Matches in SemOpenAlex for { <https://semopenalex.org/work/W2954036577> ?p ?o ?g. }
Showing items 1 to 71 of
71
with 100 items per page.
- W2954036577 endingPage "4702" @default.
- W2954036577 startingPage "4693" @default.
- W2954036577 abstract "Hyperbolic space is a geometry that is known to be well-suited for representation learning of data with an underlying hierarchical structure. In this paper, we present a novel hyperbolic distribution called textit{pseudo-hyperbolic Gaussian}, a Gaussian-like distribution on hyperbolic space whose density can be evaluated analytically and differentiated with respect to the parameters. Our distribution enables the gradient-based learning of the probabilistic models on hyperbolic space that could never have been considered before. Also, we can sample from this hyperbolic probability distribution without resorting to auxiliary means like rejection sampling. As applications of our distribution, we develop a hyperbolic-analog of variational autoencoder and a method of probabilistic word embedding on hyperbolic space. We demonstrate the efficacy of our distribution on various datasets including MNIST, Atari 2600 Breakout, and WordNet." @default.
- W2954036577 created "2019-07-12" @default.
- W2954036577 creator A5064529422 @default.
- W2954036577 creator A5069727715 @default.
- W2954036577 creator A5071661077 @default.
- W2954036577 creator A5071930860 @default.
- W2954036577 date "2019-05-24" @default.
- W2954036577 modified "2023-10-14" @default.
- W2954036577 title "A Wrapped Normal Distribution on Hyperbolic Space for Gradient-Based Learning" @default.
- W2954036577 hasPublicationYear "2019" @default.
- W2954036577 type Work @default.
- W2954036577 sameAs 2954036577 @default.
- W2954036577 citedByCount "14" @default.
- W2954036577 countsByYear W29540365772020 @default.
- W2954036577 countsByYear W29540365772021 @default.
- W2954036577 crossrefType "proceedings-article" @default.
- W2954036577 hasAuthorship W2954036577A5064529422 @default.
- W2954036577 hasAuthorship W2954036577A5069727715 @default.
- W2954036577 hasAuthorship W2954036577A5071661077 @default.
- W2954036577 hasAuthorship W2954036577A5071930860 @default.
- W2954036577 hasConcept C110121322 @default.
- W2954036577 hasConcept C121332964 @default.
- W2954036577 hasConcept C134306372 @default.
- W2954036577 hasConcept C154945302 @default.
- W2954036577 hasConcept C163716315 @default.
- W2954036577 hasConcept C190502265 @default.
- W2954036577 hasConcept C33923547 @default.
- W2954036577 hasConcept C41008148 @default.
- W2954036577 hasConcept C50644808 @default.
- W2954036577 hasConcept C62520636 @default.
- W2954036577 hasConcept C83677898 @default.
- W2954036577 hasConceptScore W2954036577C110121322 @default.
- W2954036577 hasConceptScore W2954036577C121332964 @default.
- W2954036577 hasConceptScore W2954036577C134306372 @default.
- W2954036577 hasConceptScore W2954036577C154945302 @default.
- W2954036577 hasConceptScore W2954036577C163716315 @default.
- W2954036577 hasConceptScore W2954036577C190502265 @default.
- W2954036577 hasConceptScore W2954036577C33923547 @default.
- W2954036577 hasConceptScore W2954036577C41008148 @default.
- W2954036577 hasConceptScore W2954036577C50644808 @default.
- W2954036577 hasConceptScore W2954036577C62520636 @default.
- W2954036577 hasConceptScore W2954036577C83677898 @default.
- W2954036577 hasLocation W29540365771 @default.
- W2954036577 hasOpenAccess W2954036577 @default.
- W2954036577 hasPrimaryLocation W29540365771 @default.
- W2954036577 hasRelatedWork W1576724246 @default.
- W2954036577 hasRelatedWork W1959608418 @default.
- W2954036577 hasRelatedWork W1971215074 @default.
- W2954036577 hasRelatedWork W2001070843 @default.
- W2954036577 hasRelatedWork W2904851806 @default.
- W2954036577 hasRelatedWork W2922828897 @default.
- W2954036577 hasRelatedWork W2944617599 @default.
- W2954036577 hasRelatedWork W2962911072 @default.
- W2954036577 hasRelatedWork W2962918699 @default.
- W2954036577 hasRelatedWork W2962936818 @default.
- W2954036577 hasRelatedWork W2963090522 @default.
- W2954036577 hasRelatedWork W2963849380 @default.
- W2954036577 hasRelatedWork W2964121744 @default.
- W2954036577 hasRelatedWork W2970326421 @default.
- W2954036577 hasRelatedWork W2970726356 @default.
- W2954036577 hasRelatedWork W3035102141 @default.
- W2954036577 hasRelatedWork W3102317997 @default.
- W2954036577 hasRelatedWork W3118608800 @default.
- W2954036577 hasRelatedWork W2963448675 @default.
- W2954036577 hasRelatedWork W2970757764 @default.
- W2954036577 isParatext "false" @default.
- W2954036577 isRetracted "false" @default.
- W2954036577 magId "2954036577" @default.
- W2954036577 workType "article" @default.