FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W3136633797> ?p ?o ?g. }

• W3136633797 abstract "Statistical distances (SDs), which quantify the dissimilarity between probability distributions, are central to machine learning and statistics. A modern method for estimating such distances from data relies on parametrizing a variational form by a neural network (NN) and optimizing it. These estimators are abundantly used in practice, but corresponding performance guarantees are partial and call for further exploration. In particular, there seems to be a fundamental tradeoff between the two sources of error involved: approximation and estimation. While the former needs the NN class to be rich and expressive, the latter relies on controlling complexity. This paper explores this tradeoff by means of non-asymptotic error bounds, focusing on three popular choices of SDs -- Kullback-Leibler divergence, chi-squared divergence, and squared Hellinger distance. Our analysis relies on non-asymptotic function approximation theorems and tools from empirical process theory. Numerical results validating the theory are also provided." @default.
• W3136633797 created "2021-03-29" @default.
• W3136633797 creator A5036129864 @default.
• W3136633797 creator A5071112095 @default.
• W3136633797 creator A5086698877 @default.
• W3136633797 date "2021-03-11" @default.
• W3136633797 modified "2023-10-15" @default.
• W3136633797 title "Non-Asymptotic Performance Guarantees for Neural Estimation of $mathsf{f}$-Divergences" @default.
• W3136633797 cites W152055444 @default.
• W3136633797 cites W1522301498 @default.
• W3136633797 cites W1639961155 @default.
• W3136633797 cites W1673728053 @default.
• W3136633797 cites W1959608418 @default.
• W3136633797 cites W1973631422 @default.
• W3136633797 cites W199156503 @default.
• W3136633797 cites W2001150023 @default.
• W3136633797 cites W2010353172 @default.
• W3136633797 cites W2051579606 @default.
• W3136633797 cites W2099471712 @default.
• W3136633797 cites W2111725927 @default.
• W3136633797 cites W2149268774 @default.
• W3136633797 cites W2166116275 @default.
• W3136633797 cites W2166848538 @default.
• W3136633797 cites W2166944917 @default.
• W3136633797 cites W2188155116 @default.
• W3136633797 cites W2328111639 @default.
• W3136633797 cites W2739748921 @default.
• W3136633797 cites W2803832867 @default.
• W3136633797 cites W2912433662 @default.
• W3136633797 cites W2963097630 @default.
• W3136633797 cites W2963180359 @default.
• W3136633797 cites W2963746531 @default.
• W3136633797 cites W2963800509 @default.
• W3136633797 cites W2986904542 @default.
• W3136633797 cites W3110763182 @default.
• W3136633797 cites W3127518054 @default.
• W3136633797 cites W2183586954 @default.
• W3136633797 hasPublicationYear "2021" @default.
• W3136633797 type Work @default.
• W3136633797 sameAs 3136633797 @default.
• W3136633797 citedByCount "0" @default.
• W3136633797 crossrefType "posted-content" @default.
• W3136633797 hasAuthorship W3136633797A5036129864 @default.
• W3136633797 hasAuthorship W3136633797A5071112095 @default.
• W3136633797 hasAuthorship W3136633797A5086698877 @default.
• W3136633797 hasConcept C105795698 @default.
• W3136633797 hasConcept C119047807 @default.
• W3136633797 hasConcept C126255220 @default.
• W3136633797 hasConcept C138885662 @default.
• W3136633797 hasConcept C139945424 @default.
• W3136633797 hasConcept C14036430 @default.
• W3136633797 hasConcept C153024298 @default.
• W3136633797 hasConcept C154945302 @default.
• W3136633797 hasConcept C171752962 @default.
• W3136633797 hasConcept C185429906 @default.
• W3136633797 hasConcept C207390915 @default.
• W3136633797 hasConcept C2777212361 @default.
• W3136633797 hasConcept C28826006 @default.
• W3136633797 hasConcept C33923547 @default.
• W3136633797 hasConcept C41008148 @default.
• W3136633797 hasConcept C41895202 @default.
• W3136633797 hasConcept C50644808 @default.
• W3136633797 hasConcept C78458016 @default.
• W3136633797 hasConcept C86803240 @default.
• W3136633797 hasConceptScore W3136633797C105795698 @default.
• W3136633797 hasConceptScore W3136633797C119047807 @default.
• W3136633797 hasConceptScore W3136633797C126255220 @default.
• W3136633797 hasConceptScore W3136633797C138885662 @default.
• W3136633797 hasConceptScore W3136633797C139945424 @default.
• W3136633797 hasConceptScore W3136633797C14036430 @default.
• W3136633797 hasConceptScore W3136633797C153024298 @default.
• W3136633797 hasConceptScore W3136633797C154945302 @default.
• W3136633797 hasConceptScore W3136633797C171752962 @default.
• W3136633797 hasConceptScore W3136633797C185429906 @default.
• W3136633797 hasConceptScore W3136633797C207390915 @default.
• W3136633797 hasConceptScore W3136633797C2777212361 @default.
• W3136633797 hasConceptScore W3136633797C28826006 @default.
• W3136633797 hasConceptScore W3136633797C33923547 @default.
• W3136633797 hasConceptScore W3136633797C41008148 @default.
• W3136633797 hasConceptScore W3136633797C41895202 @default.
• W3136633797 hasConceptScore W3136633797C50644808 @default.
• W3136633797 hasConceptScore W3136633797C78458016 @default.
• W3136633797 hasConceptScore W3136633797C86803240 @default.
• W3136633797 hasLocation W31366337971 @default.
• W3136633797 hasOpenAccess W3136633797 @default.
• W3136633797 hasPrimaryLocation W31366337971 @default.
• W3136633797 hasRelatedWork W1536444838 @default.
• W3136633797 hasRelatedWork W1665444075 @default.
• W3136633797 hasRelatedWork W2090458642 @default.
• W3136633797 hasRelatedWork W2130607673 @default.
• W3136633797 hasRelatedWork W2182439836 @default.
• W3136633797 hasRelatedWork W2185854139 @default.
• W3136633797 hasRelatedWork W2287077904 @default.
• W3136633797 hasRelatedWork W2519513981 @default.
• W3136633797 hasRelatedWork W2549093080 @default.
• W3136633797 hasRelatedWork W2938943746 @default.
• W3136633797 hasRelatedWork W2949761599 @default.
• W3136633797 hasRelatedWork W2950952699 @default.
• W3136633797 hasRelatedWork W2951894377 @default.
• W3136633797 hasRelatedWork W3008687972 @default.

• next