Matches in SemOpenAlex for { <https://semopenalex.org/work/W3199775905> ?p ?o ?g. }
Showing items 1 to 88 of
88
with 100 items per page.
- W3199775905 endingPage "A3182" @default.
- W3199775905 startingPage "A3158" @default.
- W3199775905 abstract "Physics-informed neural networks (PINNs) have become a popular choice for solving high-dimensional partial differential equations (PDEs) due to their excellent approximation power and generalization ability. Recently, Extended PINNs (XPINNs) based on domain decomposition methods have attracted considerable attention due to their effectiveness in modeling multiscale and multiphysics problems and their parallelization. However, theoretical understanding on their convergence and generalization properties remains unexplored. In this study, we take an initial step towards understanding how and when XPINNs outperform PINNs. Specifically, for general multi-layer PINNs and XPINNs, we first provide a prior generalization bound via the complexity of the target functions in the PDE problem, and a posterior generalization bound via the posterior matrix norms of the networks after optimization. Moreover, based on our bounds, we analyze the conditions under which XPINNs improve generalization. Concretely, our theory shows that the key building block of XPINN, namely the domain decomposition, introduces a tradeoff for generalization. On the one hand, XPINNs decompose the complex PDE solution into several simple parts, which decreases the complexity needed to learn each part and boosts generalization. On the other hand, decomposition leads to less training data being available in each subdomain, and hence such model is typically prone to overfitting and may become less generalizable. Empirically, we choose five PDEs to show when XPINNs perform better than, similar to, or worse than PINNs, hence demonstrating and justifying our new theory." @default.
- W3199775905 created "2021-09-27" @default.
- W3199775905 creator A5003184366 @default.
- W3199775905 creator A5009658255 @default.
- W3199775905 creator A5061905151 @default.
- W3199775905 creator A5090943765 @default.
- W3199775905 date "2022-09-27" @default.
- W3199775905 modified "2023-10-18" @default.
- W3199775905 title "When Do Extended Physics-Informed Neural Networks (XPINNs) Improve Generalization?" @default.
- W3199775905 cites W2011173403 @default.
- W3199775905 cites W2051434435 @default.
- W3199775905 cites W2062430377 @default.
- W3199775905 cites W2091772836 @default.
- W3199775905 cites W2550848904 @default.
- W3199775905 cites W2559827045 @default.
- W3199775905 cites W2899283552 @default.
- W3199775905 cites W2948551291 @default.
- W3199775905 cites W3010839048 @default.
- W3199775905 cites W3015865829 @default.
- W3199775905 cites W3028009715 @default.
- W3199775905 cites W3098546160 @default.
- W3199775905 cites W3099057226 @default.
- W3199775905 cites W3102139197 @default.
- W3199775905 cites W3133608513 @default.
- W3199775905 cites W3153200540 @default.
- W3199775905 doi "https://doi.org/10.1137/21m1447039" @default.
- W3199775905 hasPublicationYear "2022" @default.
- W3199775905 type Work @default.
- W3199775905 sameAs 3199775905 @default.
- W3199775905 citedByCount "26" @default.
- W3199775905 countsByYear W31997759052021 @default.
- W3199775905 countsByYear W31997759052022 @default.
- W3199775905 countsByYear W31997759052023 @default.
- W3199775905 crossrefType "journal-article" @default.
- W3199775905 hasAuthorship W3199775905A5003184366 @default.
- W3199775905 hasAuthorship W3199775905A5009658255 @default.
- W3199775905 hasAuthorship W3199775905A5061905151 @default.
- W3199775905 hasAuthorship W3199775905A5090943765 @default.
- W3199775905 hasBestOaLocation W31997759053 @default.
- W3199775905 hasConcept C11413529 @default.
- W3199775905 hasConcept C126255220 @default.
- W3199775905 hasConcept C134306372 @default.
- W3199775905 hasConcept C154945302 @default.
- W3199775905 hasConcept C177148314 @default.
- W3199775905 hasConcept C22019652 @default.
- W3199775905 hasConcept C28826006 @default.
- W3199775905 hasConcept C33923547 @default.
- W3199775905 hasConcept C41008148 @default.
- W3199775905 hasConcept C50644808 @default.
- W3199775905 hasConcept C93779851 @default.
- W3199775905 hasConceptScore W3199775905C11413529 @default.
- W3199775905 hasConceptScore W3199775905C126255220 @default.
- W3199775905 hasConceptScore W3199775905C134306372 @default.
- W3199775905 hasConceptScore W3199775905C154945302 @default.
- W3199775905 hasConceptScore W3199775905C177148314 @default.
- W3199775905 hasConceptScore W3199775905C22019652 @default.
- W3199775905 hasConceptScore W3199775905C28826006 @default.
- W3199775905 hasConceptScore W3199775905C33923547 @default.
- W3199775905 hasConceptScore W3199775905C41008148 @default.
- W3199775905 hasConceptScore W3199775905C50644808 @default.
- W3199775905 hasConceptScore W3199775905C93779851 @default.
- W3199775905 hasFunder F4320306084 @default.
- W3199775905 hasFunder F4320333591 @default.
- W3199775905 hasIssue "5" @default.
- W3199775905 hasLocation W31997759051 @default.
- W3199775905 hasLocation W31997759052 @default.
- W3199775905 hasLocation W31997759053 @default.
- W3199775905 hasLocation W31997759054 @default.
- W3199775905 hasLocation W31997759055 @default.
- W3199775905 hasOpenAccess W3199775905 @default.
- W3199775905 hasPrimaryLocation W31997759051 @default.
- W3199775905 hasRelatedWork W2058836363 @default.
- W3199775905 hasRelatedWork W2936107532 @default.
- W3199775905 hasRelatedWork W2950186470 @default.
- W3199775905 hasRelatedWork W3110382310 @default.
- W3199775905 hasRelatedWork W3110700750 @default.
- W3199775905 hasRelatedWork W3128397465 @default.
- W3199775905 hasRelatedWork W3165925361 @default.
- W3199775905 hasRelatedWork W4281626267 @default.
- W3199775905 hasRelatedWork W4378505373 @default.
- W3199775905 hasRelatedWork W4382141987 @default.
- W3199775905 hasVolume "44" @default.
- W3199775905 isParatext "false" @default.
- W3199775905 isRetracted "false" @default.
- W3199775905 magId "3199775905" @default.
- W3199775905 workType "article" @default.