FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4283653504> ?p ?o ?g. }

• W4283653504 endingPage "283" @default.
• W4283653504 startingPage "267" @default.
• W4283653504 abstract "Abstract The computational bottleneck in distributed optimization methods, which is based on projected gradient descent, is due to the computation of a full gradient vector and projection step. This is a particular problem for large datasets. To reduce the computational complexity of existing methods, we combine the randomized block-coordinate descent and the Frank–Wolfe techniques, and then propose a distributed randomized block-coordinate projection-free algorithm over networks, where each agent randomly chooses a subset of the coordinates of its gradient vector and the projection step is eschewed in favor of a much simpler linear optimization step. Moreover, the convergence performance of the proposed algorithm is also theoretically analyzed. Specifically, we rigorously prove that the proposed algorithm can converge to optimal point at rate of $${mathcal {O}}(1/t)$$ <mml:math xmlns:mml=http://www.w3.org/1998/Math/MathML> <mml:mrow> <mml:mi>O</mml:mi> <mml:mo>(</mml:mo> <mml:mn>1</mml:mn> <mml:mo>/</mml:mo> <mml:mi>t</mml:mi> <mml:mo>)</mml:mo> </mml:mrow> </mml:math> under convexity and $${mathcal {O}}(1/t^2)$$ <mml:math xmlns:mml=http://www.w3.org/1998/Math/MathML> <mml:mrow> <mml:mi>O</mml:mi> <mml:mo>(</mml:mo> <mml:mn>1</mml:mn> <mml:mo>/</mml:mo> <mml:msup> <mml:mi>t</mml:mi> <mml:mn>2</mml:mn> </mml:msup> <mml:mo>)</mml:mo> </mml:mrow> </mml:math> under strong convexity, respectively. Here, t is the number of iterations. Furthermore, the proposed algorithm can converge to a stationary point, where the “Frank-Wolfe” gap is equal to zero, at a rate $${mathcal {O}}(1/sqrt{t})$$ <mml:math xmlns:mml=http://www.w3.org/1998/Math/MathML> <mml:mrow> <mml:mi>O</mml:mi> <mml:mo>(</mml:mo> <mml:mn>1</mml:mn> <mml:mo>/</mml:mo> <mml:msqrt> <mml:mi>t</mml:mi> </mml:msqrt> <mml:mo>)</mml:mo> </mml:mrow> </mml:math> under non-convexity. To evaluate the computational benefit of the proposed algorithm, we use the proposed algorithm to solve the multiclass classification problems by simulation experiments on two datasets, i.e., aloi and news20. The results shows that the proposed algorithm is faster than the existing distributed optimization algorithms due to its lower computation per iteration. Furthermore, the results also show that well-connected graphs or smaller graphs leads to faster convergence rate, which can confirm the theoretical results." @default.
• W4283653504 created "2022-06-29" @default.
• W4283653504 creator A5001636340 @default.
• W4283653504 creator A5027721209 @default.
• W4283653504 creator A5040868833 @default.
• W4283653504 creator A5050705532 @default.
• W4283653504 creator A5080439384 @default.
• W4283653504 date "2022-06-28" @default.
• W4283653504 modified "2023-10-05" @default.
• W4283653504 title "A distributed gradient algorithm based on randomized block-coordinate and projection-free over networks" @default.
• W4283653504 cites W1553023756 @default.
• W4283653504 cites W1571416372 @default.
• W4283653504 cites W1982545958 @default.
• W4283653504 cites W1989165177 @default.
• W4283653504 cites W2002745466 @default.
• W4283653504 cites W2003146967 @default.
• W4283653504 cites W2032395696 @default.
• W4283653504 cites W2044212084 @default.
• W4283653504 cites W2090954940 @default.
• W4283653504 cites W2094336028 @default.
• W4283653504 cites W2095984592 @default.
• W4283653504 cites W2108924122 @default.
• W4283653504 cites W2114085163 @default.
• W4283653504 cites W2114791779 @default.
• W4283653504 cites W2115594466 @default.
• W4283653504 cites W2117686388 @default.
• W4283653504 cites W2123705108 @default.
• W4283653504 cites W2129122308 @default.
• W4283653504 cites W2132650954 @default.
• W4283653504 cites W2136885855 @default.
• W4283653504 cites W2154834860 @default.
• W4283653504 cites W2290318971 @default.
• W4283653504 cites W2291892967 @default.
• W4283653504 cites W2345689776 @default.
• W4283653504 cites W2481906283 @default.
• W4283653504 cites W2491324263 @default.
• W4283653504 cites W2515403150 @default.
• W4283653504 cites W2537046506 @default.
• W4283653504 cites W2564612348 @default.
• W4283653504 cites W2809028195 @default.
• W4283653504 cites W2893025380 @default.
• W4283653504 cites W2963118811 @default.
• W4283653504 cites W2963172825 @default.
• W4283653504 cites W2963213190 @default.
• W4283653504 cites W2963607435 @default.
• W4283653504 cites W2963649943 @default.
• W4283653504 cites W3043048378 @default.
• W4283653504 cites W3100513551 @default.
• W4283653504 cites W3101665129 @default.
• W4283653504 cites W3103669764 @default.
• W4283653504 cites W3104851238 @default.
• W4283653504 cites W3104871901 @default.
• W4283653504 cites W3119344485 @default.
• W4283653504 cites W3129044570 @default.
• W4283653504 cites W3129321571 @default.
• W4283653504 cites W3131057411 @default.
• W4283653504 cites W3140211828 @default.
• W4283653504 cites W3168628396 @default.
• W4283653504 cites W3202016380 @default.
• W4283653504 cites W4292363360 @default.
• W4283653504 cites W866281365 @default.
• W4283653504 doi "https://doi.org/10.1007/s40747-022-00785-8" @default.
• W4283653504 hasPublicationYear "2022" @default.
• W4283653504 type Work @default.
• W4283653504 citedByCount "1" @default.
• W4283653504 countsByYear W42836535042023 @default.
• W4283653504 crossrefType "journal-article" @default.
• W4283653504 hasAuthorship W4283653504A5001636340 @default.
• W4283653504 hasAuthorship W4283653504A5027721209 @default.
• W4283653504 hasAuthorship W4283653504A5040868833 @default.
• W4283653504 hasAuthorship W4283653504A5050705532 @default.
• W4283653504 hasAuthorship W4283653504A5080439384 @default.
• W4283653504 hasBestOaLocation W42836535041 @default.
• W4283653504 hasConcept C11413529 @default.
• W4283653504 hasConcept C153258448 @default.
• W4283653504 hasConcept C154945302 @default.
• W4283653504 hasConcept C157553263 @default.
• W4283653504 hasConcept C2524010 @default.
• W4283653504 hasConcept C2777210771 @default.
• W4283653504 hasConcept C33923547 @default.
• W4283653504 hasConcept C41008148 @default.
• W4283653504 hasConcept C50644808 @default.
• W4283653504 hasConcept C57493831 @default.
• W4283653504 hasConceptScore W4283653504C11413529 @default.
• W4283653504 hasConceptScore W4283653504C153258448 @default.
• W4283653504 hasConceptScore W4283653504C154945302 @default.
• W4283653504 hasConceptScore W4283653504C157553263 @default.
• W4283653504 hasConceptScore W4283653504C2524010 @default.
• W4283653504 hasConceptScore W4283653504C2777210771 @default.
• W4283653504 hasConceptScore W4283653504C33923547 @default.
• W4283653504 hasConceptScore W4283653504C41008148 @default.
• W4283653504 hasConceptScore W4283653504C50644808 @default.
• W4283653504 hasConceptScore W4283653504C57493831 @default.
• W4283653504 hasFunder F4320321001 @default.
• W4283653504 hasIssue "1" @default.
• W4283653504 hasLocation W42836535041 @default.
• W4283653504 hasOpenAccess W4283653504 @default.
• W4283653504 hasPrimaryLocation W42836535041 @default.

• next