Matches in SemOpenAlex for { <https://semopenalex.org/work/W3100400430> ?p ?o ?g. }
Showing items 1 to 88 of
88
with 100 items per page.
- W3100400430 endingPage "8681" @default.
- W3100400430 startingPage "8671" @default.
- W3100400430 abstract "Automated machine learning (AutoML) can produce complex model ensembles by stacking, bagging, and boosting many individual models like trees, deep networks, and nearest neighbor estimators. While highly accurate, the resulting predictors are large, slow, and opaque as compared to their constituents. To improve the deployment of AutoML on tabular data, we propose FAST-DAD to distill arbitrarily complex ensemble predictors into individual models like boosted trees, random forests, and deep networks. At the heart of our approach is a data augmentation strategy based on Gibbs sampling from a self-attention pseudolikelihood estimator. Across 30 datasets spanning regression and binary/multiclass classification tasks, FAST-DAD distillation produces significantly better individual models than one obtains through standard training on the original data. Our individual distilled models are over 10x faster and more accurate than ensemble predictors produced by AutoML tools like H2O/AutoSklearn." @default.
- W3100400430 created "2020-11-23" @default.
- W3100400430 creator A5000245150 @default.
- W3100400430 creator A5006038667 @default.
- W3100400430 creator A5010753342 @default.
- W3100400430 creator A5011601027 @default.
- W3100400430 creator A5074303284 @default.
- W3100400430 date "2020-06-25" @default.
- W3100400430 modified "2023-09-24" @default.
- W3100400430 title "Fast, Accurate, and Simple Models for Tabular Data via Augmented Distillation" @default.
- W3100400430 hasPublicationYear "2020" @default.
- W3100400430 type Work @default.
- W3100400430 sameAs 3100400430 @default.
- W3100400430 citedByCount "8" @default.
- W3100400430 countsByYear W31004004302020 @default.
- W3100400430 countsByYear W31004004302021 @default.
- W3100400430 crossrefType "proceedings-article" @default.
- W3100400430 hasAuthorship W3100400430A5000245150 @default.
- W3100400430 hasAuthorship W3100400430A5006038667 @default.
- W3100400430 hasAuthorship W3100400430A5010753342 @default.
- W3100400430 hasAuthorship W3100400430A5011601027 @default.
- W3100400430 hasAuthorship W3100400430A5074303284 @default.
- W3100400430 hasConcept C105795698 @default.
- W3100400430 hasConcept C111472728 @default.
- W3100400430 hasConcept C119857082 @default.
- W3100400430 hasConcept C124101348 @default.
- W3100400430 hasConcept C138885662 @default.
- W3100400430 hasConcept C154945302 @default.
- W3100400430 hasConcept C169258074 @default.
- W3100400430 hasConcept C178790620 @default.
- W3100400430 hasConcept C185429906 @default.
- W3100400430 hasConcept C185592680 @default.
- W3100400430 hasConcept C204030448 @default.
- W3100400430 hasConcept C2780586882 @default.
- W3100400430 hasConcept C33923547 @default.
- W3100400430 hasConcept C41008148 @default.
- W3100400430 hasConcept C45942800 @default.
- W3100400430 hasConcept C46686674 @default.
- W3100400430 hasConcept C48372109 @default.
- W3100400430 hasConcept C94375191 @default.
- W3100400430 hasConceptScore W3100400430C105795698 @default.
- W3100400430 hasConceptScore W3100400430C111472728 @default.
- W3100400430 hasConceptScore W3100400430C119857082 @default.
- W3100400430 hasConceptScore W3100400430C124101348 @default.
- W3100400430 hasConceptScore W3100400430C138885662 @default.
- W3100400430 hasConceptScore W3100400430C154945302 @default.
- W3100400430 hasConceptScore W3100400430C169258074 @default.
- W3100400430 hasConceptScore W3100400430C178790620 @default.
- W3100400430 hasConceptScore W3100400430C185429906 @default.
- W3100400430 hasConceptScore W3100400430C185592680 @default.
- W3100400430 hasConceptScore W3100400430C204030448 @default.
- W3100400430 hasConceptScore W3100400430C2780586882 @default.
- W3100400430 hasConceptScore W3100400430C33923547 @default.
- W3100400430 hasConceptScore W3100400430C41008148 @default.
- W3100400430 hasConceptScore W3100400430C45942800 @default.
- W3100400430 hasConceptScore W3100400430C46686674 @default.
- W3100400430 hasConceptScore W3100400430C48372109 @default.
- W3100400430 hasConceptScore W3100400430C94375191 @default.
- W3100400430 hasLocation W31004004301 @default.
- W3100400430 hasOpenAccess W3100400430 @default.
- W3100400430 hasPrimaryLocation W31004004301 @default.
- W3100400430 hasRelatedWork W2027215713 @default.
- W3100400430 hasRelatedWork W2149033360 @default.
- W3100400430 hasRelatedWork W2293621828 @default.
- W3100400430 hasRelatedWork W2296225892 @default.
- W3100400430 hasRelatedWork W2738995938 @default.
- W3100400430 hasRelatedWork W2865062175 @default.
- W3100400430 hasRelatedWork W2884898416 @default.
- W3100400430 hasRelatedWork W2885062049 @default.
- W3100400430 hasRelatedWork W2903228170 @default.
- W3100400430 hasRelatedWork W2963999139 @default.
- W3100400430 hasRelatedWork W2979968696 @default.
- W3100400430 hasRelatedWork W2980096319 @default.
- W3100400430 hasRelatedWork W3011307848 @default.
- W3100400430 hasRelatedWork W3014048727 @default.
- W3100400430 hasRelatedWork W3037521097 @default.
- W3100400430 hasRelatedWork W3109288977 @default.
- W3100400430 hasRelatedWork W3136460210 @default.
- W3100400430 hasRelatedWork W3160759841 @default.
- W3100400430 hasRelatedWork W3199592422 @default.
- W3100400430 hasRelatedWork W3201098700 @default.
- W3100400430 hasVolume "33" @default.
- W3100400430 isParatext "false" @default.
- W3100400430 isRetracted "false" @default.
- W3100400430 magId "3100400430" @default.
- W3100400430 workType "article" @default.