FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W2939297204> ?p ?o ?g. }

• W2939297204 abstract "Normalising flows (NFS) map two density functions via a differentiable bijection whose Jacobian determinant can be computed efficiently. Recently, as an alternative to hand-crafted bijections, Huang et al. (2018) proposed neural autoregressive flow (NAF) which is a universal approximator for density functions. Their flow is a neural network (NN) whose parameters are predicted by another NN. The latter grows quadratically with the size of the former and thus an efficient technique for parametrization is needed. We propose block neural autoregressive flow (B-NAF), a much more compact universal approximator of density functions, where we model a bijection directly using a single feed-forward network. Invertibility is ensured by carefully designing each affine transformation with block matrices that make the flow autoregressive and (strictly) monotone. We compare B-NAF to NAF and other established flows on density estimation and approximate inference for latent variable models. Our proposed flow is competitive across datasets while using orders of magnitude fewer parameters." @default.
• W2939297204 created "2019-04-25" @default.
• W2939297204 creator A5074142241 @default.
• W2939297204 creator A5075219217 @default.
• W2939297204 creator A5086717154 @default.
• W2939297204 date "2019-04-09" @default.
• W2939297204 modified "2023-10-03" @default.
• W2939297204 title "Block Neural Autoregressive Flow." @default.
• W2939297204 cites W1494871301 @default.
• W2939297204 cites W1516111018 @default.
• W2939297204 cites W1533861849 @default.
• W2939297204 cites W1583912456 @default.
• W2939297204 cites W1866230956 @default.
• W2939297204 cites W1959608418 @default.
• W2939297204 cites W2012762214 @default.
• W2939297204 cites W2070792261 @default.
• W2939297204 cites W2086161653 @default.
• W2939297204 cites W2121927366 @default.
• W2939297204 cites W2125406789 @default.
• W2939297204 cites W2135181320 @default.
• W2939297204 cites W2171282218 @default.
• W2939297204 cites W2194321275 @default.
• W2939297204 cites W2587284713 @default.
• W2939297204 cites W2770265749 @default.
• W2939297204 cites W2898631838 @default.
• W2939297204 cites W2949847548 @default.
• W2939297204 cites W2962695743 @default.
• W2939297204 cites W2963047245 @default.
• W2939297204 cites W2963090522 @default.
• W2939297204 cites W2963139417 @default.
• W2939297204 cites W2963170102 @default.
• W2939297204 cites W2963641970 @default.
• W2939297204 cites W2963685250 @default.
• W2939297204 cites W2963755523 @default.
• W2939297204 cites W2964121744 @default.
• W2939297204 cites W2964315715 @default.
• W2939297204 cites W2964343746 @default.
• W2939297204 cites W3120740533 @default.
• W2939297204 hasPublicationYear "2019" @default.
• W2939297204 type Work @default.
• W2939297204 sameAs 2939297204 @default.
• W2939297204 citedByCount "21" @default.
• W2939297204 countsByYear W29392972042019 @default.
• W2939297204 countsByYear W29392972042020 @default.
• W2939297204 countsByYear W29392972042021 @default.
• W2939297204 countsByYear W29392972042023 @default.
• W2939297204 crossrefType "posted-content" @default.
• W2939297204 hasAuthorship W2939297204A5074142241 @default.
• W2939297204 hasAuthorship W2939297204A5075219217 @default.
• W2939297204 hasAuthorship W2939297204A5086717154 @default.
• W2939297204 hasConcept C105795698 @default.
• W2939297204 hasConcept C114614502 @default.
• W2939297204 hasConcept C118615104 @default.
• W2939297204 hasConcept C121332964 @default.
• W2939297204 hasConcept C134306372 @default.
• W2939297204 hasConcept C154945302 @default.
• W2939297204 hasConcept C159877910 @default.
• W2939297204 hasConcept C177148314 @default.
• W2939297204 hasConcept C185429906 @default.
• W2939297204 hasConcept C189508267 @default.
• W2939297204 hasConcept C200331156 @default.
• W2939297204 hasConcept C202444582 @default.
• W2939297204 hasConcept C202887219 @default.
• W2939297204 hasConcept C24424167 @default.
• W2939297204 hasConcept C2524010 @default.
• W2939297204 hasConcept C2777210771 @default.
• W2939297204 hasConcept C28826006 @default.
• W2939297204 hasConcept C33923547 @default.
• W2939297204 hasConcept C38349280 @default.
• W2939297204 hasConcept C41008148 @default.
• W2939297204 hasConcept C50644808 @default.
• W2939297204 hasConcept C62520636 @default.
• W2939297204 hasConcept C74902906 @default.
• W2939297204 hasConcept C92757383 @default.
• W2939297204 hasConceptScore W2939297204C105795698 @default.
• W2939297204 hasConceptScore W2939297204C114614502 @default.
• W2939297204 hasConceptScore W2939297204C118615104 @default.
• W2939297204 hasConceptScore W2939297204C121332964 @default.
• W2939297204 hasConceptScore W2939297204C134306372 @default.
• W2939297204 hasConceptScore W2939297204C154945302 @default.
• W2939297204 hasConceptScore W2939297204C159877910 @default.
• W2939297204 hasConceptScore W2939297204C177148314 @default.
• W2939297204 hasConceptScore W2939297204C185429906 @default.
• W2939297204 hasConceptScore W2939297204C189508267 @default.
• W2939297204 hasConceptScore W2939297204C200331156 @default.
• W2939297204 hasConceptScore W2939297204C202444582 @default.
• W2939297204 hasConceptScore W2939297204C202887219 @default.
• W2939297204 hasConceptScore W2939297204C24424167 @default.
• W2939297204 hasConceptScore W2939297204C2524010 @default.
• W2939297204 hasConceptScore W2939297204C2777210771 @default.
• W2939297204 hasConceptScore W2939297204C28826006 @default.
• W2939297204 hasConceptScore W2939297204C33923547 @default.
• W2939297204 hasConceptScore W2939297204C38349280 @default.
• W2939297204 hasConceptScore W2939297204C41008148 @default.
• W2939297204 hasConceptScore W2939297204C50644808 @default.
• W2939297204 hasConceptScore W2939297204C62520636 @default.
• W2939297204 hasConceptScore W2939297204C74902906 @default.
• W2939297204 hasConceptScore W2939297204C92757383 @default.
• W2939297204 hasOpenAccess W2939297204 @default.
• W2939297204 hasRelatedWork W1522301498 @default.

• next