Matches in SemOpenAlex for { <https://semopenalex.org/work/W2752620087> ?p ?o ?g. }
- W2752620087 abstract "Implicit probabilistic models are a flexible class of models defined by a simulation process for data. They form the basis for theories which encompass our understanding of the physical world. Despite this fundamental nature, the use of implicit models remains limited due to challenges in specifying complex latent structure in them, and in performing inferences in such models with large data sets. In this paper, we first introduce hierarchical implicit models (HIMs). HIMs combine the idea of implicit densities with hierarchical Bayesian modeling, thereby defining models via simulators of data with rich hidden structure. Next, we develop likelihood-free variational inference (LFVI), a scalable variational inference algorithm for HIMs. Key to LFVI is specifying a variational family that is also implicit. This matches the model's flexibility and allows for accurate approximation of the posterior. We demonstrate diverse applications: a large-scale physical simulator for predator-prey populations in ecology; a Bayesian generative adversarial network for discrete data; and a deep implicit model for text generation." @default.
- W2752620087 created "2017-09-15" @default.
- W2752620087 creator A5022202456 @default.
- W2752620087 creator A5070920982 @default.
- W2752620087 creator A5081819708 @default.
- W2752620087 date "2017-02-28" @default.
- W2752620087 modified "2023-09-27" @default.
- W2752620087 title "Hierarchical Implicit Models and Likelihood-Free Variational Inference" @default.
- W2752620087 cites W114517082 @default.
- W2752620087 cites W114923250 @default.
- W2752620087 cites W1503398984 @default.
- W2752620087 cites W1516111018 @default.
- W2752620087 cites W1567512734 @default.
- W2752620087 cites W1568513494 @default.
- W2752620087 cites W166614460 @default.
- W2752620087 cites W1880262756 @default.
- W2752620087 cites W1884859883 @default.
- W2752620087 cites W1906598733 @default.
- W2752620087 cites W1909320841 @default.
- W2752620087 cites W1959608418 @default.
- W2752620087 cites W1971085446 @default.
- W2752620087 cites W1981457167 @default.
- W2752620087 cites W2025720061 @default.
- W2752620087 cites W2034795216 @default.
- W2752620087 cites W2045656233 @default.
- W2752620087 cites W2085040216 @default.
- W2752620087 cites W2089818247 @default.
- W2752620087 cites W2099471712 @default.
- W2752620087 cites W2117670920 @default.
- W2752620087 cites W2136133754 @default.
- W2752620087 cites W2139812092 @default.
- W2752620087 cites W2140660104 @default.
- W2752620087 cites W2153125595 @default.
- W2752620087 cites W2166851633 @default.
- W2752620087 cites W2167030304 @default.
- W2752620087 cites W2328111639 @default.
- W2752620087 cites W2396566817 @default.
- W2752620087 cites W2397262406 @default.
- W2752620087 cites W2411541852 @default.
- W2752620087 cites W2412320034 @default.
- W2752620087 cites W2434741482 @default.
- W2752620087 cites W2503443212 @default.
- W2752620087 cites W2530741948 @default.
- W2752620087 cites W2539792571 @default.
- W2752620087 cites W2543468432 @default.
- W2752620087 cites W2557283755 @default.
- W2752620087 cites W2562887561 @default.
- W2752620087 cites W2565378226 @default.
- W2752620087 cites W2752539956 @default.
- W2752620087 cites W284754667 @default.
- W2752620087 cites W2949353404 @default.
- W2752620087 cites W2949416428 @default.
- W2752620087 cites W2949995983 @default.
- W2752620087 cites W2951266961 @default.
- W2752620087 cites W2952673310 @default.
- W2752620087 cites W2963173382 @default.
- W2752620087 cites W2963684088 @default.
- W2752620087 cites W2963811225 @default.
- W2752620087 cites W2964052395 @default.
- W2752620087 cites W2964167449 @default.
- W2752620087 cites W2964250089 @default.
- W2752620087 cites W3127518054 @default.
- W2752620087 cites W632087424 @default.
- W2752620087 hasPublicationYear "2017" @default.
- W2752620087 type Work @default.
- W2752620087 sameAs 2752620087 @default.
- W2752620087 citedByCount "68" @default.
- W2752620087 countsByYear W27526200872017 @default.
- W2752620087 countsByYear W27526200872018 @default.
- W2752620087 countsByYear W27526200872019 @default.
- W2752620087 countsByYear W27526200872020 @default.
- W2752620087 countsByYear W27526200872021 @default.
- W2752620087 countsByYear W27526200872022 @default.
- W2752620087 crossrefType "posted-content" @default.
- W2752620087 hasAuthorship W2752620087A5022202456 @default.
- W2752620087 hasAuthorship W2752620087A5070920982 @default.
- W2752620087 hasAuthorship W2752620087A5081819708 @default.
- W2752620087 hasConcept C105795698 @default.
- W2752620087 hasConcept C107673813 @default.
- W2752620087 hasConcept C119857082 @default.
- W2752620087 hasConcept C154945302 @default.
- W2752620087 hasConcept C160234255 @default.
- W2752620087 hasConcept C167966045 @default.
- W2752620087 hasConcept C2776214188 @default.
- W2752620087 hasConcept C2780598303 @default.
- W2752620087 hasConcept C33923547 @default.
- W2752620087 hasConcept C39890363 @default.
- W2752620087 hasConcept C41008148 @default.
- W2752620087 hasConcept C48044578 @default.
- W2752620087 hasConcept C77088390 @default.
- W2752620087 hasConcept C80444323 @default.
- W2752620087 hasConceptScore W2752620087C105795698 @default.
- W2752620087 hasConceptScore W2752620087C107673813 @default.
- W2752620087 hasConceptScore W2752620087C119857082 @default.
- W2752620087 hasConceptScore W2752620087C154945302 @default.
- W2752620087 hasConceptScore W2752620087C160234255 @default.
- W2752620087 hasConceptScore W2752620087C167966045 @default.
- W2752620087 hasConceptScore W2752620087C2776214188 @default.
- W2752620087 hasConceptScore W2752620087C2780598303 @default.
- W2752620087 hasConceptScore W2752620087C33923547 @default.