Matches in SemOpenAlex for { <https://semopenalex.org/work/W2897082384> ?p ?o ?g. }
Showing items 1 to 86 of
86
with 100 items per page.
- W2897082384 endingPage "2750" @default.
- W2897082384 startingPage "2741" @default.
- W2897082384 abstract "Unnormalised latent variable models are a broad and flexible class of statistical models. However, learning their parameters from data is intractable, and few estimation techniques are currently available for such models. To increase the number of techniques in our arsenal, we propose variational noise-contrastive estimation (VNCE), building on NCE which is a method that only applies to unnormalised models. The core idea is to use a variational lower bound to the NCE objective function, which can be optimised in the same fashion as the evidence lower bound (ELBO) in standard variational inference (VI). We prove that VNCE can be used for both parameter estimation of unnormalised models and posterior inference of latent variables. The developed theory shows that VNCE has the same level of generality as standard VI, meaning that advances made there can be directly imported to the unnormalised setting. We validate VNCE on toy models and apply it to a realistic problem of estimating an undirected graphical model from incomplete data." @default.
- W2897082384 created "2018-10-26" @default.
- W2897082384 creator A5009207907 @default.
- W2897082384 creator A5038807284 @default.
- W2897082384 date "2019-04-11" @default.
- W2897082384 modified "2023-09-28" @default.
- W2897082384 title "Variational Noise-Contrastive Estimation" @default.
- W2897082384 hasPublicationYear "2019" @default.
- W2897082384 type Work @default.
- W2897082384 sameAs 2897082384 @default.
- W2897082384 citedByCount "6" @default.
- W2897082384 countsByYear W28970823842019 @default.
- W2897082384 countsByYear W28970823842020 @default.
- W2897082384 countsByYear W28970823842021 @default.
- W2897082384 crossrefType "proceedings-article" @default.
- W2897082384 hasAuthorship W2897082384A5009207907 @default.
- W2897082384 hasAuthorship W2897082384A5038807284 @default.
- W2897082384 hasConcept C11413529 @default.
- W2897082384 hasConcept C115961682 @default.
- W2897082384 hasConcept C126255220 @default.
- W2897082384 hasConcept C134306372 @default.
- W2897082384 hasConcept C14036430 @default.
- W2897082384 hasConcept C154945302 @default.
- W2897082384 hasConcept C155846161 @default.
- W2897082384 hasConcept C15744967 @default.
- W2897082384 hasConcept C167928553 @default.
- W2897082384 hasConcept C2776214188 @default.
- W2897082384 hasConcept C2780767217 @default.
- W2897082384 hasConcept C28826006 @default.
- W2897082384 hasConcept C33923547 @default.
- W2897082384 hasConcept C41008148 @default.
- W2897082384 hasConcept C51167844 @default.
- W2897082384 hasConcept C542102704 @default.
- W2897082384 hasConcept C77553402 @default.
- W2897082384 hasConcept C78458016 @default.
- W2897082384 hasConcept C86803240 @default.
- W2897082384 hasConcept C99498987 @default.
- W2897082384 hasConceptScore W2897082384C11413529 @default.
- W2897082384 hasConceptScore W2897082384C115961682 @default.
- W2897082384 hasConceptScore W2897082384C126255220 @default.
- W2897082384 hasConceptScore W2897082384C134306372 @default.
- W2897082384 hasConceptScore W2897082384C14036430 @default.
- W2897082384 hasConceptScore W2897082384C154945302 @default.
- W2897082384 hasConceptScore W2897082384C155846161 @default.
- W2897082384 hasConceptScore W2897082384C15744967 @default.
- W2897082384 hasConceptScore W2897082384C167928553 @default.
- W2897082384 hasConceptScore W2897082384C2776214188 @default.
- W2897082384 hasConceptScore W2897082384C2780767217 @default.
- W2897082384 hasConceptScore W2897082384C28826006 @default.
- W2897082384 hasConceptScore W2897082384C33923547 @default.
- W2897082384 hasConceptScore W2897082384C41008148 @default.
- W2897082384 hasConceptScore W2897082384C51167844 @default.
- W2897082384 hasConceptScore W2897082384C542102704 @default.
- W2897082384 hasConceptScore W2897082384C77553402 @default.
- W2897082384 hasConceptScore W2897082384C78458016 @default.
- W2897082384 hasConceptScore W2897082384C86803240 @default.
- W2897082384 hasConceptScore W2897082384C99498987 @default.
- W2897082384 hasLocation W28970823841 @default.
- W2897082384 hasOpenAccess W2897082384 @default.
- W2897082384 hasPrimaryLocation W28970823841 @default.
- W2897082384 hasRelatedWork W1481229783 @default.
- W2897082384 hasRelatedWork W2115979064 @default.
- W2897082384 hasRelatedWork W2121693152 @default.
- W2897082384 hasRelatedWork W2183391071 @default.
- W2897082384 hasRelatedWork W2271522117 @default.
- W2897082384 hasRelatedWork W2554637102 @default.
- W2897082384 hasRelatedWork W2555699918 @default.
- W2897082384 hasRelatedWork W2728803307 @default.
- W2897082384 hasRelatedWork W2801896452 @default.
- W2897082384 hasRelatedWork W2952054959 @default.
- W2897082384 hasRelatedWork W2959716150 @default.
- W2897082384 hasRelatedWork W2989574682 @default.
- W2897082384 hasRelatedWork W2996782460 @default.
- W2897082384 hasRelatedWork W3037733149 @default.
- W2897082384 hasRelatedWork W3097459875 @default.
- W2897082384 hasRelatedWork W3111366808 @default.
- W2897082384 hasRelatedWork W3133733630 @default.
- W2897082384 hasRelatedWork W3184738396 @default.
- W2897082384 hasRelatedWork W3194839898 @default.
- W2897082384 hasRelatedWork W3205586694 @default.
- W2897082384 isParatext "false" @default.
- W2897082384 isRetracted "false" @default.
- W2897082384 magId "2897082384" @default.
- W2897082384 workType "article" @default.