FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4285148794> ?p ?o ?g. }

• W4285148794 endingPage "2139" @default.
• W4285148794 startingPage "2125" @default.
• W4285148794 abstract "In this article, we study decentralized convex constrained optimization problems in networks. We focus on the dual averaging-based algorithmic framework that is well-documented to be superior in handling constraints and complex communication environments simultaneously. Two new decentralized dual averaging (DDA) algorithms are proposed. In the first one, a second-order dynamic average consensus protocol is tailored for DDA-type algorithms, which equips each agent with a provably more accurate estimate of the global dual variable than conventional schemes. We rigorously prove that the proposed algorithm attains <inline-formula xmlns:mml=http://www.w3.org/1998/Math/MathML xmlns:xlink=http://www.w3.org/1999/xlink><tex-math notation=LaTeX>$mathcal {O}(1/t)$</tex-math></inline-formula> convergence for general convex and smooth problems, for which existing DDA methods were only known to converge at <inline-formula xmlns:mml=http://www.w3.org/1998/Math/MathML xmlns:xlink=http://www.w3.org/1999/xlink><tex-math notation=LaTeX>$mathcal {O}(1/sqrt{t})$</tex-math></inline-formula> prior to our work. In the second one, we use the extrapolation technique to accelerate the convergence of DDA. Compared to existing accelerated algorithms, where typically two different variables are exchanged among agents at each time, the proposed algorithm only seeks consensus on local gradients. Then, the extrapolation is performed based on two sequences of primal variables, which are determined by the accumulations of gradients at two consecutive time instants, respectively. The algorithm is proved to converge at <inline-formula xmlns:mml=http://www.w3.org/1998/Math/MathML xmlns:xlink=http://www.w3.org/1999/xlink><tex-math notation=LaTeX>$mathcal {O}(1)left(frac{1}{t^{2}}+frac{1}{t(1-beta)^{2}}right)$</tex-math></inline-formula> , where <inline-formula xmlns:mml=http://www.w3.org/1998/Math/MathML xmlns:xlink=http://www.w3.org/1999/xlink><tex-math notation=LaTeX>$beta$</tex-math></inline-formula> denotes the second largest singular value of the mixing matrix. We remark that the condition for the algorithmic parameter to guarantee convergence does not rely on the spectrum of the mixing matrix, making itself easy to satisfy in practice. Finally, numerical results are presented to demonstrate the efficiency of the proposed methods." @default.
• W4285148794 created "2022-07-14" @default.
• W4285148794 creator A5003088149 @default.
• W4285148794 creator A5028730873 @default.
• W4285148794 creator A5048267931 @default.
• W4285148794 creator A5074550946 @default.
• W4285148794 date "2023-04-01" @default.
• W4285148794 modified "2023-09-25" @default.
• W4285148794 title "Accelerated Dual Averaging Methods for Decentralized Constrained Optimization" @default.
• W4285148794 cites W1571416372 @default.
• W4285148794 cites W1616857247 @default.
• W4285148794 cites W1627780903 @default.
• W4285148794 cites W1994860969 @default.
• W4285148794 cites W2044212084 @default.
• W4285148794 cites W2063403497 @default.
• W4285148794 cites W2074796812 @default.
• W4285148794 cites W2114791779 @default.
• W4285148794 cites W2123705108 @default.
• W4285148794 cites W2129122308 @default.
• W4285148794 cites W2169713291 @default.
• W4285148794 cites W2180180824 @default.
• W4285148794 cites W2243169878 @default.
• W4285148794 cites W2291434103 @default.
• W4285148794 cites W2328649617 @default.
• W4285148794 cites W2535496140 @default.
• W4285148794 cites W2607045744 @default.
• W4285148794 cites W2782375002 @default.
• W4285148794 cites W2811008754 @default.
• W4285148794 cites W2946038967 @default.
• W4285148794 cites W2962989062 @default.
• W4285148794 cites W2963133220 @default.
• W4285148794 cites W2963649943 @default.
• W4285148794 cites W2963732316 @default.
• W4285148794 cites W2964191394 @default.
• W4285148794 cites W2967933985 @default.
• W4285148794 cites W2998882145 @default.
• W4285148794 cites W3003430042 @default.
• W4285148794 cites W3016897523 @default.
• W4285148794 cites W3081144209 @default.
• W4285148794 cites W3100513551 @default.
• W4285148794 cites W3101665129 @default.
• W4285148794 cites W3102661755 @default.
• W4285148794 cites W3104871901 @default.
• W4285148794 cites W3126592366 @default.
• W4285148794 doi "https://doi.org/10.1109/tac.2022.3173062" @default.
• W4285148794 hasPublicationYear "2023" @default.
• W4285148794 type Work @default.
• W4285148794 citedByCount "1" @default.
• W4285148794 countsByYear W42851487942023 @default.
• W4285148794 crossrefType "journal-article" @default.
• W4285148794 hasAuthorship W4285148794A5003088149 @default.
• W4285148794 hasAuthorship W4285148794A5028730873 @default.
• W4285148794 hasAuthorship W4285148794A5048267931 @default.
• W4285148794 hasAuthorship W4285148794A5074550946 @default.
• W4285148794 hasBestOaLocation W42851487942 @default.
• W4285148794 hasConcept C105795698 @default.
• W4285148794 hasConcept C112680207 @default.
• W4285148794 hasConcept C11413529 @default.
• W4285148794 hasConcept C118615104 @default.
• W4285148794 hasConcept C124952713 @default.
• W4285148794 hasConcept C126255220 @default.
• W4285148794 hasConcept C132459708 @default.
• W4285148794 hasConcept C134306372 @default.
• W4285148794 hasConcept C142362112 @default.
• W4285148794 hasConcept C145446738 @default.
• W4285148794 hasConcept C162324750 @default.
• W4285148794 hasConcept C182365436 @default.
• W4285148794 hasConcept C2524010 @default.
• W4285148794 hasConcept C2777303404 @default.
• W4285148794 hasConcept C2780980858 @default.
• W4285148794 hasConcept C28826006 @default.
• W4285148794 hasConcept C33923547 @default.
• W4285148794 hasConcept C41008148 @default.
• W4285148794 hasConcept C45357846 @default.
• W4285148794 hasConcept C50522688 @default.
• W4285148794 hasConcept C94375191 @default.
• W4285148794 hasConceptScore W4285148794C105795698 @default.
• W4285148794 hasConceptScore W4285148794C112680207 @default.
• W4285148794 hasConceptScore W4285148794C11413529 @default.
• W4285148794 hasConceptScore W4285148794C118615104 @default.
• W4285148794 hasConceptScore W4285148794C124952713 @default.
• W4285148794 hasConceptScore W4285148794C126255220 @default.
• W4285148794 hasConceptScore W4285148794C132459708 @default.
• W4285148794 hasConceptScore W4285148794C134306372 @default.
• W4285148794 hasConceptScore W4285148794C142362112 @default.
• W4285148794 hasConceptScore W4285148794C145446738 @default.
• W4285148794 hasConceptScore W4285148794C162324750 @default.
• W4285148794 hasConceptScore W4285148794C182365436 @default.
• W4285148794 hasConceptScore W4285148794C2524010 @default.
• W4285148794 hasConceptScore W4285148794C2777303404 @default.
• W4285148794 hasConceptScore W4285148794C2780980858 @default.
• W4285148794 hasConceptScore W4285148794C28826006 @default.
• W4285148794 hasConceptScore W4285148794C33923547 @default.
• W4285148794 hasConceptScore W4285148794C41008148 @default.
• W4285148794 hasConceptScore W4285148794C45357846 @default.
• W4285148794 hasConceptScore W4285148794C50522688 @default.
• W4285148794 hasConceptScore W4285148794C94375191 @default.
• W4285148794 hasFunder F4320321001 @default.

• next