Matches in SemOpenAlex for { <https://semopenalex.org/work/W4287691839> ?p ?o ?g. }
Showing items 1 to 83 of
83
with 100 items per page.
- W4287691839 abstract "We consider the variational reconstruction framework for inverse problems and propose to learn a data-adaptive input-convex neural network (ICNN) as the regularization functional. The ICNN-based convex regularizer is trained adversarially to discern ground-truth images from unregularized reconstructions. Convexity of the regularizer is desirable since (i) one can establish analytical convergence guarantees for the corresponding variational reconstruction problem and (ii) devise efficient and provable algorithms for reconstruction. In particular, we show that the optimal solution to the variational problem converges to the ground-truth if the penalty parameter decays sub-linearly with respect to the norm of the noise. Further, we prove the existence of a sub-gradient-based algorithm that leads to a monotonically decreasing error in the parameter space with iterations. To demonstrate the performance of our approach for solving inverse problems, we consider the tasks of deblurring natural images and reconstructing images in computed tomography (CT), and show that the proposed convex regularizer is at least competitive with and sometimes superior to state-of-the-art data-driven techniques for inverse problems." @default.
- W4287691839 created "2022-07-26" @default.
- W4287691839 creator A5033880300 @default.
- W4287691839 creator A5035377071 @default.
- W4287691839 creator A5058871756 @default.
- W4287691839 creator A5064245326 @default.
- W4287691839 creator A5078374818 @default.
- W4287691839 creator A5087214686 @default.
- W4287691839 date "2020-08-06" @default.
- W4287691839 modified "2023-09-26" @default.
- W4287691839 title "Learned convex regularizers for inverse problems" @default.
- W4287691839 doi "https://doi.org/10.48550/arxiv.2008.02839" @default.
- W4287691839 hasPublicationYear "2020" @default.
- W4287691839 type Work @default.
- W4287691839 citedByCount "0" @default.
- W4287691839 crossrefType "posted-content" @default.
- W4287691839 hasAuthorship W4287691839A5033880300 @default.
- W4287691839 hasAuthorship W4287691839A5035377071 @default.
- W4287691839 hasAuthorship W4287691839A5058871756 @default.
- W4287691839 hasAuthorship W4287691839A5064245326 @default.
- W4287691839 hasAuthorship W4287691839A5078374818 @default.
- W4287691839 hasAuthorship W4287691839A5087214686 @default.
- W4287691839 hasBestOaLocation W42876918391 @default.
- W4287691839 hasConcept C106159729 @default.
- W4287691839 hasConcept C106430172 @default.
- W4287691839 hasConcept C112680207 @default.
- W4287691839 hasConcept C11413529 @default.
- W4287691839 hasConcept C115961682 @default.
- W4287691839 hasConcept C126255220 @default.
- W4287691839 hasConcept C134306372 @default.
- W4287691839 hasConcept C135252773 @default.
- W4287691839 hasConcept C145446738 @default.
- W4287691839 hasConcept C154945302 @default.
- W4287691839 hasConcept C162324750 @default.
- W4287691839 hasConcept C17744445 @default.
- W4287691839 hasConcept C191795146 @default.
- W4287691839 hasConcept C199539241 @default.
- W4287691839 hasConcept C2524010 @default.
- W4287691839 hasConcept C2776135515 @default.
- W4287691839 hasConcept C2777693668 @default.
- W4287691839 hasConcept C28826006 @default.
- W4287691839 hasConcept C33923547 @default.
- W4287691839 hasConcept C41008148 @default.
- W4287691839 hasConcept C72134830 @default.
- W4287691839 hasConcept C9417928 @default.
- W4287691839 hasConceptScore W4287691839C106159729 @default.
- W4287691839 hasConceptScore W4287691839C106430172 @default.
- W4287691839 hasConceptScore W4287691839C112680207 @default.
- W4287691839 hasConceptScore W4287691839C11413529 @default.
- W4287691839 hasConceptScore W4287691839C115961682 @default.
- W4287691839 hasConceptScore W4287691839C126255220 @default.
- W4287691839 hasConceptScore W4287691839C134306372 @default.
- W4287691839 hasConceptScore W4287691839C135252773 @default.
- W4287691839 hasConceptScore W4287691839C145446738 @default.
- W4287691839 hasConceptScore W4287691839C154945302 @default.
- W4287691839 hasConceptScore W4287691839C162324750 @default.
- W4287691839 hasConceptScore W4287691839C17744445 @default.
- W4287691839 hasConceptScore W4287691839C191795146 @default.
- W4287691839 hasConceptScore W4287691839C199539241 @default.
- W4287691839 hasConceptScore W4287691839C2524010 @default.
- W4287691839 hasConceptScore W4287691839C2776135515 @default.
- W4287691839 hasConceptScore W4287691839C2777693668 @default.
- W4287691839 hasConceptScore W4287691839C28826006 @default.
- W4287691839 hasConceptScore W4287691839C33923547 @default.
- W4287691839 hasConceptScore W4287691839C41008148 @default.
- W4287691839 hasConceptScore W4287691839C72134830 @default.
- W4287691839 hasConceptScore W4287691839C9417928 @default.
- W4287691839 hasLocation W42876918391 @default.
- W4287691839 hasOpenAccess W4287691839 @default.
- W4287691839 hasPrimaryLocation W42876918391 @default.
- W4287691839 hasRelatedWork W1214677504 @default.
- W4287691839 hasRelatedWork W2209076415 @default.
- W4287691839 hasRelatedWork W2370756284 @default.
- W4287691839 hasRelatedWork W3048327053 @default.
- W4287691839 hasRelatedWork W3105299938 @default.
- W4287691839 hasRelatedWork W3212385543 @default.
- W4287691839 hasRelatedWork W4225986009 @default.
- W4287691839 hasRelatedWork W4287691839 @default.
- W4287691839 hasRelatedWork W4293469310 @default.
- W4287691839 hasRelatedWork W45494237 @default.
- W4287691839 isParatext "false" @default.
- W4287691839 isRetracted "false" @default.
- W4287691839 workType "article" @default.