Matches in SemOpenAlex for { <https://semopenalex.org/work/W2964052395> ?p ?o ?g. }
- W2964052395 endingPage "2577" @default.
- W2964052395 startingPage "2568" @default.
- W2964052395 abstract "Black box variational inference allows researchers to easily prototype and evaluate an array of models. Recent advances allow such algorithms to scale to high dimensions. However, a central question remains: How to specify an expressive variational distribution that maintains efficient computation? To address this, we develop hierarchical variational models (HVMs). HVMs augment a variational approximation with a prior on its parameters, which allows it to capture complex structure for both discrete and continuous latent variables. The algorithm we develop is black box, can be used for any HVM, and has the same computational efficiency as the original approximation. We study HVMs on a variety of deep discrete latent variable models. HVMs generalize other expressive variational distributions and maintains higher fidelity to the posterior." @default.
- W2964052395 created "2019-07-30" @default.
- W2964052395 creator A5022202456 @default.
- W2964052395 creator A5070920982 @default.
- W2964052395 creator A5081819708 @default.
- W2964052395 date "2016-06-19" @default.
- W2964052395 modified "2023-09-27" @default.
- W2964052395 title "Hierarchical variational models" @default.
- W2964052395 cites W105785986 @default.
- W2964052395 cites W1483024020 @default.
- W2964052395 cites W1501567504 @default.
- W2964052395 cites W1506806321 @default.
- W2964052395 cites W1510659740 @default.
- W2964052395 cites W1515272691 @default.
- W2964052395 cites W1516111018 @default.
- W2964052395 cites W1554348720 @default.
- W2964052395 cites W1590505064 @default.
- W2964052395 cites W1663973292 @default.
- W2964052395 cites W1746680969 @default.
- W2964052395 cites W1795258949 @default.
- W2964052395 cites W1906598733 @default.
- W2964052395 cites W1909320841 @default.
- W2964052395 cites W1959608418 @default.
- W2964052395 cites W1981457167 @default.
- W2964052395 cites W1994616650 @default.
- W2964052395 cites W2049633694 @default.
- W2964052395 cites W2079819958 @default.
- W2964052395 cites W2098084154 @default.
- W2964052395 cites W2098694378 @default.
- W2964052395 cites W2099111195 @default.
- W2964052395 cites W2104163628 @default.
- W2964052395 cites W2115870554 @default.
- W2964052395 cites W2119717200 @default.
- W2964052395 cites W2120340025 @default.
- W2964052395 cites W2120633557 @default.
- W2964052395 cites W2122262818 @default.
- W2964052395 cites W2144100511 @default.
- W2964052395 cites W2150807068 @default.
- W2964052395 cites W2161335636 @default.
- W2964052395 cites W2164613257 @default.
- W2964052395 cites W2166851633 @default.
- W2964052395 cites W2187669537 @default.
- W2964052395 cites W2280377497 @default.
- W2964052395 cites W2296242069 @default.
- W2964052395 cites W2510002191 @default.
- W2964052395 cites W2539792571 @default.
- W2964052395 cites W2962994101 @default.
- W2964052395 cites W2963090522 @default.
- W2964052395 cites W2963173382 @default.
- W2964052395 cites W2963811225 @default.
- W2964052395 cites W2963910604 @default.
- W2964052395 cites W2979719808 @default.
- W2964052395 cites W3104819538 @default.
- W2964052395 cites W3127711384 @default.
- W2964052395 cites W3128954882 @default.
- W2964052395 cites W634934296 @default.
- W2964052395 hasPublicationYear "2016" @default.
- W2964052395 type Work @default.
- W2964052395 sameAs 2964052395 @default.
- W2964052395 citedByCount "151" @default.
- W2964052395 countsByYear W29640523952015 @default.
- W2964052395 countsByYear W29640523952016 @default.
- W2964052395 countsByYear W29640523952017 @default.
- W2964052395 countsByYear W29640523952018 @default.
- W2964052395 countsByYear W29640523952019 @default.
- W2964052395 countsByYear W29640523952020 @default.
- W2964052395 countsByYear W29640523952021 @default.
- W2964052395 crossrefType "proceedings-article" @default.
- W2964052395 hasAuthorship W2964052395A5022202456 @default.
- W2964052395 hasAuthorship W2964052395A5070920982 @default.
- W2964052395 hasAuthorship W2964052395A5081819708 @default.
- W2964052395 hasConcept C113364801 @default.
- W2964052395 hasConcept C11413529 @default.
- W2964052395 hasConcept C119599485 @default.
- W2964052395 hasConcept C126255220 @default.
- W2964052395 hasConcept C127413603 @default.
- W2964052395 hasConcept C134306372 @default.
- W2964052395 hasConcept C136197465 @default.
- W2964052395 hasConcept C154945302 @default.
- W2964052395 hasConcept C182365436 @default.
- W2964052395 hasConcept C2776214188 @default.
- W2964052395 hasConcept C2776459999 @default.
- W2964052395 hasConcept C28826006 @default.
- W2964052395 hasConcept C33923547 @default.
- W2964052395 hasConcept C41008148 @default.
- W2964052395 hasConcept C45374587 @default.
- W2964052395 hasConcept C51167844 @default.
- W2964052395 hasConcept C76155785 @default.
- W2964052395 hasConcept C80444323 @default.
- W2964052395 hasConcept C94966114 @default.
- W2964052395 hasConceptScore W2964052395C113364801 @default.
- W2964052395 hasConceptScore W2964052395C11413529 @default.
- W2964052395 hasConceptScore W2964052395C119599485 @default.
- W2964052395 hasConceptScore W2964052395C126255220 @default.
- W2964052395 hasConceptScore W2964052395C127413603 @default.
- W2964052395 hasConceptScore W2964052395C134306372 @default.
- W2964052395 hasConceptScore W2964052395C136197465 @default.
- W2964052395 hasConceptScore W2964052395C154945302 @default.