FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W2017304912> ?p ?o ?g. }

• W2017304912 endingPage "3018" @default.
• W2017304912 startingPage "3002" @default.
• W2017304912 abstract "The truncated singular value decomposition of the measurement matrix is the optimal solution to the representation problem of how to best approximate a noisy measurement matrix using a low-rank matrix. Here, we consider the (unobservable) denoising problem of how to best approximate a low-rank signal matrix buried in noise by optimal (re)weighting of the singular vectors of the measurement matrix. We exploit recent results from random matrix theory to exactly characterize the large matrix limit of the optimal weighting coefficients and show that they can be computed directly from data for a large class of noise models that includes the independent identically distributed Gaussian noise case. Our analysis brings into sharp focus the shrinkage-and-thresholding form of the optimal weights, the nonconvex nature of the associated shrinkage function (on the singular values), and explains why matrix regularization via singular value thresholding with convex penalty functions (such as the nuclear norm) will always be suboptimal. We validate our theoretical predictions with numerical simulations, develop an implementable algorithm (OptShrink) that realizes the predicted performance gains and show how our methods can be used to improve estimation in the setting where the measured matrix has missing entries." @default.
• W2017304912 created "2016-06-24" @default.
• W2017304912 creator A5071117473 @default.
• W2017304912 date "2014-05-01" @default.
• W2017304912 modified "2023-10-16" @default.
• W2017304912 title "OptShrink: An Algorithm for Improved Low-Rank Signal Matrix Denoising by Optimal, Data-Driven Singular Value Shrinkage" @default.
• W2017304912 cites W1488435683 @default.
• W2017304912 cites W1520752838 @default.
• W2017304912 cites W1586554030 @default.
• W2017304912 cites W1599867596 @default.
• W2017304912 cites W1857410117 @default.
• W2017304912 cites W1956647075 @default.
• W2017304912 cites W1960920821 @default.
• W2017304912 cites W1969015668 @default.
• W2017304912 cites W1970576574 @default.
• W2017304912 cites W1975395389 @default.
• W2017304912 cites W1975900269 @default.
• W2017304912 cites W1979356326 @default.
• W2017304912 cites W1979915596 @default.
• W2017304912 cites W1994938797 @default.
• W2017304912 cites W2000157792 @default.
• W2017304912 cites W2004026774 @default.
• W2017304912 cites W2005553562 @default.
• W2017304912 cites W2011892826 @default.
• W2017304912 cites W2014092582 @default.
• W2017304912 cites W2014259951 @default.
• W2017304912 cites W2015583498 @default.
• W2017304912 cites W2031213242 @default.
• W2017304912 cites W2032921855 @default.
• W2017304912 cites W2047071281 @default.
• W2017304912 cites W2058512713 @default.
• W2017304912 cites W2060581589 @default.
• W2017304912 cites W2064980127 @default.
• W2017304912 cites W2066459155 @default.
• W2017304912 cites W2070094080 @default.
• W2017304912 cites W2074961722 @default.
• W2017304912 cites W2081940622 @default.
• W2017304912 cites W2083138589 @default.
• W2017304912 cites W2084745075 @default.
• W2017304912 cites W2091352038 @default.
• W2017304912 cites W2097714737 @default.
• W2017304912 cites W2098502158 @default.
• W2017304912 cites W2101513535 @default.
• W2017304912 cites W2103437658 @default.
• W2017304912 cites W2103972604 @default.
• W2017304912 cites W2106084579 @default.
• W2017304912 cites W2109378630 @default.
• W2017304912 cites W2117377454 @default.
• W2017304912 cites W2119367754 @default.
• W2017304912 cites W2123226256 @default.
• W2017304912 cites W2126625374 @default.
• W2017304912 cites W2130499908 @default.
• W2017304912 cites W2132657058 @default.
• W2017304912 cites W2134332047 @default.
• W2017304912 cites W2145962650 @default.
• W2017304912 cites W2146610201 @default.
• W2017304912 cites W2146756121 @default.
• W2017304912 cites W2149538437 @default.
• W2017304912 cites W2152687999 @default.
• W2017304912 cites W2155421090 @default.
• W2017304912 cites W2158589846 @default.
• W2017304912 cites W2163885535 @default.
• W2017304912 cites W2544357824 @default.
• W2017304912 cites W2554839354 @default.
• W2017304912 cites W2557168633 @default.
• W2017304912 cites W2611328865 @default.
• W2017304912 cites W2949734021 @default.
• W2017304912 cites W2962769133 @default.
• W2017304912 cites W2963092731 @default.
• W2017304912 cites W2963649004 @default.
• W2017304912 cites W3104624268 @default.
• W2017304912 cites W3105388035 @default.
• W2017304912 cites W3105772645 @default.
• W2017304912 cites W3106326876 @default.
• W2017304912 cites W4245577611 @default.
• W2017304912 cites W602904462 @default.
• W2017304912 doi "https://doi.org/10.1109/tit.2014.2311661" @default.
• W2017304912 hasPublicationYear "2014" @default.
• W2017304912 type Work @default.
• W2017304912 sameAs 2017304912 @default.
• W2017304912 citedByCount "104" @default.
• W2017304912 countsByYear W20173049122013 @default.
• W2017304912 countsByYear W20173049122014 @default.
• W2017304912 countsByYear W20173049122015 @default.
• W2017304912 countsByYear W20173049122016 @default.
• W2017304912 countsByYear W20173049122017 @default.
• W2017304912 countsByYear W20173049122018 @default.
• W2017304912 countsByYear W20173049122019 @default.
• W2017304912 countsByYear W20173049122020 @default.
• W2017304912 countsByYear W20173049122021 @default.
• W2017304912 countsByYear W20173049122022 @default.
• W2017304912 countsByYear W20173049122023 @default.
• W2017304912 crossrefType "journal-article" @default.
• W2017304912 hasAuthorship W2017304912A5071117473 @default.
• W2017304912 hasBestOaLocation W20173049122 @default.
• W2017304912 hasConcept C106487976 @default.
• W2017304912 hasConcept C109282560 @default.
• W2017304912 hasConcept C11413529 @default.

• next