FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W2561509423> ?p ?o ?g. }

• W2561509423 abstract "This paper presents two strategies to speed up the alternating direction method of multipliers (ADMM) for distributed data. In the first method, inspired by stochastic gradient descent, each machine uses only a subset of its data at the first few iterations, speeding up those iterations. A key result is in proving that despite this approximation, our method enjoys the same convergence rate in terms of the number of iterations as the standard ADMM, and hence is faster overall. The second method also follows the idea of sampling a subset of the data to update the model before the communication of each round. It converts an objective to the approximated dual form and performs ADMM on the dual. The method turns out to be a distributed variant of the recently proposed SDCA-ADMM. Yet, compared to the straightforward distributed implementation of SDCA-ADMM, the proposed method enjoys less frequent communication between machines, better memory usage, and lighter computational demand. Experiments demonstrate the effectiveness of our two strategies." @default.
• W2561509423 created "2017-01-06" @default.
• W2561509423 creator A5031186428 @default.
• W2561509423 creator A5087480257 @default.
• W2561509423 date "2016-10-01" @default.
• W2561509423 modified "2023-09-22" @default.
• W2561509423 title "Efficient Sampling-Based ADMM for Distributed Data" @default.
• W2561509423 cites W114517082 @default.
• W2561509423 cites W130696423 @default.
• W2561509423 cites W1890144115 @default.
• W2561509423 cites W1939652453 @default.
• W2561509423 cites W1970554427 @default.
• W2561509423 cites W1986080131 @default.
• W2561509423 cites W2031342017 @default.
• W2561509423 cites W2061570747 @default.
• W2561509423 cites W2096199223 @default.
• W2561509423 cites W2106955134 @default.
• W2561509423 cites W2123154536 @default.
• W2561509423 cites W2153635508 @default.
• W2561509423 cites W2156118598 @default.
• W2561509423 cites W2157462866 @default.
• W2561509423 cites W2164278908 @default.
• W2561509423 cites W2165966284 @default.
• W2561509423 cites W2166706236 @default.
• W2561509423 cites W2510516734 @default.
• W2561509423 cites W25321933 @default.
• W2561509423 cites W2556913586 @default.
• W2561509423 cites W2884132298 @default.
• W2561509423 cites W2950978476 @default.
• W2561509423 cites W2964064266 @default.
• W2561509423 cites W3029645440 @default.
• W2561509423 cites W3103657382 @default.
• W2561509423 cites W38875623 @default.
• W2561509423 doi "https://doi.org/10.1109/dsaa.2016.41" @default.
• W2561509423 hasPublicationYear "2016" @default.
• W2561509423 type Work @default.
• W2561509423 sameAs 2561509423 @default.
• W2561509423 citedByCount "0" @default.
• W2561509423 crossrefType "proceedings-article" @default.
• W2561509423 hasAuthorship W2561509423A5031186428 @default.
• W2561509423 hasAuthorship W2561509423A5087480257 @default.
• W2561509423 hasConcept C106131492 @default.
• W2561509423 hasConcept C11413529 @default.
• W2561509423 hasConcept C120314980 @default.
• W2561509423 hasConcept C124952713 @default.
• W2561509423 hasConcept C126255220 @default.
• W2561509423 hasConcept C130120984 @default.
• W2561509423 hasConcept C140779682 @default.
• W2561509423 hasConcept C142362112 @default.
• W2561509423 hasConcept C154945302 @default.
• W2561509423 hasConcept C162324750 @default.
• W2561509423 hasConcept C173608175 @default.
• W2561509423 hasConcept C206688291 @default.
• W2561509423 hasConcept C26517878 @default.
• W2561509423 hasConcept C2777303404 @default.
• W2561509423 hasConcept C2780980858 @default.
• W2561509423 hasConcept C31972630 @default.
• W2561509423 hasConcept C33923547 @default.
• W2561509423 hasConcept C38652104 @default.
• W2561509423 hasConcept C41008148 @default.
• W2561509423 hasConcept C50522688 @default.
• W2561509423 hasConcept C50644808 @default.
• W2561509423 hasConcept C57869625 @default.
• W2561509423 hasConcept C68339613 @default.
• W2561509423 hasConceptScore W2561509423C106131492 @default.
• W2561509423 hasConceptScore W2561509423C11413529 @default.
• W2561509423 hasConceptScore W2561509423C120314980 @default.
• W2561509423 hasConceptScore W2561509423C124952713 @default.
• W2561509423 hasConceptScore W2561509423C126255220 @default.
• W2561509423 hasConceptScore W2561509423C130120984 @default.
• W2561509423 hasConceptScore W2561509423C140779682 @default.
• W2561509423 hasConceptScore W2561509423C142362112 @default.
• W2561509423 hasConceptScore W2561509423C154945302 @default.
• W2561509423 hasConceptScore W2561509423C162324750 @default.
• W2561509423 hasConceptScore W2561509423C173608175 @default.
• W2561509423 hasConceptScore W2561509423C206688291 @default.
• W2561509423 hasConceptScore W2561509423C26517878 @default.
• W2561509423 hasConceptScore W2561509423C2777303404 @default.
• W2561509423 hasConceptScore W2561509423C2780980858 @default.
• W2561509423 hasConceptScore W2561509423C31972630 @default.
• W2561509423 hasConceptScore W2561509423C33923547 @default.
• W2561509423 hasConceptScore W2561509423C38652104 @default.
• W2561509423 hasConceptScore W2561509423C41008148 @default.
• W2561509423 hasConceptScore W2561509423C50522688 @default.
• W2561509423 hasConceptScore W2561509423C50644808 @default.
• W2561509423 hasConceptScore W2561509423C57869625 @default.
• W2561509423 hasConceptScore W2561509423C68339613 @default.
• W2561509423 hasLocation W25615094231 @default.
• W2561509423 hasOpenAccess W2561509423 @default.
• W2561509423 hasPrimaryLocation W25615094231 @default.
• W2561509423 hasRelatedWork W1522126829 @default.
• W2561509423 hasRelatedWork W1570678512 @default.
• W2561509423 hasRelatedWork W2464600283 @default.
• W2561509423 hasRelatedWork W2624188997 @default.
• W2561509423 hasRelatedWork W2794008625 @default.
• W2561509423 hasRelatedWork W2910462660 @default.
• W2561509423 hasRelatedWork W2955365367 @default.
• W2561509423 hasRelatedWork W2957603202 @default.
• W2561509423 hasRelatedWork W2964026016 @default.
• W2561509423 hasRelatedWork W2980701846 @default.

• next