Matches in SemOpenAlex for { <https://semopenalex.org/work/W2989361410> ?p ?o ?g. }
Showing items 1 to 86 of
86
with 100 items per page.
- W2989361410 abstract "This work proposes a theoretical analysis of distributed optimization of convex functions using a network of computing units. We investigate this problem under two communication schemes (centralized and decentralized) and four classical regularity assumptions: Lipschitz continuity, strong convexity, smoothness, and a combination of strong convexity and smoothness. Under the decentralized communication scheme, we provide matching upper and lower bounds of complexity along with algorithms achieving this rate up to logarithmic constants. For non-smooth objective functions, while the dominant term of the error is in $O(1/sqrt{t})$, the structure of the communication network only impacts a second-order term in $O(1/t)$, where $t$ is time. In other words, the error due to limits in communication resources decreases at a fast rate even in the case of non-strongly convex objective functions. Such a convergence rate is achieved by the novel multi-step primal-dual (MSPD) algorithm. Under the centralized communication scheme, we show that the naive distribution of standard optimization algorithms is optimal for smooth objective functions, and provide a simple yet efficient algorithm called distributed randomized smoothing (DRS) based on a local smoothing of the objective function for non-smooth functions. We then show that DRS is within a $d^{1/4}$ multiplicative factor of the optimal convergence rate, where $d$ is the underlying dimension." @default.
- W2989361410 created "2019-11-22" @default.
- W2989361410 creator A5001483226 @default.
- W2989361410 creator A5007698196 @default.
- W2989361410 creator A5021842384 @default.
- W2989361410 creator A5024980585 @default.
- W2989361410 creator A5056747950 @default.
- W2989361410 date "2019-01-01" @default.
- W2989361410 modified "2023-10-17" @default.
- W2989361410 title "Optimal Convergence Rates for Convex Distributed Optimization in Networks" @default.
- W2989361410 cites W1993111701 @default.
- W2989361410 cites W2057873962 @default.
- W2989361410 cites W2092663520 @default.
- W2989361410 cites W2117905067 @default.
- W2989361410 cites W2123705108 @default.
- W2989361410 cites W2129122308 @default.
- W2989361410 cites W2216483973 @default.
- W2989361410 cites W2539133644 @default.
- W2989361410 cites W2587943776 @default.
- W2989361410 cites W2590635385 @default.
- W2989361410 cites W2611960733 @default.
- W2989361410 cites W2892209803 @default.
- W2989361410 cites W2894941002 @default.
- W2989361410 cites W2911327153 @default.
- W2989361410 cites W2962720772 @default.
- W2989361410 cites W2962756315 @default.
- W2989361410 cites W2962897077 @default.
- W2989361410 cites W2963326510 @default.
- W2989361410 cites W2963649943 @default.
- W2989361410 cites W2963834323 @default.
- W2989361410 cites W2964181194 @default.
- W2989361410 cites W2964183442 @default.
- W2989361410 cites W3141595720 @default.
- W2989361410 hasPublicationYear "2019" @default.
- W2989361410 type Work @default.
- W2989361410 sameAs 2989361410 @default.
- W2989361410 citedByCount "23" @default.
- W2989361410 countsByYear W29893614102018 @default.
- W2989361410 countsByYear W29893614102019 @default.
- W2989361410 countsByYear W29893614102020 @default.
- W2989361410 countsByYear W29893614102021 @default.
- W2989361410 countsByYear W29893614102022 @default.
- W2989361410 countsByYear W29893614102023 @default.
- W2989361410 crossrefType "journal-article" @default.
- W2989361410 hasAuthorship W2989361410A5001483226 @default.
- W2989361410 hasAuthorship W2989361410A5007698196 @default.
- W2989361410 hasAuthorship W2989361410A5021842384 @default.
- W2989361410 hasAuthorship W2989361410A5024980585 @default.
- W2989361410 hasAuthorship W2989361410A5056747950 @default.
- W2989361410 hasBestOaLocation W29893614101 @default.
- W2989361410 hasConcept C112680207 @default.
- W2989361410 hasConcept C126255220 @default.
- W2989361410 hasConcept C157972887 @default.
- W2989361410 hasConcept C162324750 @default.
- W2989361410 hasConcept C2524010 @default.
- W2989361410 hasConcept C2777303404 @default.
- W2989361410 hasConcept C33923547 @default.
- W2989361410 hasConcept C41008148 @default.
- W2989361410 hasConcept C50522688 @default.
- W2989361410 hasConceptScore W2989361410C112680207 @default.
- W2989361410 hasConceptScore W2989361410C126255220 @default.
- W2989361410 hasConceptScore W2989361410C157972887 @default.
- W2989361410 hasConceptScore W2989361410C162324750 @default.
- W2989361410 hasConceptScore W2989361410C2524010 @default.
- W2989361410 hasConceptScore W2989361410C2777303404 @default.
- W2989361410 hasConceptScore W2989361410C33923547 @default.
- W2989361410 hasConceptScore W2989361410C41008148 @default.
- W2989361410 hasConceptScore W2989361410C50522688 @default.
- W2989361410 hasLocation W29893614101 @default.
- W2989361410 hasLocation W29893614102 @default.
- W2989361410 hasOpenAccess W2989361410 @default.
- W2989361410 hasPrimaryLocation W29893614101 @default.
- W2989361410 hasRelatedWork W2589063463 @default.
- W2989361410 hasRelatedWork W2747249330 @default.
- W2989361410 hasRelatedWork W2811008754 @default.
- W2989361410 hasRelatedWork W2953109382 @default.
- W2989361410 hasRelatedWork W2992250528 @default.
- W2989361410 hasRelatedWork W3003165794 @default.
- W2989361410 hasRelatedWork W4287899549 @default.
- W2989361410 hasRelatedWork W4297899479 @default.
- W2989361410 hasRelatedWork W4302370212 @default.
- W2989361410 hasRelatedWork W4310429815 @default.
- W2989361410 isParatext "false" @default.
- W2989361410 isRetracted "false" @default.
- W2989361410 magId "2989361410" @default.
- W2989361410 workType "article" @default.