Matches in SemOpenAlex for { <https://semopenalex.org/work/W2389866904> ?p ?o ?g. }
- W2389866904 abstract "We solve the inverse problem of deblurring a pixelized image of Jupiter using regularized deconvolution and by sample-based Bayesian inference. By efficiently sampling the marginal posterior distribution for hyperparameters, then the full conditional for the deblurred image, we find that we can evaluate the posterior mean faster than regularized inversion, when selection of the regularizing parameter is considered. To our knowledge, this is the first demonstration of sampling and inference that takes less compute time than regularized inversion in an inverse problems. Comparison to random-walk Metropolis-Hastings and block Gibbs MCMC shows that marginal then conditional sampling also outperforms these more common sampling algorithms, having better scaling with problem size. When problem-specific computations are feasible the asymptotic cost of an independent sample is one linear solve, implying that sample-based Bayesian inference may be performed directly over function spaces, when that limit exists." @default.
- W2389866904 created "2016-06-24" @default.
- W2389866904 creator A5026274660 @default.
- W2389866904 creator A5073882804 @default.
- W2389866904 date "2015-07-06" @default.
- W2389866904 modified "2023-09-27" @default.
- W2389866904 title "Fast sampling in a linear-Gaussian inverse problem" @default.
- W2389866904 cites W1523113578 @default.
- W2389866904 cites W1554663368 @default.
- W2389866904 cites W1579788182 @default.
- W2389866904 cites W1968735445 @default.
- W2389866904 cites W1972429397 @default.
- W2389866904 cites W1979926788 @default.
- W2389866904 cites W1987805535 @default.
- W2389866904 cites W1990058630 @default.
- W2389866904 cites W1997628954 @default.
- W2389866904 cites W2006681603 @default.
- W2389866904 cites W2030597423 @default.
- W2389866904 cites W2033242948 @default.
- W2389866904 cites W2041717489 @default.
- W2389866904 cites W2048971218 @default.
- W2389866904 cites W2069993596 @default.
- W2389866904 cites W2085803676 @default.
- W2389866904 cites W2101998432 @default.
- W2389866904 cites W2114424556 @default.
- W2389866904 cites W2134539556 @default.
- W2389866904 cites W2138408045 @default.
- W2389866904 cites W2140064412 @default.
- W2389866904 cites W2156679002 @default.
- W2389866904 cites W2232386237 @default.
- W2389866904 cites W2341059552 @default.
- W2389866904 cites W255181480 @default.
- W2389866904 cites W2964297483 @default.
- W2389866904 cites W3098198761 @default.
- W2389866904 cites W116472225 @default.
- W2389866904 hasPublicationYear "2015" @default.
- W2389866904 type Work @default.
- W2389866904 sameAs 2389866904 @default.
- W2389866904 citedByCount "0" @default.
- W2389866904 crossrefType "posted-content" @default.
- W2389866904 hasAuthorship W2389866904A5026274660 @default.
- W2389866904 hasAuthorship W2389866904A5073882804 @default.
- W2389866904 hasConcept C105795698 @default.
- W2389866904 hasConcept C106131492 @default.
- W2389866904 hasConcept C106430172 @default.
- W2389866904 hasConcept C107673813 @default.
- W2389866904 hasConcept C111350023 @default.
- W2389866904 hasConcept C11413529 @default.
- W2389866904 hasConcept C115961682 @default.
- W2389866904 hasConcept C126255220 @default.
- W2389866904 hasConcept C134306372 @default.
- W2389866904 hasConcept C135252773 @default.
- W2389866904 hasConcept C140779682 @default.
- W2389866904 hasConcept C154945302 @default.
- W2389866904 hasConcept C158424031 @default.
- W2389866904 hasConcept C160234255 @default.
- W2389866904 hasConcept C174576160 @default.
- W2389866904 hasConcept C177769412 @default.
- W2389866904 hasConcept C2776214188 @default.
- W2389866904 hasConcept C2777693668 @default.
- W2389866904 hasConcept C31972630 @default.
- W2389866904 hasConcept C33923547 @default.
- W2389866904 hasConcept C41008148 @default.
- W2389866904 hasConcept C57830394 @default.
- W2389866904 hasConcept C8642999 @default.
- W2389866904 hasConcept C9417928 @default.
- W2389866904 hasConceptScore W2389866904C105795698 @default.
- W2389866904 hasConceptScore W2389866904C106131492 @default.
- W2389866904 hasConceptScore W2389866904C106430172 @default.
- W2389866904 hasConceptScore W2389866904C107673813 @default.
- W2389866904 hasConceptScore W2389866904C111350023 @default.
- W2389866904 hasConceptScore W2389866904C11413529 @default.
- W2389866904 hasConceptScore W2389866904C115961682 @default.
- W2389866904 hasConceptScore W2389866904C126255220 @default.
- W2389866904 hasConceptScore W2389866904C134306372 @default.
- W2389866904 hasConceptScore W2389866904C135252773 @default.
- W2389866904 hasConceptScore W2389866904C140779682 @default.
- W2389866904 hasConceptScore W2389866904C154945302 @default.
- W2389866904 hasConceptScore W2389866904C158424031 @default.
- W2389866904 hasConceptScore W2389866904C160234255 @default.
- W2389866904 hasConceptScore W2389866904C174576160 @default.
- W2389866904 hasConceptScore W2389866904C177769412 @default.
- W2389866904 hasConceptScore W2389866904C2776214188 @default.
- W2389866904 hasConceptScore W2389866904C2777693668 @default.
- W2389866904 hasConceptScore W2389866904C31972630 @default.
- W2389866904 hasConceptScore W2389866904C33923547 @default.
- W2389866904 hasConceptScore W2389866904C41008148 @default.
- W2389866904 hasConceptScore W2389866904C57830394 @default.
- W2389866904 hasConceptScore W2389866904C8642999 @default.
- W2389866904 hasConceptScore W2389866904C9417928 @default.
- W2389866904 hasLocation W23898669041 @default.
- W2389866904 hasOpenAccess W2389866904 @default.
- W2389866904 hasPrimaryLocation W23898669041 @default.
- W2389866904 hasRelatedWork W1971758257 @default.
- W2389866904 hasRelatedWork W2062943478 @default.
- W2389866904 hasRelatedWork W2127798732 @default.
- W2389866904 hasRelatedWork W2131242330 @default.
- W2389866904 hasRelatedWork W2157596407 @default.
- W2389866904 hasRelatedWork W2201133737 @default.
- W2389866904 hasRelatedWork W2281180419 @default.