Matches in SemOpenAlex for { <https://semopenalex.org/work/W2891788052> ?p ?o ?g. }
Showing items 1 to 78 of
78
with 100 items per page.
- W2891788052 abstract "The development of new classification and regression algorithms based on empirical risk minimization (ERM) over deep neural network hypothesis classes, coined deep learning, revolutionized the area of artificial intelligence, machine learning, and data analysis. In particular, these methods have been applied to the numerical solution of high-dimensional partial differential equations with great success. Recent simulations indicate that deep learning-based algorithms are capable of overcoming the curse of dimensionality for the numerical solution of Kolmogorov equations, which are widely used in models from engineering, finance, and the natural sciences. The present paper considers under which conditions ERM over a deep neural network hypothesis class approximates the solution of a $d$-dimensional Kolmogorov equation with affine drift and diffusion coefficients and typical initial values arising from problems in computational finance up to error $varepsilon$. We establish that, with high probability over draws of training samples, such an approximation can be achieved with both the size of the hypothesis class and the number of training samples scaling only polynomially in $d$ and $varepsilon^{-1}$. It can be concluded that ERM over deep neural network hypothesis classes overcomes the curse of dimensionality for the numerical solution of linear Kolmogorov equations with affine coefficients." @default.
- W2891788052 created "2018-09-27" @default.
- W2891788052 creator A5023888160 @default.
- W2891788052 creator A5063776881 @default.
- W2891788052 creator A5074382323 @default.
- W2891788052 date "2018-09-01" @default.
- W2891788052 modified "2023-09-23" @default.
- W2891788052 title "Analysis of the generalization error: Empirical risk minimization over deep artificial neural networks overcomes the curse of dimensionality in the numerical approximation of Black-Scholes partial differential equations" @default.
- W2891788052 hasPublicationYear "2018" @default.
- W2891788052 type Work @default.
- W2891788052 sameAs 2891788052 @default.
- W2891788052 citedByCount "2" @default.
- W2891788052 countsByYear W28917880522020 @default.
- W2891788052 crossrefType "journal-article" @default.
- W2891788052 hasAuthorship W2891788052A5023888160 @default.
- W2891788052 hasAuthorship W2891788052A5063776881 @default.
- W2891788052 hasAuthorship W2891788052A5074382323 @default.
- W2891788052 hasConcept C107321475 @default.
- W2891788052 hasConcept C108583219 @default.
- W2891788052 hasConcept C111030470 @default.
- W2891788052 hasConcept C126255220 @default.
- W2891788052 hasConcept C134306372 @default.
- W2891788052 hasConcept C154945302 @default.
- W2891788052 hasConcept C186219872 @default.
- W2891788052 hasConcept C202444582 @default.
- W2891788052 hasConcept C28826006 @default.
- W2891788052 hasConcept C33923547 @default.
- W2891788052 hasConcept C41008148 @default.
- W2891788052 hasConcept C50644808 @default.
- W2891788052 hasConcept C51544822 @default.
- W2891788052 hasConcept C59465623 @default.
- W2891788052 hasConcept C78045399 @default.
- W2891788052 hasConcept C92757383 @default.
- W2891788052 hasConcept C93779851 @default.
- W2891788052 hasConceptScore W2891788052C107321475 @default.
- W2891788052 hasConceptScore W2891788052C108583219 @default.
- W2891788052 hasConceptScore W2891788052C111030470 @default.
- W2891788052 hasConceptScore W2891788052C126255220 @default.
- W2891788052 hasConceptScore W2891788052C134306372 @default.
- W2891788052 hasConceptScore W2891788052C154945302 @default.
- W2891788052 hasConceptScore W2891788052C186219872 @default.
- W2891788052 hasConceptScore W2891788052C202444582 @default.
- W2891788052 hasConceptScore W2891788052C28826006 @default.
- W2891788052 hasConceptScore W2891788052C33923547 @default.
- W2891788052 hasConceptScore W2891788052C41008148 @default.
- W2891788052 hasConceptScore W2891788052C50644808 @default.
- W2891788052 hasConceptScore W2891788052C51544822 @default.
- W2891788052 hasConceptScore W2891788052C59465623 @default.
- W2891788052 hasConceptScore W2891788052C78045399 @default.
- W2891788052 hasConceptScore W2891788052C92757383 @default.
- W2891788052 hasConceptScore W2891788052C93779851 @default.
- W2891788052 hasLocation W28917880521 @default.
- W2891788052 hasOpenAccess W2891788052 @default.
- W2891788052 hasPrimaryLocation W28917880521 @default.
- W2891788052 hasRelatedWork W1497252155 @default.
- W2891788052 hasRelatedWork W1998158229 @default.
- W2891788052 hasRelatedWork W2069357081 @default.
- W2891788052 hasRelatedWork W2617695214 @default.
- W2891788052 hasRelatedWork W2762578791 @default.
- W2891788052 hasRelatedWork W2793574154 @default.
- W2891788052 hasRelatedWork W2852105405 @default.
- W2891788052 hasRelatedWork W2951074469 @default.
- W2891788052 hasRelatedWork W2963483869 @default.
- W2891788052 hasRelatedWork W2963494703 @default.
- W2891788052 hasRelatedWork W2964038363 @default.
- W2891788052 hasRelatedWork W2994974560 @default.
- W2891788052 hasRelatedWork W3027390827 @default.
- W2891788052 hasRelatedWork W3084415865 @default.
- W2891788052 hasRelatedWork W3085857580 @default.
- W2891788052 hasRelatedWork W3097796098 @default.
- W2891788052 hasRelatedWork W3103622152 @default.
- W2891788052 hasRelatedWork W3137849220 @default.
- W2891788052 hasRelatedWork W3157945851 @default.
- W2891788052 hasRelatedWork W3179632780 @default.
- W2891788052 isParatext "false" @default.
- W2891788052 isRetracted "false" @default.
- W2891788052 magId "2891788052" @default.
- W2891788052 workType "article" @default.