FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4380490515> ?p ?o ?g. }

• W4380490515 abstract "We study the properties of nonparametric least squares regression using deep neural networks. We derive nonasymptotic upper bounds for the excess risk of the empirical risk minimizer of feedforward deep neural regression. Our error bounds achieve minimax optimal rate and improve over the existing ones in the sense that they depend polynomially on the dimension of the predictor, instead of exponentially on dimension. We show that the neural regression estimator can circumvent the curse of dimensionality under the assumption that the predictor is supported on an approximate low-dimensional manifold or a set with low Minkowski dimension. We also establish the optimal convergence rate under the exact manifold support assumption. We investigate how the prediction error of the neural regression estimator depends on the structure of neural networks and propose a notion of network relative efficiency between two types of neural networks, which provides a quantitative measure for evaluating the relative merits of different network structures. To establish these results, we derive a novel approximation error bound for the Hölder smooth functions using ReLU activated neural networks, which may be of independent interest. Our results are derived under weaker assumptions on the data distribution and the neural network structure than those in the existing literature." @default.
• W4380490515 created "2023-06-14" @default.
• W4380490515 creator A5012067697 @default.
• W4380490515 creator A5012426113 @default.
• W4380490515 creator A5058851479 @default.
• W4380490515 creator A5080185313 @default.
• W4380490515 date "2023-04-01" @default.
• W4380490515 modified "2023-10-16" @default.
• W4380490515 title "Deep nonparametric regression on approximate manifolds: Nonasymptotic error bounds with polynomial prefactors" @default.
• W4380490515 cites W1484867920 @default.
• W4380490515 cites W1564947197 @default.
• W4380490515 cites W1680677650 @default.
• W4380490515 cites W1742512077 @default.
• W4380490515 cites W1966949944 @default.
• W4380490515 cites W1967632959 @default.
• W4380490515 cites W1969705577 @default.
• W4380490515 cites W1978930761 @default.
• W4380490515 cites W1986736933 @default.
• W4380490515 cites W1991566301 @default.
• W4380490515 cites W2001141328 @default.
• W4380490515 cites W2010353172 @default.
• W4380490515 cites W2018450309 @default.
• W4380490515 cites W2026151926 @default.
• W4380490515 cites W2028461624 @default.
• W4380490515 cites W2029115180 @default.
• W4380490515 cites W2038845890 @default.
• W4380490515 cites W2044109872 @default.
• W4380490515 cites W2044852142 @default.
• W4380490515 cites W2049343897 @default.
• W4380490515 cites W2053186076 @default.
• W4380490515 cites W2058225082 @default.
• W4380490515 cites W2076791197 @default.
• W4380490515 cites W2078309027 @default.
• W4380490515 cites W2085481869 @default.
• W4380490515 cites W2086874647 @default.
• W4380490515 cites W2091886411 @default.
• W4380490515 cites W2093015317 @default.
• W4380490515 cites W2097308346 @default.
• W4380490515 cites W2108598243 @default.
• W4380490515 cites W2115986460 @default.
• W4380490515 cites W2129586496 @default.
• W4380490515 cites W2156838815 @default.
• W4380490515 cites W2157878484 @default.
• W4380490515 cites W2158485828 @default.
• W4380490515 cites W2159058260 @default.
• W4380490515 cites W2528305538 @default.
• W4380490515 cites W2563917727 @default.
• W4380490515 cites W2946302218 @default.
• W4380490515 cites W2962875621 @default.
• W4380490515 cites W2963631324 @default.
• W4380490515 cites W2963693826 @default.
• W4380490515 cites W2965192329 @default.
• W4380490515 cites W3035281012 @default.
• W4380490515 cites W3049195464 @default.
• W4380490515 cites W3101996726 @default.
• W4380490515 cites W3102511045 @default.
• W4380490515 cites W3103799282 @default.
• W4380490515 cites W3105189648 @default.
• W4380490515 cites W3121856224 @default.
• W4380490515 cites W3125407111 @default.
• W4380490515 cites W3185971845 @default.
• W4380490515 cites W3201938571 @default.
• W4380490515 cites W3204236384 @default.
• W4380490515 cites W4205377395 @default.
• W4380490515 cites W4206421659 @default.
• W4380490515 cites W4238652859 @default.
• W4380490515 cites W4245577611 @default.
• W4380490515 cites W4246954948 @default.
• W4380490515 cites W4249716558 @default.
• W4380490515 cites W4250954493 @default.
• W4380490515 cites W4292025355 @default.
• W4380490515 cites W4293203252 @default.
• W4380490515 doi "https://doi.org/10.1214/23-aos2266" @default.
• W4380490515 hasPublicationYear "2023" @default.
• W4380490515 type Work @default.
• W4380490515 citedByCount "0" @default.
• W4380490515 crossrefType "journal-article" @default.
• W4380490515 hasAuthorship W4380490515A5012067697 @default.
• W4380490515 hasAuthorship W4380490515A5012426113 @default.
• W4380490515 hasAuthorship W4380490515A5058851479 @default.
• W4380490515 hasAuthorship W4380490515A5080185313 @default.
• W4380490515 hasConcept C105795698 @default.
• W4380490515 hasConcept C111030470 @default.
• W4380490515 hasConcept C114614502 @default.
• W4380490515 hasConcept C126255220 @default.
• W4380490515 hasConcept C127162648 @default.
• W4380490515 hasConcept C149728462 @default.
• W4380490515 hasConcept C154945302 @default.
• W4380490515 hasConcept C185429906 @default.
• W4380490515 hasConcept C28826006 @default.
• W4380490515 hasConcept C31258907 @default.
• W4380490515 hasConcept C33676613 @default.
• W4380490515 hasConcept C33923547 @default.
• W4380490515 hasConcept C41008148 @default.
• W4380490515 hasConcept C50644808 @default.
• W4380490515 hasConcept C57869625 @default.
• W4380490515 hasConcept C74127309 @default.
• W4380490515 hasConceptScore W4380490515C105795698 @default.
• W4380490515 hasConceptScore W4380490515C111030470 @default.
• W4380490515 hasConceptScore W4380490515C114614502 @default.

• next