Matches in SemOpenAlex for { <https://semopenalex.org/work/W4287326146> ?p ?o ?g. }
Showing items 1 to 70 of
70
with 100 items per page.
- W4287326146 abstract "DeepONets have recently been proposed as a framework for learning nonlinear operators mapping between infinite dimensional Banach spaces. We analyze DeepONets and prove estimates on the resulting approximation and generalization errors. In particular, we extend the universal approximation property of DeepONets to include measurable mappings in non-compact spaces. By a decomposition of the error into encoding, approximation and reconstruction errors, we prove both lower and upper bounds on the total error, relating it to the spectral decay properties of the covariance operators, associated with the underlying measures. We derive almost optimal error bounds with very general affine reconstructors and with random sensor locations as well as bounds on the generalization error, using covering number arguments. We illustrate our general framework with four prototypical examples of nonlinear operators, namely those arising in a nonlinear forced ODE, an elliptic PDE with variable coefficients and nonlinear parabolic and hyperbolic PDEs. While the approximation of arbitrary Lipschitz operators by DeepONets to accuracy $epsilon$ is argued to suffer from a curse of dimensionality (requiring a neural networks of exponential size in $1/epsilon$), in contrast, for all the above concrete examples of interest, we rigorously prove that DeepONets can break this curse of dimensionality (achieving accuracy $epsilon$ with neural networks of size that can grow algebraically in $1/epsilon$). Thus, we demonstrate the efficient approximation of a potentially large class of operators with this machine learning framework." @default.
- W4287326146 created "2022-07-25" @default.
- W4287326146 creator A5009658255 @default.
- W4287326146 creator A5036562548 @default.
- W4287326146 creator A5082251879 @default.
- W4287326146 date "2021-02-18" @default.
- W4287326146 modified "2023-09-24" @default.
- W4287326146 title "Error estimates for DeepOnets: A deep learning framework in infinite dimensions" @default.
- W4287326146 doi "https://doi.org/10.48550/arxiv.2102.09618" @default.
- W4287326146 hasPublicationYear "2021" @default.
- W4287326146 type Work @default.
- W4287326146 citedByCount "0" @default.
- W4287326146 crossrefType "posted-content" @default.
- W4287326146 hasAuthorship W4287326146A5009658255 @default.
- W4287326146 hasAuthorship W4287326146A5036562548 @default.
- W4287326146 hasAuthorship W4287326146A5082251879 @default.
- W4287326146 hasBestOaLocation W42873261461 @default.
- W4287326146 hasConcept C105795698 @default.
- W4287326146 hasConcept C111030470 @default.
- W4287326146 hasConcept C118615104 @default.
- W4287326146 hasConcept C121332964 @default.
- W4287326146 hasConcept C122383733 @default.
- W4287326146 hasConcept C132954091 @default.
- W4287326146 hasConcept C134306372 @default.
- W4287326146 hasConcept C152306953 @default.
- W4287326146 hasConcept C154945302 @default.
- W4287326146 hasConcept C158622935 @default.
- W4287326146 hasConcept C177148314 @default.
- W4287326146 hasConcept C202444582 @default.
- W4287326146 hasConcept C22324862 @default.
- W4287326146 hasConcept C28826006 @default.
- W4287326146 hasConcept C33923547 @default.
- W4287326146 hasConcept C41008148 @default.
- W4287326146 hasConcept C50644808 @default.
- W4287326146 hasConcept C62520636 @default.
- W4287326146 hasConceptScore W4287326146C105795698 @default.
- W4287326146 hasConceptScore W4287326146C111030470 @default.
- W4287326146 hasConceptScore W4287326146C118615104 @default.
- W4287326146 hasConceptScore W4287326146C121332964 @default.
- W4287326146 hasConceptScore W4287326146C122383733 @default.
- W4287326146 hasConceptScore W4287326146C132954091 @default.
- W4287326146 hasConceptScore W4287326146C134306372 @default.
- W4287326146 hasConceptScore W4287326146C152306953 @default.
- W4287326146 hasConceptScore W4287326146C154945302 @default.
- W4287326146 hasConceptScore W4287326146C158622935 @default.
- W4287326146 hasConceptScore W4287326146C177148314 @default.
- W4287326146 hasConceptScore W4287326146C202444582 @default.
- W4287326146 hasConceptScore W4287326146C22324862 @default.
- W4287326146 hasConceptScore W4287326146C28826006 @default.
- W4287326146 hasConceptScore W4287326146C33923547 @default.
- W4287326146 hasConceptScore W4287326146C41008148 @default.
- W4287326146 hasConceptScore W4287326146C50644808 @default.
- W4287326146 hasConceptScore W4287326146C62520636 @default.
- W4287326146 hasLocation W42873261461 @default.
- W4287326146 hasLocation W42873261462 @default.
- W4287326146 hasOpenAccess W4287326146 @default.
- W4287326146 hasPrimaryLocation W42873261461 @default.
- W4287326146 hasRelatedWork W2036827279 @default.
- W4287326146 hasRelatedWork W2081467783 @default.
- W4287326146 hasRelatedWork W2217875172 @default.
- W4287326146 hasRelatedWork W2884620040 @default.
- W4287326146 hasRelatedWork W3133338006 @default.
- W4287326146 hasRelatedWork W3183298406 @default.
- W4287326146 hasRelatedWork W4287326146 @default.
- W4287326146 hasRelatedWork W4294539917 @default.
- W4287326146 hasRelatedWork W972173259 @default.
- W4287326146 hasRelatedWork W977684400 @default.
- W4287326146 isParatext "false" @default.
- W4287326146 isRetracted "false" @default.
- W4287326146 workType "article" @default.