Matches in SemOpenAlex for { <https://semopenalex.org/work/W2158348507> ?p ?o ?g. }
- W2158348507 endingPage "1953" @default.
- W2158348507 startingPage "1937" @default.
- W2158348507 abstract "Support vector machines are a powerful machine learning technology, but the training process involves a dense quadratic optimization problem and is computationally challenging. A parallel implementation of linear Support Vector Machine training has been developed, using a combination of MPI and OpenMP. Using an interior point method for the optimization and a reformulation that avoids the dense Hessian matrix, the structure of the augmented system matrix is exploited to partition data and computations amongst parallel processors efficiently. The new implementation has been applied to solve problems from the PASCAL Challenge on Large-scale Learning. We show that our approach is competitive, and is able to solve problems in the Challenge many times faster than other parallel approaches. We also demonstrate that the hybrid version performs more efficiently than the version using pure MPI." @default.
- W2158348507 created "2016-06-24" @default.
- W2158348507 creator A5022942802 @default.
- W2158348507 creator A5033855320 @default.
- W2158348507 date "2009-12-01" @default.
- W2158348507 modified "2023-09-26" @default.
- W2158348507 title "Hybrid MPI/OpenMP Parallel Linear Support Vector Machine Training" @default.
- W2158348507 cites W1503126987 @default.
- W2158348507 cites W1512098439 @default.
- W2158348507 cites W1518039036 @default.
- W2158348507 cites W1575350781 @default.
- W2158348507 cites W1761010383 @default.
- W2158348507 cites W1963882433 @default.
- W2158348507 cites W2009593947 @default.
- W2158348507 cites W2014261141 @default.
- W2158348507 cites W2016990965 @default.
- W2158348507 cites W2065614041 @default.
- W2158348507 cites W2065887373 @default.
- W2158348507 cites W2069231281 @default.
- W2158348507 cites W2073061372 @default.
- W2158348507 cites W2079658918 @default.
- W2158348507 cites W2099262739 @default.
- W2158348507 cites W2117990954 @default.
- W2158348507 cites W2118585731 @default.
- W2158348507 cites W2124480634 @default.
- W2158348507 cites W2125126592 @default.
- W2158348507 cites W2137557016 @default.
- W2158348507 cites W2148603752 @default.
- W2158348507 cites W2150062669 @default.
- W2158348507 cites W2150773524 @default.
- W2158348507 cites W2161713006 @default.
- W2158348507 cites W2541981042 @default.
- W2158348507 cites W594409146 @default.
- W2158348507 cites W70659124 @default.
- W2158348507 doi "https://doi.org/10.1103/10.1145/1577069.1755850" @default.
- W2158348507 hasPublicationYear "2009" @default.
- W2158348507 type Work @default.
- W2158348507 sameAs 2158348507 @default.
- W2158348507 citedByCount "14" @default.
- W2158348507 countsByYear W21583485072013 @default.
- W2158348507 countsByYear W21583485072014 @default.
- W2158348507 countsByYear W21583485072015 @default.
- W2158348507 countsByYear W21583485072016 @default.
- W2158348507 countsByYear W21583485072017 @default.
- W2158348507 countsByYear W21583485072018 @default.
- W2158348507 countsByYear W21583485072019 @default.
- W2158348507 countsByYear W21583485072020 @default.
- W2158348507 crossrefType "journal-article" @default.
- W2158348507 hasAuthorship W2158348507A5022942802 @default.
- W2158348507 hasAuthorship W2158348507A5033855320 @default.
- W2158348507 hasConcept C11413529 @default.
- W2158348507 hasConcept C114614502 @default.
- W2158348507 hasConcept C12267149 @default.
- W2158348507 hasConcept C154945302 @default.
- W2158348507 hasConcept C173608175 @default.
- W2158348507 hasConcept C199360897 @default.
- W2158348507 hasConcept C203616005 @default.
- W2158348507 hasConcept C28826006 @default.
- W2158348507 hasConcept C33923547 @default.
- W2158348507 hasConcept C41008148 @default.
- W2158348507 hasConcept C42812 @default.
- W2158348507 hasConcept C45374587 @default.
- W2158348507 hasConcept C75608658 @default.
- W2158348507 hasConceptScore W2158348507C11413529 @default.
- W2158348507 hasConceptScore W2158348507C114614502 @default.
- W2158348507 hasConceptScore W2158348507C12267149 @default.
- W2158348507 hasConceptScore W2158348507C154945302 @default.
- W2158348507 hasConceptScore W2158348507C173608175 @default.
- W2158348507 hasConceptScore W2158348507C199360897 @default.
- W2158348507 hasConceptScore W2158348507C203616005 @default.
- W2158348507 hasConceptScore W2158348507C28826006 @default.
- W2158348507 hasConceptScore W2158348507C33923547 @default.
- W2158348507 hasConceptScore W2158348507C41008148 @default.
- W2158348507 hasConceptScore W2158348507C42812 @default.
- W2158348507 hasConceptScore W2158348507C45374587 @default.
- W2158348507 hasConceptScore W2158348507C75608658 @default.
- W2158348507 hasIssue "67" @default.
- W2158348507 hasLocation W21583485071 @default.
- W2158348507 hasOpenAccess W2158348507 @default.
- W2158348507 hasPrimaryLocation W21583485071 @default.
- W2158348507 hasRelatedWork W1512098439 @default.
- W2158348507 hasRelatedWork W1560724230 @default.
- W2158348507 hasRelatedWork W1563088657 @default.
- W2158348507 hasRelatedWork W1574862351 @default.
- W2158348507 hasRelatedWork W1761010383 @default.
- W2158348507 hasRelatedWork W2065887373 @default.
- W2158348507 hasRelatedWork W2099262739 @default.
- W2158348507 hasRelatedWork W2109722477 @default.
- W2158348507 hasRelatedWork W2116173306 @default.
- W2158348507 hasRelatedWork W2117990954 @default.
- W2158348507 hasRelatedWork W2118585731 @default.
- W2158348507 hasRelatedWork W2119821739 @default.
- W2158348507 hasRelatedWork W2148603752 @default.
- W2158348507 hasRelatedWork W2153635508 @default.
- W2158348507 hasRelatedWork W2156909104 @default.
- W2158348507 hasRelatedWork W2159350554 @default.
- W2158348507 hasRelatedWork W2161713006 @default.
- W2158348507 hasRelatedWork W2165966284 @default.