Matches in SemOpenAlex for { <https://semopenalex.org/work/W4225549368> ?p ?o ?g. }
Showing items 1 to 72 of
72
with 100 items per page.
- W4225549368 abstract "Generative networks such as normalizing flows can serve as a learning-based prior to augment inverse problems to achieve high-quality results. However, the latent space vector may not remain a typical sample from the desired high-dimensional standard Gaussian distribution when traversing the latent space during an inversion. As a result, it can be challenging to attain a high-fidelity solution, particularly in the presence of noise and inaccurate physics-based models. To address this issue, we propose to re-parameterize and Gaussianize the latent vector using novel differentiable data-dependent layers wherein custom operators are defined by solving optimization problems. These proposed layers enforce an inversion to find a feasible solution within a Gaussian typical set of the latent space. We tested and validated our technique on an image deblurring task and eikonal tomography -- a PDE-constrained inverse problem and achieved high-fidelity results." @default.
- W4225549368 created "2022-05-05" @default.
- W4225549368 creator A5016906708 @default.
- W4225549368 creator A5088229467 @default.
- W4225549368 date "2021-12-07" @default.
- W4225549368 modified "2023-09-29" @default.
- W4225549368 title "Traversing within the Gaussian Typical Set: Differentiable Gaussianization Layers for Inverse Problems Augmented by Normalizing Flows" @default.
- W4225549368 hasPublicationYear "2021" @default.
- W4225549368 type Work @default.
- W4225549368 citedByCount "0" @default.
- W4225549368 crossrefType "posted-content" @default.
- W4225549368 hasAuthorship W4225549368A5016906708 @default.
- W4225549368 hasAuthorship W4225549368A5088229467 @default.
- W4225549368 hasBestOaLocation W42255493681 @default.
- W4225549368 hasConcept C106430172 @default.
- W4225549368 hasConcept C107673813 @default.
- W4225549368 hasConcept C11413529 @default.
- W4225549368 hasConcept C115961682 @default.
- W4225549368 hasConcept C121332964 @default.
- W4225549368 hasConcept C126255220 @default.
- W4225549368 hasConcept C13280743 @default.
- W4225549368 hasConcept C134306372 @default.
- W4225549368 hasConcept C135252773 @default.
- W4225549368 hasConcept C154945302 @default.
- W4225549368 hasConcept C163716315 @default.
- W4225549368 hasConcept C176809094 @default.
- W4225549368 hasConcept C177769412 @default.
- W4225549368 hasConcept C202615002 @default.
- W4225549368 hasConcept C205649164 @default.
- W4225549368 hasConcept C2777693668 @default.
- W4225549368 hasConcept C28826006 @default.
- W4225549368 hasConcept C33923547 @default.
- W4225549368 hasConcept C41008148 @default.
- W4225549368 hasConcept C62520636 @default.
- W4225549368 hasConcept C9417928 @default.
- W4225549368 hasConceptScore W4225549368C106430172 @default.
- W4225549368 hasConceptScore W4225549368C107673813 @default.
- W4225549368 hasConceptScore W4225549368C11413529 @default.
- W4225549368 hasConceptScore W4225549368C115961682 @default.
- W4225549368 hasConceptScore W4225549368C121332964 @default.
- W4225549368 hasConceptScore W4225549368C126255220 @default.
- W4225549368 hasConceptScore W4225549368C13280743 @default.
- W4225549368 hasConceptScore W4225549368C134306372 @default.
- W4225549368 hasConceptScore W4225549368C135252773 @default.
- W4225549368 hasConceptScore W4225549368C154945302 @default.
- W4225549368 hasConceptScore W4225549368C163716315 @default.
- W4225549368 hasConceptScore W4225549368C176809094 @default.
- W4225549368 hasConceptScore W4225549368C177769412 @default.
- W4225549368 hasConceptScore W4225549368C202615002 @default.
- W4225549368 hasConceptScore W4225549368C205649164 @default.
- W4225549368 hasConceptScore W4225549368C2777693668 @default.
- W4225549368 hasConceptScore W4225549368C28826006 @default.
- W4225549368 hasConceptScore W4225549368C33923547 @default.
- W4225549368 hasConceptScore W4225549368C41008148 @default.
- W4225549368 hasConceptScore W4225549368C62520636 @default.
- W4225549368 hasConceptScore W4225549368C9417928 @default.
- W4225549368 hasLocation W42255493681 @default.
- W4225549368 hasOpenAccess W4225549368 @default.
- W4225549368 hasPrimaryLocation W42255493681 @default.
- W4225549368 hasRelatedWork W12539047 @default.
- W4225549368 hasRelatedWork W1268192 @default.
- W4225549368 hasRelatedWork W15220964 @default.
- W4225549368 hasRelatedWork W15382557 @default.
- W4225549368 hasRelatedWork W15892214 @default.
- W4225549368 hasRelatedWork W3765441 @default.
- W4225549368 hasRelatedWork W4420722 @default.
- W4225549368 hasRelatedWork W5309060 @default.
- W4225549368 hasRelatedWork W8018568 @default.
- W4225549368 hasRelatedWork W8351625 @default.
- W4225549368 isParatext "false" @default.
- W4225549368 isRetracted "false" @default.
- W4225549368 workType "article" @default.