Matches in SemOpenAlex for { <https://semopenalex.org/work/W2090078891> ?p ?o ?g. }
Showing items 1 to 92 of
92
with 100 items per page.
- W2090078891 endingPage "960" @default.
- W2090078891 startingPage "952" @default.
- W2090078891 abstract "Latent Dirichlet allocation (LDA) is a popular algorithm for discovering semantic structure in large collections of text or other data. Although its complexity is linear in the data size, its use on increasingly massive collections has created considerable interest in parallel implementations. “Approximate distributed” LDA, or AD-LDA, approximates the popular collapsed Gibbs sampling algorithm for LDA models while running on a distributed architecture. Although this algorithm often appears to perform well in practice, its quality is not well understood theoretically or easily assessed on new data. In this work, we theoretically justify the approximation, and modify AD-LDA to track an error bound on performance. Specifically, we upper bound the probability of making a sampling error at each step of the algorithm (compared to an exact, sequential Gibbs sampler), given the samples drawn thus far. We show empirically that our bound is sufficiently tight to give a meaningful and intuitive measure of approximation error in AD-LDA, allowing the user to track the tradeoff between accuracy and efficiency while executing in parallel." @default.
- W2090078891 created "2016-06-24" @default.
- W2090078891 creator A5048047705 @default.
- W2090078891 creator A5088727983 @default.
- W2090078891 date "2012-05-01" @default.
- W2090078891 modified "2023-09-23" @default.
- W2090078891 title "Understanding Errors in Approximate Distributed Latent Dirichlet Allocation" @default.
- W2090078891 cites W2001082470 @default.
- W2090078891 cites W2082042541 @default.
- W2090078891 cites W2103658758 @default.
- W2090078891 cites W2118034653 @default.
- W2090078891 cites W2154594550 @default.
- W2090078891 cites W3099640513 @default.
- W2090078891 cites W4205818646 @default.
- W2090078891 cites W4237791300 @default.
- W2090078891 doi "https://doi.org/10.1109/tkde.2011.29" @default.
- W2090078891 hasPublicationYear "2012" @default.
- W2090078891 type Work @default.
- W2090078891 sameAs 2090078891 @default.
- W2090078891 citedByCount "20" @default.
- W2090078891 countsByYear W20900788912013 @default.
- W2090078891 countsByYear W20900788912014 @default.
- W2090078891 countsByYear W20900788912015 @default.
- W2090078891 countsByYear W20900788912016 @default.
- W2090078891 countsByYear W20900788912017 @default.
- W2090078891 countsByYear W20900788912018 @default.
- W2090078891 countsByYear W20900788912019 @default.
- W2090078891 crossrefType "journal-article" @default.
- W2090078891 hasAuthorship W2090078891A5048047705 @default.
- W2090078891 hasAuthorship W2090078891A5088727983 @default.
- W2090078891 hasBestOaLocation W20900788912 @default.
- W2090078891 hasConcept C106131492 @default.
- W2090078891 hasConcept C107673813 @default.
- W2090078891 hasConcept C11413529 @default.
- W2090078891 hasConcept C122383733 @default.
- W2090078891 hasConcept C124101348 @default.
- W2090078891 hasConcept C134306372 @default.
- W2090078891 hasConcept C140779682 @default.
- W2090078891 hasConcept C148764684 @default.
- W2090078891 hasConcept C154945302 @default.
- W2090078891 hasConcept C158424031 @default.
- W2090078891 hasConcept C169214877 @default.
- W2090078891 hasConcept C171686336 @default.
- W2090078891 hasConcept C182310444 @default.
- W2090078891 hasConcept C31972630 @default.
- W2090078891 hasConcept C33923547 @default.
- W2090078891 hasConcept C41008148 @default.
- W2090078891 hasConcept C500882744 @default.
- W2090078891 hasConcept C77553402 @default.
- W2090078891 hasConcept C80444323 @default.
- W2090078891 hasConceptScore W2090078891C106131492 @default.
- W2090078891 hasConceptScore W2090078891C107673813 @default.
- W2090078891 hasConceptScore W2090078891C11413529 @default.
- W2090078891 hasConceptScore W2090078891C122383733 @default.
- W2090078891 hasConceptScore W2090078891C124101348 @default.
- W2090078891 hasConceptScore W2090078891C134306372 @default.
- W2090078891 hasConceptScore W2090078891C140779682 @default.
- W2090078891 hasConceptScore W2090078891C148764684 @default.
- W2090078891 hasConceptScore W2090078891C154945302 @default.
- W2090078891 hasConceptScore W2090078891C158424031 @default.
- W2090078891 hasConceptScore W2090078891C169214877 @default.
- W2090078891 hasConceptScore W2090078891C171686336 @default.
- W2090078891 hasConceptScore W2090078891C182310444 @default.
- W2090078891 hasConceptScore W2090078891C31972630 @default.
- W2090078891 hasConceptScore W2090078891C33923547 @default.
- W2090078891 hasConceptScore W2090078891C41008148 @default.
- W2090078891 hasConceptScore W2090078891C500882744 @default.
- W2090078891 hasConceptScore W2090078891C77553402 @default.
- W2090078891 hasConceptScore W2090078891C80444323 @default.
- W2090078891 hasIssue "5" @default.
- W2090078891 hasLocation W20900788911 @default.
- W2090078891 hasLocation W20900788912 @default.
- W2090078891 hasLocation W20900788913 @default.
- W2090078891 hasOpenAccess W2090078891 @default.
- W2090078891 hasPrimaryLocation W20900788911 @default.
- W2090078891 hasRelatedWork W2001994797 @default.
- W2090078891 hasRelatedWork W2018409826 @default.
- W2090078891 hasRelatedWork W2074708675 @default.
- W2090078891 hasRelatedWork W2158085718 @default.
- W2090078891 hasRelatedWork W2352674739 @default.
- W2090078891 hasRelatedWork W2375722203 @default.
- W2090078891 hasRelatedWork W2791817765 @default.
- W2090078891 hasRelatedWork W2939843948 @default.
- W2090078891 hasRelatedWork W4294646186 @default.
- W2090078891 hasRelatedWork W4308574359 @default.
- W2090078891 hasVolume "24" @default.
- W2090078891 isParatext "false" @default.
- W2090078891 isRetracted "false" @default.
- W2090078891 magId "2090078891" @default.
- W2090078891 workType "article" @default.