Matches in SemOpenAlex for { <https://semopenalex.org/work/W4289713169> ?p ?o ?g. }
Showing items 1 to 75 of
75
with 100 items per page.
- W4289713169 abstract "The variational autoencoder (VAE) has been used in a myriad of applications, e.g., dimensionality reduction and generative modeling. VAE uses a specific model for stochastic sampling in latent space. The normal distribution is the most commonly used one because it allows a straightforward sampling, a reparameterization trick, and a differentiable expression of the Kullback–Leibler divergence. Although various other distributions such as Laplace were studied in literature, the effect of heterogeneous use of different distributions for posterior-prior pair is less known to date. In this paper, we investigate numerous possibilities of such a mismatched VAE, e.g., where the uniform distribution is used as a posterior belief at the encoder while the Cauchy distribution is used as a prior belief at the decoder. To design the mismatched VAE, the total number of potential combinations to explore grows rapidly with the number of latent nodes when allowing different distributions across latent nodes. We propose a novel framework called AutoVAE, which searches for better pairing set of posterior-prior beliefs in the context of automated machine learning for hyperparameter optimization. We demonstrate that the proposed irregular pairing offers a potential gain in the variational Rényi bound. In addition, we analyze a variety of likelihood beliefs and divergence order." @default.
- W4289713169 created "2022-08-04" @default.
- W4289713169 creator A5023338067 @default.
- W4289713169 creator A5065592637 @default.
- W4289713169 date "2022-06-26" @default.
- W4289713169 modified "2023-10-18" @default.
- W4289713169 title "AutoVAE: Mismatched Variational Autoencoder with Irregular Posterior-Prior Pairing" @default.
- W4289713169 cites W1979985652 @default.
- W4289713169 cites W2026653933 @default.
- W4289713169 cites W2949676527 @default.
- W4289713169 cites W3101380508 @default.
- W4289713169 doi "https://doi.org/10.1109/isit50566.2022.9834769" @default.
- W4289713169 hasPublicationYear "2022" @default.
- W4289713169 type Work @default.
- W4289713169 citedByCount "1" @default.
- W4289713169 countsByYear W42897131692023 @default.
- W4289713169 crossrefType "proceedings-article" @default.
- W4289713169 hasAuthorship W4289713169A5023338067 @default.
- W4289713169 hasAuthorship W4289713169A5065592637 @default.
- W4289713169 hasConcept C101738243 @default.
- W4289713169 hasConcept C105795698 @default.
- W4289713169 hasConcept C107673813 @default.
- W4289713169 hasConcept C108583219 @default.
- W4289713169 hasConcept C11413529 @default.
- W4289713169 hasConcept C138885662 @default.
- W4289713169 hasConcept C149441793 @default.
- W4289713169 hasConcept C151730666 @default.
- W4289713169 hasConcept C153180895 @default.
- W4289713169 hasConcept C154945302 @default.
- W4289713169 hasConcept C171752962 @default.
- W4289713169 hasConcept C177769412 @default.
- W4289713169 hasConcept C207390915 @default.
- W4289713169 hasConcept C2779343474 @default.
- W4289713169 hasConcept C33923547 @default.
- W4289713169 hasConcept C41008148 @default.
- W4289713169 hasConcept C41895202 @default.
- W4289713169 hasConcept C57830394 @default.
- W4289713169 hasConcept C8642999 @default.
- W4289713169 hasConcept C86803240 @default.
- W4289713169 hasConceptScore W4289713169C101738243 @default.
- W4289713169 hasConceptScore W4289713169C105795698 @default.
- W4289713169 hasConceptScore W4289713169C107673813 @default.
- W4289713169 hasConceptScore W4289713169C108583219 @default.
- W4289713169 hasConceptScore W4289713169C11413529 @default.
- W4289713169 hasConceptScore W4289713169C138885662 @default.
- W4289713169 hasConceptScore W4289713169C149441793 @default.
- W4289713169 hasConceptScore W4289713169C151730666 @default.
- W4289713169 hasConceptScore W4289713169C153180895 @default.
- W4289713169 hasConceptScore W4289713169C154945302 @default.
- W4289713169 hasConceptScore W4289713169C171752962 @default.
- W4289713169 hasConceptScore W4289713169C177769412 @default.
- W4289713169 hasConceptScore W4289713169C207390915 @default.
- W4289713169 hasConceptScore W4289713169C2779343474 @default.
- W4289713169 hasConceptScore W4289713169C33923547 @default.
- W4289713169 hasConceptScore W4289713169C41008148 @default.
- W4289713169 hasConceptScore W4289713169C41895202 @default.
- W4289713169 hasConceptScore W4289713169C57830394 @default.
- W4289713169 hasConceptScore W4289713169C8642999 @default.
- W4289713169 hasConceptScore W4289713169C86803240 @default.
- W4289713169 hasLocation W42897131691 @default.
- W4289713169 hasOpenAccess W4289713169 @default.
- W4289713169 hasPrimaryLocation W42897131691 @default.
- W4289713169 hasRelatedWork W1972722672 @default.
- W4289713169 hasRelatedWork W2465202047 @default.
- W4289713169 hasRelatedWork W2547407901 @default.
- W4289713169 hasRelatedWork W2891583400 @default.
- W4289713169 hasRelatedWork W2949649223 @default.
- W4289713169 hasRelatedWork W2963015795 @default.
- W4289713169 hasRelatedWork W3124198295 @default.
- W4289713169 hasRelatedWork W3215977089 @default.
- W4289713169 hasRelatedWork W4225782343 @default.
- W4289713169 hasRelatedWork W4289713169 @default.
- W4289713169 isParatext "false" @default.
- W4289713169 isRetracted "false" @default.
- W4289713169 workType "article" @default.