Matches in SemOpenAlex for { <https://semopenalex.org/work/W4386841613> ?p ?o ?g. }
Showing items 1 to 65 of
65
with 100 items per page.
- W4386841613 abstract "We consider the problem of signal estimation in a generalized linear model (GLM). GLMs include many canonical problems in statistical estimation, such as linear regression, phase retrieval, and 1-bit compressed sensing. Recent work has precisely characterized the asymptotic minimum mean-squared error (MMSE) for GLMs with i.i.d. Gaussian sensing matrices. However, in many models there is a significant gap between the MMSE and the performance of the best known feasible estimators. In this work, we address this issue by considering GLMs defined via spatially coupled sensing matrices. We propose an efficient approximate message passing (AMP) algorithm for estimation and prove that with a simple choice of spatially coupled design, the MSE of a carefully tuned AMP estimator approaches the asymptotic MMSE in the high-dimensional limit. To prove the result, we first rigorously characterize the asymptotic performance of AMP for a GLM with a generic spatially coupled design. This characterization is in terms of a deterministic recursion (`state evolution') that depends on the parameters defining the spatial coupling. Then, using a simple spatially coupled design and judicious choice of functions defining the AMP, we analyze the fixed points of the resulting state evolution and show that it achieves the asymptotic MMSE. Numerical results for phase retrieval and rectified linear regression show that spatially coupled designs can yield substantially lower MSE than i.i.d. Gaussian designs at finite dimensions when used with AMP algorithms." @default.
- W4386841613 created "2023-09-19" @default.
- W4386841613 creator A5057708112 @default.
- W4386841613 creator A5081409970 @default.
- W4386841613 creator A5092809254 @default.
- W4386841613 date "2023-09-15" @default.
- W4386841613 modified "2023-09-27" @default.
- W4386841613 title "Bayes-Optimal Estimation in Generalized Linear Models via Spatial Coupling" @default.
- W4386841613 doi "https://doi.org/10.48550/arxiv.2309.08404" @default.
- W4386841613 hasPublicationYear "2023" @default.
- W4386841613 type Work @default.
- W4386841613 citedByCount "0" @default.
- W4386841613 crossrefType "posted-content" @default.
- W4386841613 hasAuthorship W4386841613A5057708112 @default.
- W4386841613 hasAuthorship W4386841613A5081409970 @default.
- W4386841613 hasAuthorship W4386841613A5092809254 @default.
- W4386841613 hasBestOaLocation W43868416131 @default.
- W4386841613 hasConcept C105795698 @default.
- W4386841613 hasConcept C11413529 @default.
- W4386841613 hasConcept C121332964 @default.
- W4386841613 hasConcept C126255220 @default.
- W4386841613 hasConcept C139945424 @default.
- W4386841613 hasConcept C163175372 @default.
- W4386841613 hasConcept C163716315 @default.
- W4386841613 hasConcept C168773036 @default.
- W4386841613 hasConcept C185429906 @default.
- W4386841613 hasConcept C28826006 @default.
- W4386841613 hasConcept C33923547 @default.
- W4386841613 hasConcept C41008148 @default.
- W4386841613 hasConcept C41587187 @default.
- W4386841613 hasConcept C48921125 @default.
- W4386841613 hasConcept C62520636 @default.
- W4386841613 hasConcept C90652560 @default.
- W4386841613 hasConceptScore W4386841613C105795698 @default.
- W4386841613 hasConceptScore W4386841613C11413529 @default.
- W4386841613 hasConceptScore W4386841613C121332964 @default.
- W4386841613 hasConceptScore W4386841613C126255220 @default.
- W4386841613 hasConceptScore W4386841613C139945424 @default.
- W4386841613 hasConceptScore W4386841613C163175372 @default.
- W4386841613 hasConceptScore W4386841613C163716315 @default.
- W4386841613 hasConceptScore W4386841613C168773036 @default.
- W4386841613 hasConceptScore W4386841613C185429906 @default.
- W4386841613 hasConceptScore W4386841613C28826006 @default.
- W4386841613 hasConceptScore W4386841613C33923547 @default.
- W4386841613 hasConceptScore W4386841613C41008148 @default.
- W4386841613 hasConceptScore W4386841613C41587187 @default.
- W4386841613 hasConceptScore W4386841613C48921125 @default.
- W4386841613 hasConceptScore W4386841613C62520636 @default.
- W4386841613 hasConceptScore W4386841613C90652560 @default.
- W4386841613 hasLocation W43868416131 @default.
- W4386841613 hasOpenAccess W4386841613 @default.
- W4386841613 hasPrimaryLocation W43868416131 @default.
- W4386841613 hasRelatedWork W1965097788 @default.
- W4386841613 hasRelatedWork W1996549107 @default.
- W4386841613 hasRelatedWork W2001168328 @default.
- W4386841613 hasRelatedWork W2136981816 @default.
- W4386841613 hasRelatedWork W2255368515 @default.
- W4386841613 hasRelatedWork W2375834578 @default.
- W4386841613 hasRelatedWork W2389250926 @default.
- W4386841613 hasRelatedWork W4234584239 @default.
- W4386841613 hasRelatedWork W4296533956 @default.
- W4386841613 hasRelatedWork W2186209607 @default.
- W4386841613 isParatext "false" @default.
- W4386841613 isRetracted "false" @default.
- W4386841613 workType "article" @default.