Matches in SemOpenAlex for { <https://semopenalex.org/work/W4321196271> ?p ?o ?g. }
- W4321196271 endingPage "110878" @default.
- W4321196271 startingPage "110878" @default.
- W4321196271 abstract "With decentralized optimization having increased applications in various domains ranging from machine learning, control, to robotics, its privacy is also receiving increased attention. Existing privacy solutions for decentralized optimization achieve privacy by patching information-technology privacy mechanisms such as differential privacy or homomorphic encryption, which either sacrifices optimization accuracy or incurs heavy computation/communication overhead. We propose an inherently privacy-preserving decentralized optimization algorithm by exploiting the robustness of decentralized optimization dynamics. More specifically, we present a general decentralized optimization framework, based on which we show that the privacy of participating nodes’ gradients can be protected by adding randomness in optimization parameters. We further show that the added randomness has no influence on the accuracy of optimization, and prove that our inherently privacy-preserving algorithm has R-linear convergence when the global objective function is smooth and strongly convex. We also prove that the proposed algorithm can avoid the gradient of a node from being inferable by other nodes. Simulation results confirm the theoretical predictions." @default.
- W4321196271 created "2023-02-18" @default.
- W4321196271 creator A5014592284 @default.
- W4321196271 creator A5052663817 @default.
- W4321196271 creator A5056715372 @default.
- W4321196271 date "2023-05-01" @default.
- W4321196271 modified "2023-10-15" @default.
- W4321196271 title "Dynamics based privacy preservation in decentralized optimization" @default.
- W4321196271 cites W1538118056 @default.
- W4321196271 cites W1571416372 @default.
- W4321196271 cites W1616857247 @default.
- W4321196271 cites W1993014346 @default.
- W4321196271 cites W1998345701 @default.
- W4321196271 cites W2004398490 @default.
- W4321196271 cites W2044212084 @default.
- W4321196271 cites W2099901267 @default.
- W4321196271 cites W2108924122 @default.
- W4321196271 cites W2115594466 @default.
- W4321196271 cites W2137435346 @default.
- W4321196271 cites W2149778463 @default.
- W4321196271 cites W2291434103 @default.
- W4321196271 cites W2527559122 @default.
- W4321196271 cites W2594659080 @default.
- W4321196271 cites W2606410458 @default.
- W4321196271 cites W2737743075 @default.
- W4321196271 cites W2765234683 @default.
- W4321196271 cites W2800873021 @default.
- W4321196271 cites W2810524107 @default.
- W4321196271 cites W2887374384 @default.
- W4321196271 cites W2887509958 @default.
- W4321196271 cites W2906629352 @default.
- W4321196271 cites W2946923486 @default.
- W4321196271 cites W2962678892 @default.
- W4321196271 cites W2962684828 @default.
- W4321196271 cites W2962703255 @default.
- W4321196271 cites W2962943778 @default.
- W4321196271 cites W2962989062 @default.
- W4321196271 cites W2963007855 @default.
- W4321196271 cites W2963649943 @default.
- W4321196271 cites W2963724567 @default.
- W4321196271 cites W2964008526 @default.
- W4321196271 cites W2987524100 @default.
- W4321196271 cites W2993317151 @default.
- W4321196271 cites W2993821328 @default.
- W4321196271 cites W3000785930 @default.
- W4321196271 cites W3003613721 @default.
- W4321196271 cites W3022767088 @default.
- W4321196271 cites W3099715789 @default.
- W4321196271 cites W3100491209 @default.
- W4321196271 cites W3100513551 @default.
- W4321196271 cites W3104851238 @default.
- W4321196271 cites W4298352039 @default.
- W4321196271 doi "https://doi.org/10.1016/j.automatica.2023.110878" @default.
- W4321196271 hasPublicationYear "2023" @default.
- W4321196271 type Work @default.
- W4321196271 citedByCount "0" @default.
- W4321196271 crossrefType "journal-article" @default.
- W4321196271 hasAuthorship W4321196271A5014592284 @default.
- W4321196271 hasAuthorship W4321196271A5052663817 @default.
- W4321196271 hasAuthorship W4321196271A5056715372 @default.
- W4321196271 hasBestOaLocation W43211962712 @default.
- W4321196271 hasConcept C104317684 @default.
- W4321196271 hasConcept C105795698 @default.
- W4321196271 hasConcept C108827166 @default.
- W4321196271 hasConcept C112680207 @default.
- W4321196271 hasConcept C11413529 @default.
- W4321196271 hasConcept C123201435 @default.
- W4321196271 hasConcept C125112378 @default.
- W4321196271 hasConcept C126255220 @default.
- W4321196271 hasConcept C137836250 @default.
- W4321196271 hasConcept C148730421 @default.
- W4321196271 hasConcept C157972887 @default.
- W4321196271 hasConcept C158338273 @default.
- W4321196271 hasConcept C162324750 @default.
- W4321196271 hasConcept C185592680 @default.
- W4321196271 hasConcept C23130292 @default.
- W4321196271 hasConcept C2524010 @default.
- W4321196271 hasConcept C2777303404 @default.
- W4321196271 hasConcept C31258907 @default.
- W4321196271 hasConcept C33923547 @default.
- W4321196271 hasConcept C41008148 @default.
- W4321196271 hasConcept C50522688 @default.
- W4321196271 hasConcept C55493867 @default.
- W4321196271 hasConcept C63479239 @default.
- W4321196271 hasConceptScore W4321196271C104317684 @default.
- W4321196271 hasConceptScore W4321196271C105795698 @default.
- W4321196271 hasConceptScore W4321196271C108827166 @default.
- W4321196271 hasConceptScore W4321196271C112680207 @default.
- W4321196271 hasConceptScore W4321196271C11413529 @default.
- W4321196271 hasConceptScore W4321196271C123201435 @default.
- W4321196271 hasConceptScore W4321196271C125112378 @default.
- W4321196271 hasConceptScore W4321196271C126255220 @default.
- W4321196271 hasConceptScore W4321196271C137836250 @default.
- W4321196271 hasConceptScore W4321196271C148730421 @default.
- W4321196271 hasConceptScore W4321196271C157972887 @default.
- W4321196271 hasConceptScore W4321196271C158338273 @default.
- W4321196271 hasConceptScore W4321196271C162324750 @default.
- W4321196271 hasConceptScore W4321196271C185592680 @default.