that enables its success, i.e., information sharing among participating agents, however, also leads to the disclosure of individual agents' private information, which is unacceptable when sensitive data are involved. As differential privacy is becoming a de facto standard for privacy preservation, recently results have emerged integrating differential privacy with distributed optimization. However, directly incorporating differential privacy design in existing distributed optimization approaches significantly compromises optimization accuracy. In this paper, we propose to redesign and tailor gradient methods for differentially-private distributed optimization, and propose two differential-privacy oriented gradient methods that can ensure both rigorous epsilon-differential privacy and optimality. The first algorithm is based on static-consensus based gradient methods, and the second algorithm is based on dynamic-consensus (gradient-tracking) based distributed optimization methods and, hence, is applicable to general directed interaction graph topologies. Both algorithms can simultaneously ensure almost sure convergence to an optimal solution and a finite privacy budget, even when the number of iterations goes to infinity. To our knowledge, this is the first time that both goals are achieved simultaneously. Numerical simulations using a distributed estimation problem and experimental results on a benchmark dataset confirm the effectiveness of the proposed approaches." @default.
- W4226341485 created "2022-05-05" @default.
- W4226341485 creator A5014592284 @default.
- W4226341485 creator A5052663817 @default.
- W4226341485 date "2022-02-02" @default.
- W4226341485 modified "2023-09-24" @default.
- W4226341485 title "Tailoring Gradient Methods for Differentially-Private Distributed Optimization" @default.
- W4226341485 doi "https://doi.org/10.48550/arxiv.2202.01113" @default.
- W4226341485 hasPublicationYear "2022" @default.
- W4226341485 type Work @default.
- W4226341485 citedByCount "0" @default.
- W4226341485 crossrefType "posted-content" @default.
- W4226341485 hasAuthorship W4226341485A5014592284 @default.
- W4226341485 hasAuthorship W4226341485A5052663817 @default.
- W4226341485 hasBestOaLocation W42263414851 @default.
- W4226341485 hasConcept C11413529 @default.
- W4226341485 hasConcept C126255220 @default.
- W4226341485 hasConcept C13280743 @default.
- W4226341485 hasConcept C137836250 @default.
- W4226341485 hasConcept C162324750 @default.
- W4226341485 hasConcept C185798385 @default.
- W4226341485 hasConcept C205649164 @default.
- W4226341485 hasConcept C23130292 @default.
- W4226341485 hasConcept C2777303404 @default.
- W4226341485 hasConcept C33923547 @default.
- W4226341485 hasConcept C41008148 @default.
- W4226341485 hasConcept C50522688 @default.
- W4226341485 hasConceptScore W4226341485C11413529 @default.
- W4226341485 hasConceptScore W4226341485C126255220 @default.
- W4226341485 hasConceptScore W4226341485C13280743 @default.
- W4226341485 hasConceptScore W4226341485C137836250 @default.
- W4226341485 hasConceptScore W4226341485C162324750 @default.
- W4226341485 hasConceptScore W4226341485C185798385 @default.
- W4226341485 hasConceptScore W4226341485C205649164 @default.
- W4226341485 hasConceptScore W4226341485C23130292 @default.
- W4226341485 hasConceptScore W4226341485C2777303404 @default.
- W4226341485 hasConceptScore W4226341485C33923547 @default.
- W4226341485 hasConceptScore W4226341485C41008148 @default.
- W4226341485 hasConceptScore W4226341485C50522688 @default.
- W4226341485 hasLocation W42263414851 @default.
- W4226341485 hasOpenAccess W4226341485 @default.
- W4226341485 hasPrimaryLocation W42263414851 @default.
- W4226341485 hasRelatedWork W1987039528 @default.
- W4226341485 hasRelatedWork W2113807069 @default.
- W4226341485 hasRelatedWork W2136258730 @default.
- W4226341485 hasRelatedWork W2187613024 @default.
- W4226341485 hasRelatedWork W2289289167 @default.
- W4226341485 hasRelatedWork W2613673799 @default.
- W4226341485 hasRelatedWork W2895841339 @default.
- W4226341485 hasRelatedWork W2967293417 @default.
- W4226341485 hasRelatedWork W3115948200 @default.
- W4226341485 hasRelatedWork W3206863852 @default.
- W4226341485 isParatext "false" @default.
- W4226341485 isRetracted "false" @default.
- W4226341485 workType "article" @default.