Matches in SemOpenAlex for { <https://semopenalex.org/work/W4365440892> ?p ?o ?g. }
Showing items 1 to 73 of
73
with 100 items per page.
- W4365440892 abstract "PDE-constrained inverse problems are some of the most challenging and computationally demanding problems in computational science today. Fine meshes that are required to accurately compute the PDE solution introduce an enormous number of parameters and require large scale computing resources such as more processors and more memory to solve such systems in a reasonable time. For inverse problems constrained by time dependent PDEs, the adjoint method that is often employed to efficiently compute gradients and higher order derivatives requires solving a time-reversed, so-called adjoint PDE that depends on the forward PDE solution at each timestep. This necessitates the storage of a high dimensional forward solution vector at every timestep. Such a procedure quickly exhausts the available memory resources. Several approaches that trade additional computation for reduced memory footprint have been proposed to mitigate the memory bottleneck, including checkpointing and compression strategies. In this work, we propose a close-to-ideal scalable compression approach using autoencoders to eliminate the need for checkpointing and substantial memory storage, thereby reducing both the time-to-solution and memory requirements. We compare our approach with checkpointing and an off-the-shelf compression approach on an earth-scale ill-posed seismic inverse problem. The results verify the expected close-to-ideal speedup for both the gradient and Hessian-vector product using the proposed autoencoder compression approach. To highlight the usefulness of the proposed approach, we combine the autoencoder compression with the data-informed active subspace (DIAS) prior to show how the DIAS method can be affordably extended to large scale problems without the need of checkpointing and large memory." @default.
- W4365440892 created "2023-04-15" @default.
- W4365440892 creator A5008274019 @default.
- W4365440892 creator A5050927026 @default.
- W4365440892 creator A5051806400 @default.
- W4365440892 creator A5069669632 @default.
- W4365440892 date "2023-04-10" @default.
- W4365440892 modified "2023-09-30" @default.
- W4365440892 title "An autoencoder compression approach for accelerating large-scale inverse problems" @default.
- W4365440892 doi "https://doi.org/10.48550/arxiv.2304.04781" @default.
- W4365440892 hasPublicationYear "2023" @default.
- W4365440892 type Work @default.
- W4365440892 citedByCount "0" @default.
- W4365440892 crossrefType "posted-content" @default.
- W4365440892 hasAuthorship W4365440892A5008274019 @default.
- W4365440892 hasAuthorship W4365440892A5050927026 @default.
- W4365440892 hasAuthorship W4365440892A5051806400 @default.
- W4365440892 hasAuthorship W4365440892A5069669632 @default.
- W4365440892 hasBestOaLocation W43654408921 @default.
- W4365440892 hasConcept C101738243 @default.
- W4365440892 hasConcept C108583219 @default.
- W4365440892 hasConcept C111919701 @default.
- W4365440892 hasConcept C11413529 @default.
- W4365440892 hasConcept C126255220 @default.
- W4365440892 hasConcept C134306372 @default.
- W4365440892 hasConcept C135252773 @default.
- W4365440892 hasConcept C147060835 @default.
- W4365440892 hasConcept C149635348 @default.
- W4365440892 hasConcept C154945302 @default.
- W4365440892 hasConcept C159694833 @default.
- W4365440892 hasConcept C173608175 @default.
- W4365440892 hasConcept C2780513914 @default.
- W4365440892 hasConcept C33923547 @default.
- W4365440892 hasConcept C41008148 @default.
- W4365440892 hasConcept C48044578 @default.
- W4365440892 hasConcept C68339613 @default.
- W4365440892 hasConcept C74912251 @default.
- W4365440892 hasConcept C77088390 @default.
- W4365440892 hasConceptScore W4365440892C101738243 @default.
- W4365440892 hasConceptScore W4365440892C108583219 @default.
- W4365440892 hasConceptScore W4365440892C111919701 @default.
- W4365440892 hasConceptScore W4365440892C11413529 @default.
- W4365440892 hasConceptScore W4365440892C126255220 @default.
- W4365440892 hasConceptScore W4365440892C134306372 @default.
- W4365440892 hasConceptScore W4365440892C135252773 @default.
- W4365440892 hasConceptScore W4365440892C147060835 @default.
- W4365440892 hasConceptScore W4365440892C149635348 @default.
- W4365440892 hasConceptScore W4365440892C154945302 @default.
- W4365440892 hasConceptScore W4365440892C159694833 @default.
- W4365440892 hasConceptScore W4365440892C173608175 @default.
- W4365440892 hasConceptScore W4365440892C2780513914 @default.
- W4365440892 hasConceptScore W4365440892C33923547 @default.
- W4365440892 hasConceptScore W4365440892C41008148 @default.
- W4365440892 hasConceptScore W4365440892C48044578 @default.
- W4365440892 hasConceptScore W4365440892C68339613 @default.
- W4365440892 hasConceptScore W4365440892C74912251 @default.
- W4365440892 hasConceptScore W4365440892C77088390 @default.
- W4365440892 hasLocation W43654408921 @default.
- W4365440892 hasOpenAccess W4365440892 @default.
- W4365440892 hasPrimaryLocation W43654408921 @default.
- W4365440892 hasRelatedWork W1531780705 @default.
- W4365440892 hasRelatedWork W1573331674 @default.
- W4365440892 hasRelatedWork W1967627035 @default.
- W4365440892 hasRelatedWork W2131083599 @default.
- W4365440892 hasRelatedWork W2134266179 @default.
- W4365440892 hasRelatedWork W2370911386 @default.
- W4365440892 hasRelatedWork W3207233976 @default.
- W4365440892 hasRelatedWork W4226385918 @default.
- W4365440892 hasRelatedWork W4239886135 @default.
- W4365440892 hasRelatedWork W4286901967 @default.
- W4365440892 isParatext "false" @default.
- W4365440892 isRetracted "false" @default.
- W4365440892 workType "article" @default.