Matches in SemOpenAlex for { <https://semopenalex.org/work/W3107979457> ?p ?o ?g. }
- W3107979457 endingPage "798" @default.
- W3107979457 startingPage "777" @default.
- W3107979457 abstract "This article studies a high-dimensional inference problem involving the matrix tensor product of random matrices. This problem generalizes a number of contemporary data science problems including the spiked matrix models used in sparse principal component analysis and covariance estimation and the stochastic block model used in network analysis. The main results are single-letter formulas (i.e., analytical expressions that can be approximated numerically) for the mutual information and the minimum mean-squared error (MMSE) in the Bayes optimal setting where the distributions of all random quantities are known. We provide non-asymptotic bounds and show that our formulas describe exactly the leading order terms in the mutual information and MMSE in the high-dimensional regime where the number of rows n and number of columns d scale with d = O(n <sup xmlns:mml=http://www.w3.org/1998/Math/MathML xmlns:xlink=http://www.w3.org/1999/xlink>α</sup> ) for some α <; 1/20. On the technical side, this article introduces some new techniques for the analysis of high-dimensional matrix-valued signals. Specific contributions include a novel extension of the adaptive interpolation method that uses order-preserving positive semidefinite interpolation paths, and a variance inequality between the overlap and the free energy that is based on continuous-time I-MMSE relations." @default.
- W3107979457 created "2020-12-07" @default.
- W3107979457 creator A5084396713 @default.
- W3107979457 date "2020-11-01" @default.
- W3107979457 modified "2023-10-16" @default.
- W3107979457 title "Information-Theoretic Limits for the Matrix Tensor Product" @default.
- W3107979457 cites W1520752838 @default.
- W3107979457 cites W1539851785 @default.
- W3107979457 cites W1655742870 @default.
- W3107979457 cites W1922029667 @default.
- W3107979457 cites W1975900269 @default.
- W3107979457 cites W2004531067 @default.
- W3107979457 cites W2015818766 @default.
- W3107979457 cites W205960364 @default.
- W3107979457 cites W2066459155 @default.
- W3107979457 cites W2097714737 @default.
- W3107979457 cites W2097854052 @default.
- W3107979457 cites W2111616148 @default.
- W3107979457 cites W2129462326 @default.
- W3107979457 cites W2136464164 @default.
- W3107979457 cites W2153463205 @default.
- W3107979457 cites W2157638198 @default.
- W3107979457 cites W2161410247 @default.
- W3107979457 cites W2167455364 @default.
- W3107979457 cites W2167783913 @default.
- W3107979457 cites W2170833470 @default.
- W3107979457 cites W2174000564 @default.
- W3107979457 cites W2332917886 @default.
- W3107979457 cites W2483978192 @default.
- W3107979457 cites W2566505556 @default.
- W3107979457 cites W2588219153 @default.
- W3107979457 cites W2742470390 @default.
- W3107979457 cites W2793533891 @default.
- W3107979457 cites W2886879928 @default.
- W3107979457 cites W2909365420 @default.
- W3107979457 cites W2918745211 @default.
- W3107979457 cites W2963279235 @default.
- W3107979457 cites W2963639053 @default.
- W3107979457 cites W2963765569 @default.
- W3107979457 cites W2964227601 @default.
- W3107979457 cites W2964282092 @default.
- W3107979457 cites W2975352502 @default.
- W3107979457 cites W2992466427 @default.
- W3107979457 cites W3042689868 @default.
- W3107979457 cites W3080456940 @default.
- W3107979457 cites W3085023861 @default.
- W3107979457 cites W3099655991 @default.
- W3107979457 cites W3100129515 @default.
- W3107979457 cites W3101975788 @default.
- W3107979457 cites W3102974460 @default.
- W3107979457 cites W3103647971 @default.
- W3107979457 cites W3104469760 @default.
- W3107979457 cites W3104898123 @default.
- W3107979457 cites W3105573210 @default.
- W3107979457 cites W3105600170 @default.
- W3107979457 cites W3106533591 @default.
- W3107979457 cites W4245577611 @default.
- W3107979457 cites W4249667877 @default.
- W3107979457 doi "https://doi.org/10.1109/jsait.2020.3040598" @default.
- W3107979457 hasPublicationYear "2020" @default.
- W3107979457 type Work @default.
- W3107979457 sameAs 3107979457 @default.
- W3107979457 citedByCount "13" @default.
- W3107979457 countsByYear W31079794572020 @default.
- W3107979457 countsByYear W31079794572021 @default.
- W3107979457 countsByYear W31079794572022 @default.
- W3107979457 countsByYear W31079794572023 @default.
- W3107979457 crossrefType "journal-article" @default.
- W3107979457 hasAuthorship W3107979457A5084396713 @default.
- W3107979457 hasBestOaLocation W31079794571 @default.
- W3107979457 hasConcept C104114177 @default.
- W3107979457 hasConcept C105795698 @default.
- W3107979457 hasConcept C106487976 @default.
- W3107979457 hasConcept C11413529 @default.
- W3107979457 hasConcept C121332964 @default.
- W3107979457 hasConcept C126255220 @default.
- W3107979457 hasConcept C137800194 @default.
- W3107979457 hasConcept C154945302 @default.
- W3107979457 hasConcept C155281189 @default.
- W3107979457 hasConcept C158693339 @default.
- W3107979457 hasConcept C159985019 @default.
- W3107979457 hasConcept C178650346 @default.
- W3107979457 hasConcept C185142706 @default.
- W3107979457 hasConcept C192562407 @default.
- W3107979457 hasConcept C202444582 @default.
- W3107979457 hasConcept C28826006 @default.
- W3107979457 hasConcept C33923547 @default.
- W3107979457 hasConcept C41008148 @default.
- W3107979457 hasConcept C51255310 @default.
- W3107979457 hasConcept C62520636 @default.
- W3107979457 hasConcept C64812099 @default.
- W3107979457 hasConceptScore W3107979457C104114177 @default.
- W3107979457 hasConceptScore W3107979457C105795698 @default.
- W3107979457 hasConceptScore W3107979457C106487976 @default.
- W3107979457 hasConceptScore W3107979457C11413529 @default.
- W3107979457 hasConceptScore W3107979457C121332964 @default.
- W3107979457 hasConceptScore W3107979457C126255220 @default.
- W3107979457 hasConceptScore W3107979457C137800194 @default.