FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W2964065385> ?p ?o ?g. }

• W2964065385 endingPage "652" @default.
• W2964065385 startingPage "613" @default.
• W2964065385 abstract "The need to reason about uncertainty in large, complex, and multimodal data sets has become increasingly common across modern scientific environments. The ability to transform samples from one distribution P to another distribution Q enables the solution to many problems in machine learning (e.g., Bayesian inference, generative modeling) and has been actively pursued from theoretical, computational, and application perspectives across the fields of information theory, computer science, and biology. Performing such transformations in general still leads to computational difficulties, especially in high dimensions. Here, we consider the problem of computing such measure transport maps with efficient and parallelizable methods. Under the mild assumptions that P need not be known but can be sampled from and that the density of Q is known up to a proportionality constant, and that Q is log-concave, we provide in this work a convex optimization problem pertaining to relative entropy minimization. We show how an empirical minimization formulation and polynomial chaos map parameterization can allow for learning a transport map between P and Q with distributed and scalable methods. We also leverage findings from nonequilibrium thermodynamics to represent the transport map as a composition of simpler maps, each of which is learned sequentially with a transport cost regularized version of the aforementioned problem formulation. We provide examples of our framework within the context of Bayesian inference for the Boston housing data set and generative modeling for handwritten digit images from the MNIST data set." @default.
• W2964065385 created "2019-07-30" @default.
• W2964065385 creator A5006260768 @default.
• W2964065385 creator A5019429894 @default.
• W2964065385 creator A5021487849 @default.
• W2964065385 creator A5044833213 @default.
• W2964065385 creator A5046582466 @default.
• W2964065385 date "2019-04-01" @default.
• W2964065385 modified "2023-10-14" @default.
• W2964065385 title "A Distributed Framework for the Construction of Transport Maps" @default.
• W2964065385 cites W1669177583 @default.
• W2964065385 cites W1974776581 @default.
• W2964065385 cites W1982652137 @default.
• W2964065385 cites W1991757114 @default.
• W2964065385 cites W1995691260 @default.
• W2964065385 cites W2000769684 @default.
• W2964065385 cites W2020999234 @default.
• W2964065385 cites W2023103251 @default.
• W2964065385 cites W2028852533 @default.
• W2964065385 cites W2029469881 @default.
• W2964065385 cites W2036996178 @default.
• W2964065385 cites W2041779820 @default.
• W2964065385 cites W2045971645 @default.
• W2964065385 cites W2052643735 @default.
• W2964065385 cites W2071048859 @default.
• W2964065385 cites W2112796928 @default.
• W2964065385 cites W2135194391 @default.
• W2964065385 cites W2138309709 @default.
• W2964065385 cites W2542733199 @default.
• W2964065385 cites W3105627363 @default.
• W2964065385 cites W3121701465 @default.
• W2964065385 cites W4236312485 @default.
• W2964065385 cites W4255839052 @default.
• W2964065385 cites W4292363360 @default.
• W2964065385 cites W4292691288 @default.
• W2964065385 cites W65928136 @default.
• W2964065385 doi "https://doi.org/10.1162/neco_a_01172" @default.
• W2964065385 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/30764740" @default.
• W2964065385 hasPublicationYear "2019" @default.
• W2964065385 type Work @default.
• W2964065385 sameAs 2964065385 @default.
• W2964065385 citedByCount "7" @default.
• W2964065385 countsByYear W29640653852019 @default.
• W2964065385 countsByYear W29640653852021 @default.
• W2964065385 countsByYear W29640653852022 @default.
• W2964065385 crossrefType "journal-article" @default.
• W2964065385 hasAuthorship W2964065385A5006260768 @default.
• W2964065385 hasAuthorship W2964065385A5019429894 @default.
• W2964065385 hasAuthorship W2964065385A5021487849 @default.
• W2964065385 hasAuthorship W2964065385A5044833213 @default.
• W2964065385 hasAuthorship W2964065385A5046582466 @default.
• W2964065385 hasBestOaLocation W29640653852 @default.
• W2964065385 hasConcept C107673813 @default.
• W2964065385 hasConcept C119857082 @default.
• W2964065385 hasConcept C126255220 @default.
• W2964065385 hasConcept C153083717 @default.
• W2964065385 hasConcept C154945302 @default.
• W2964065385 hasConcept C160234255 @default.
• W2964065385 hasConcept C171752962 @default.
• W2964065385 hasConcept C190502265 @default.
• W2964065385 hasConcept C2776214188 @default.
• W2964065385 hasConcept C33923547 @default.
• W2964065385 hasConcept C41008148 @default.
• W2964065385 hasConcept C50644808 @default.
• W2964065385 hasConcept C80444323 @default.
• W2964065385 hasConcept C9679016 @default.
• W2964065385 hasConceptScore W2964065385C107673813 @default.
• W2964065385 hasConceptScore W2964065385C119857082 @default.
• W2964065385 hasConceptScore W2964065385C126255220 @default.
• W2964065385 hasConceptScore W2964065385C153083717 @default.
• W2964065385 hasConceptScore W2964065385C154945302 @default.
• W2964065385 hasConceptScore W2964065385C160234255 @default.
• W2964065385 hasConceptScore W2964065385C171752962 @default.
• W2964065385 hasConceptScore W2964065385C190502265 @default.
• W2964065385 hasConceptScore W2964065385C2776214188 @default.
• W2964065385 hasConceptScore W2964065385C33923547 @default.
• W2964065385 hasConceptScore W2964065385C41008148 @default.
• W2964065385 hasConceptScore W2964065385C50644808 @default.
• W2964065385 hasConceptScore W2964065385C80444323 @default.
• W2964065385 hasConceptScore W2964065385C9679016 @default.
• W2964065385 hasIssue "4" @default.
• W2964065385 hasLocation W29640653851 @default.
• W2964065385 hasLocation W29640653852 @default.
• W2964065385 hasLocation W29640653853 @default.
• W2964065385 hasOpenAccess W2964065385 @default.
• W2964065385 hasPrimaryLocation W29640653851 @default.
• W2964065385 hasRelatedWork W2057533129 @default.
• W2964065385 hasRelatedWork W2218958931 @default.
• W2964065385 hasRelatedWork W2511279186 @default.
• W2964065385 hasRelatedWork W2559984982 @default.
• W2964065385 hasRelatedWork W2895067291 @default.
• W2964065385 hasRelatedWork W2899509766 @default.
• W2964065385 hasRelatedWork W2963058055 @default.
• W2964065385 hasRelatedWork W3029748970 @default.
• W2964065385 hasRelatedWork W3037935198 @default.
• W2964065385 hasRelatedWork W4297785650 @default.
• W2964065385 hasVolume "31" @default.
• W2964065385 isParatext "false" @default.

• next