Matches in SemOpenAlex for { <https://semopenalex.org/work/W4287764477> ?p ?o ?g. }
Showing items 1 to 79 of
79
with 100 items per page.
- W4287764477 abstract "We propose new machine learning schemes for solving high dimensional nonlinear partial differential equations (PDEs). Relying on the classical backward stochastic differential equation (BSDE) representation of PDEs, our algorithms estimate simultaneously the solution and its gradient by deep neural networks. These approximations are performed at each time step from the minimization of loss functions defined recursively by backward induction. The methodology is extended to variational inequalities arising in optimal stopping problems. We analyze the convergence of the deep learning schemes and provide error estimates in terms of the universal approximation of neural networks. Numerical results show that our algorithms give very good results till dimension 50 (and certainly above), for both PDEs and variational inequalities problems. For the PDEs resolution, our results are very similar to those obtained by the recent method in cite{weinan2017deep} when the latter converges to the right solution or does not diverge. Numerical tests indicate that the proposed methods are not stuck in poor local minimaas it can be the case with the algorithm designed in cite{weinan2017deep}, and no divergence is experienced. The only limitation seems to be due to the inability of the considered deep neural networks to represent a solution with a too complex structure in high dimension." @default.
- W4287764477 created "2022-07-26" @default.
- W4287764477 creator A5000513018 @default.
- W4287764477 creator A5055802354 @default.
- W4287764477 creator A5083566951 @default.
- W4287764477 date "2020-06-04" @default.
- W4287764477 modified "2023-09-30" @default.
- W4287764477 title "Deep backward schemes for high-dimensional nonlinear PDEs" @default.
- W4287764477 hasPublicationYear "2020" @default.
- W4287764477 type Work @default.
- W4287764477 citedByCount "0" @default.
- W4287764477 crossrefType "posted-content" @default.
- W4287764477 hasAuthorship W4287764477A5000513018 @default.
- W4287764477 hasAuthorship W4287764477A5055802354 @default.
- W4287764477 hasAuthorship W4287764477A5083566951 @default.
- W4287764477 hasBestOaLocation W42877644771 @default.
- W4287764477 hasConcept C108583219 @default.
- W4287764477 hasConcept C11413529 @default.
- W4287764477 hasConcept C121332964 @default.
- W4287764477 hasConcept C126255220 @default.
- W4287764477 hasConcept C134306372 @default.
- W4287764477 hasConcept C138885662 @default.
- W4287764477 hasConcept C154945302 @default.
- W4287764477 hasConcept C158622935 @default.
- W4287764477 hasConcept C161999928 @default.
- W4287764477 hasConcept C162324750 @default.
- W4287764477 hasConcept C202444582 @default.
- W4287764477 hasConcept C207390915 @default.
- W4287764477 hasConcept C2777303404 @default.
- W4287764477 hasConcept C28826006 @default.
- W4287764477 hasConcept C33676613 @default.
- W4287764477 hasConcept C33923547 @default.
- W4287764477 hasConcept C41008148 @default.
- W4287764477 hasConcept C41895202 @default.
- W4287764477 hasConcept C50522688 @default.
- W4287764477 hasConcept C50644808 @default.
- W4287764477 hasConcept C62520636 @default.
- W4287764477 hasConcept C93779851 @default.
- W4287764477 hasConceptScore W4287764477C108583219 @default.
- W4287764477 hasConceptScore W4287764477C11413529 @default.
- W4287764477 hasConceptScore W4287764477C121332964 @default.
- W4287764477 hasConceptScore W4287764477C126255220 @default.
- W4287764477 hasConceptScore W4287764477C134306372 @default.
- W4287764477 hasConceptScore W4287764477C138885662 @default.
- W4287764477 hasConceptScore W4287764477C154945302 @default.
- W4287764477 hasConceptScore W4287764477C158622935 @default.
- W4287764477 hasConceptScore W4287764477C161999928 @default.
- W4287764477 hasConceptScore W4287764477C162324750 @default.
- W4287764477 hasConceptScore W4287764477C202444582 @default.
- W4287764477 hasConceptScore W4287764477C207390915 @default.
- W4287764477 hasConceptScore W4287764477C2777303404 @default.
- W4287764477 hasConceptScore W4287764477C28826006 @default.
- W4287764477 hasConceptScore W4287764477C33676613 @default.
- W4287764477 hasConceptScore W4287764477C33923547 @default.
- W4287764477 hasConceptScore W4287764477C41008148 @default.
- W4287764477 hasConceptScore W4287764477C41895202 @default.
- W4287764477 hasConceptScore W4287764477C50522688 @default.
- W4287764477 hasConceptScore W4287764477C50644808 @default.
- W4287764477 hasConceptScore W4287764477C62520636 @default.
- W4287764477 hasConceptScore W4287764477C93779851 @default.
- W4287764477 hasLocation W42877644771 @default.
- W4287764477 hasLocation W42877644772 @default.
- W4287764477 hasLocation W42877644773 @default.
- W4287764477 hasLocation W42877644774 @default.
- W4287764477 hasOpenAccess W4287764477 @default.
- W4287764477 hasPrimaryLocation W42877644771 @default.
- W4287764477 hasRelatedWork W1984319311 @default.
- W4287764477 hasRelatedWork W2037480753 @default.
- W4287764477 hasRelatedWork W2065421399 @default.
- W4287764477 hasRelatedWork W2079475979 @default.
- W4287764477 hasRelatedWork W2171131874 @default.
- W4287764477 hasRelatedWork W3033119168 @default.
- W4287764477 hasRelatedWork W3134989227 @default.
- W4287764477 hasRelatedWork W4229075390 @default.
- W4287764477 hasRelatedWork W4287764477 @default.
- W4287764477 hasRelatedWork W2300790417 @default.
- W4287764477 isParatext "false" @default.
- W4287764477 isRetracted "false" @default.
- W4287764477 workType "article" @default.