Matches in SemOpenAlex for { <https://semopenalex.org/work/W2215831833> ?p ?o ?g. }
Showing items 1 to 89 of
89
with 100 items per page.
- W2215831833 abstract "Training a structured prediction model involves performing several loss-augmented inference steps. Over the lifetime of the training, many of these inference problems, although different, share the same solution. We propose AI-DCD, an Amortized Inference framework for Dual Coordinate Descent method, an approximate learning algorithm, that accelerates the training process by exploiting this redundancy of solutions, without compromising the performance of the model. We show the efficacy of our method by training a structured SVM using dual coordinate descent for an entityrelation extraction task. Our method learns the same model as an exact training algorithm would, but call the inference engine only in 10% – 24% of the inference problems encountered during training. We observe similar gains on a multi-label classification task and with a Structured Perceptron model for the entity-relation task." @default.
- W2215831833 created "2016-06-24" @default.
- W2215831833 creator A5023802054 @default.
- W2215831833 creator A5056769987 @default.
- W2215831833 creator A5087096372 @default.
- W2215831833 creator A5090034944 @default.
- W2215831833 date "2015-02-21" @default.
- W2215831833 modified "2023-09-23" @default.
- W2215831833 title "Structural Learning with Amortized Inference" @default.
- W2215831833 cites W1489483588 @default.
- W2215831833 cites W1566346388 @default.
- W2215831833 cites W162171320 @default.
- W2215831833 cites W2008652694 @default.
- W2215831833 cites W2031248101 @default.
- W2215831833 cites W2092423930 @default.
- W2215831833 cites W2097707447 @default.
- W2215831833 cites W2103853614 @default.
- W2215831833 cites W2105644991 @default.
- W2215831833 cites W2105842272 @default.
- W2215831833 cites W2111161343 @default.
- W2215831833 cites W2117822433 @default.
- W2215831833 cites W2120386375 @default.
- W2215831833 cites W2141466631 @default.
- W2215831833 cites W2159992248 @default.
- W2215831833 cites W2161653775 @default.
- W2215831833 cites W2165966284 @default.
- W2215831833 cites W2407980920 @default.
- W2215831833 cites W2465041517 @default.
- W2215831833 cites W2569568557 @default.
- W2215831833 cites W2964262905 @default.
- W2215831833 cites W81081615 @default.
- W2215831833 cites W94363386 @default.
- W2215831833 doi "https://doi.org/10.1609/aaai.v29i1.9535" @default.
- W2215831833 hasPublicationYear "2015" @default.
- W2215831833 type Work @default.
- W2215831833 sameAs 2215831833 @default.
- W2215831833 citedByCount "5" @default.
- W2215831833 countsByYear W22158318332015 @default.
- W2215831833 countsByYear W22158318332017 @default.
- W2215831833 countsByYear W22158318332018 @default.
- W2215831833 countsByYear W22158318332020 @default.
- W2215831833 countsByYear W22158318332021 @default.
- W2215831833 crossrefType "journal-article" @default.
- W2215831833 hasAuthorship W2215831833A5023802054 @default.
- W2215831833 hasAuthorship W2215831833A5056769987 @default.
- W2215831833 hasAuthorship W2215831833A5087096372 @default.
- W2215831833 hasAuthorship W2215831833A5090034944 @default.
- W2215831833 hasBestOaLocation W22158318331 @default.
- W2215831833 hasConcept C111919701 @default.
- W2215831833 hasConcept C119857082 @default.
- W2215831833 hasConcept C152124472 @default.
- W2215831833 hasConcept C154945302 @default.
- W2215831833 hasConcept C157553263 @default.
- W2215831833 hasConcept C162324750 @default.
- W2215831833 hasConcept C187736073 @default.
- W2215831833 hasConcept C22367795 @default.
- W2215831833 hasConcept C2776214188 @default.
- W2215831833 hasConcept C2780451532 @default.
- W2215831833 hasConcept C41008148 @default.
- W2215831833 hasConceptScore W2215831833C111919701 @default.
- W2215831833 hasConceptScore W2215831833C119857082 @default.
- W2215831833 hasConceptScore W2215831833C152124472 @default.
- W2215831833 hasConceptScore W2215831833C154945302 @default.
- W2215831833 hasConceptScore W2215831833C157553263 @default.
- W2215831833 hasConceptScore W2215831833C162324750 @default.
- W2215831833 hasConceptScore W2215831833C187736073 @default.
- W2215831833 hasConceptScore W2215831833C22367795 @default.
- W2215831833 hasConceptScore W2215831833C2776214188 @default.
- W2215831833 hasConceptScore W2215831833C2780451532 @default.
- W2215831833 hasConceptScore W2215831833C41008148 @default.
- W2215831833 hasIssue "1" @default.
- W2215831833 hasLocation W22158318331 @default.
- W2215831833 hasOpenAccess W2215831833 @default.
- W2215831833 hasPrimaryLocation W22158318331 @default.
- W2215831833 hasRelatedWork W2081647779 @default.
- W2215831833 hasRelatedWork W2215831833 @default.
- W2215831833 hasRelatedWork W2961085424 @default.
- W2215831833 hasRelatedWork W3046775127 @default.
- W2215831833 hasRelatedWork W3170094116 @default.
- W2215831833 hasRelatedWork W4285260836 @default.
- W2215831833 hasRelatedWork W4286629047 @default.
- W2215831833 hasRelatedWork W4306321456 @default.
- W2215831833 hasRelatedWork W4306674287 @default.
- W2215831833 hasRelatedWork W4224009465 @default.
- W2215831833 hasVolume "29" @default.
- W2215831833 isParatext "false" @default.
- W2215831833 isRetracted "false" @default.
- W2215831833 magId "2215831833" @default.
- W2215831833 workType "article" @default.