Matches in SemOpenAlex for { <https://semopenalex.org/work/W3039005005> ?p ?o ?g. }
Showing items 1 to 79 of
79
with 100 items per page.
- W3039005005 abstract "We study the approximation by tensor networks (TNs) of functions from classical smoothness classes. The considered approximation tool combines a tensorization of functions in $L^p([0,1))$, which allows to identify a univariate function with a multivariate function (or tensor), and the use of tree tensor networks (the tensor train format) for exploiting low-rank structures of multivariate functions. The resulting tool can be interpreted as a feed-forward neural network, with first layers implementing the tensorization, interpreted as a particular featuring step, followed by a sum-product network with sparse architecture. In part I of this work, we presented several approximation classes associated with different measures of complexity of tensor networks and studied their properties. In this work (part II), we show how classical approximation tools, such as polynomials or splines (with fixed or free knots), can be encoded as a tensor network with controlled complexity. We use this to derive direct (Jackson) inequalities for the approximation spaces of tensor networks. This is then utilized to show that Besov spaces are continuously embedded into these approximation spaces. In other words, we show that arbitrary Besov functions can be approximated with optimal or near to optimal rate. We also show that an arbitrary function in the approximation class possesses no Besov smoothness, unless one limits the depth of the tensor network." @default.
- W3039005005 created "2020-07-10" @default.
- W3039005005 creator A5009985938 @default.
- W3039005005 creator A5031143836 @default.
- W3039005005 date "2020-07-04" @default.
- W3039005005 modified "2023-10-17" @default.
- W3039005005 title "Approximation with Tensor Networks. Part II: Approximation Rates for Smoothness Classes" @default.
- W3039005005 cites W1499500817 @default.
- W3039005005 cites W1569512666 @default.
- W3039005005 cites W1575992356 @default.
- W3039005005 cites W1601728065 @default.
- W3039005005 cites W162854683 @default.
- W3039005005 cites W1990261069 @default.
- W3039005005 cites W2020038074 @default.
- W3039005005 cites W2059998776 @default.
- W3039005005 cites W2067393519 @default.
- W3039005005 cites W2076063813 @default.
- W3039005005 cites W2107829755 @default.
- W3039005005 cites W2115755118 @default.
- W3039005005 cites W2160251536 @default.
- W3039005005 cites W2171630320 @default.
- W3039005005 cites W2208555118 @default.
- W3039005005 cites W2226462370 @default.
- W3039005005 cites W2269850907 @default.
- W3039005005 cites W2343408237 @default.
- W3039005005 cites W2528305538 @default.
- W3039005005 cites W2617994470 @default.
- W3039005005 cites W2765804450 @default.
- W3039005005 cites W2787302432 @default.
- W3039005005 cites W2975807211 @default.
- W3039005005 cites W2998107928 @default.
- W3039005005 cites W3007082955 @default.
- W3039005005 cites W3009390838 @default.
- W3039005005 cites W3103945605 @default.
- W3039005005 cites W3104867814 @default.
- W3039005005 cites W3121797243 @default.
- W3039005005 cites W3161792008 @default.
- W3039005005 cites W3101570982 @default.
- W3039005005 hasPublicationYear "2020" @default.
- W3039005005 type Work @default.
- W3039005005 sameAs 3039005005 @default.
- W3039005005 citedByCount "2" @default.
- W3039005005 countsByYear W30390050052020 @default.
- W3039005005 countsByYear W30390050052021 @default.
- W3039005005 crossrefType "posted-content" @default.
- W3039005005 hasAuthorship W3039005005A5009985938 @default.
- W3039005005 hasAuthorship W3039005005A5031143836 @default.
- W3039005005 hasBestOaLocation W30390050053 @default.
- W3039005005 hasConcept C102634674 @default.
- W3039005005 hasConcept C134306372 @default.
- W3039005005 hasConcept C155281189 @default.
- W3039005005 hasConcept C202444582 @default.
- W3039005005 hasConcept C28826006 @default.
- W3039005005 hasConcept C33923547 @default.
- W3039005005 hasConceptScore W3039005005C102634674 @default.
- W3039005005 hasConceptScore W3039005005C134306372 @default.
- W3039005005 hasConceptScore W3039005005C155281189 @default.
- W3039005005 hasConceptScore W3039005005C202444582 @default.
- W3039005005 hasConceptScore W3039005005C28826006 @default.
- W3039005005 hasConceptScore W3039005005C33923547 @default.
- W3039005005 hasLocation W30390050051 @default.
- W3039005005 hasLocation W30390050052 @default.
- W3039005005 hasLocation W30390050053 @default.
- W3039005005 hasOpenAccess W3039005005 @default.
- W3039005005 hasPrimaryLocation W30390050051 @default.
- W3039005005 hasRelatedWork W1529715114 @default.
- W3039005005 hasRelatedWork W2038678729 @default.
- W3039005005 hasRelatedWork W2052848886 @default.
- W3039005005 hasRelatedWork W2061184854 @default.
- W3039005005 hasRelatedWork W2079728534 @default.
- W3039005005 hasRelatedWork W2081521562 @default.
- W3039005005 hasRelatedWork W2099288746 @default.
- W3039005005 hasRelatedWork W2911894338 @default.
- W3039005005 hasRelatedWork W3104034845 @default.
- W3039005005 hasRelatedWork W794158601 @default.
- W3039005005 isParatext "false" @default.
- W3039005005 isRetracted "false" @default.
- W3039005005 magId "3039005005" @default.
- W3039005005 workType "article" @default.