FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W3100205528> ?p ?o ?g. }

• W3100205528 endingPage "4470" @default.
• W3100205528 startingPage "4449" @default.
• W3100205528 abstract "We consider two-class linear classification in a high-dimensional, small-sample-size setting. Only a small fraction of the features are useful, these being unknown to us, and each useful feature contributes weakly to the classification decision. This was called the rare/weak (RW) model in our previous study ( Donoho, D. & Jin, J. 2008 Proc. Natl Acad. Sci. USA 105 , 14 790–14 795). We select features by thresholding feature Z -scores. The threshold is set by higher criticism (HC). For 1≤ i ≤ N , let π i denote the p -value associated with the i th Z -score and π ( i ) denote the i th order statistic of the collection of p -values. The HC threshold (HCT) is the order statistic of the Z -score corresponding to index i maximizing . The ideal threshold optimizes the classification error. In that previous study, we showed that HCT was numerically close to the ideal threshold. We formalize an asymptotic framework for studying the RW model, considering a sequence of problems with increasingly many features and relatively fewer observations. We show that, along this sequence, the limiting performance of ideal HCT is essentially just as good as the limiting performance of ideal thresholding. Our results describe two-dimensional phase space , a two-dimensional diagram with coordinates quantifying ‘rare’ and ‘weak’ in the RW model. The phase space can be partitioned into two regions—one where ideal threshold classification is successful, and one where the features are so weak and so rare that it must fail. Surprisingly, the regions where ideal HCT succeeds and fails make exactly the same partition of the phase diagram. Other threshold methods, such as false (feature) discovery rate (FDR) threshold selection, are successful in a substantially smaller region of the phase space than either HCT or ideal thresholding. The FDR and local FDR of the ideal and HC threshold selectors have surprising phase diagrams, which are also described. Results showing the asymptotic equivalence of HCT with ideal HCT can be found in a forthcoming paper ( Donoho, D. & Jin, J. In preparation )." @default.
• W3100205528 created "2020-11-23" @default.
• W3100205528 creator A5065355421 @default.
• W3100205528 creator A5083038132 @default.
• W3100205528 date "2009-11-13" @default.
• W3100205528 modified "2023-10-02" @default.
• W3100205528 title "Feature selection by higher criticism thresholding achieves the optimal phase diagram" @default.
• W3100205528 cites W1584471057 @default.
• W3100205528 cites W1587510588 @default.
• W3100205528 cites W1824047490 @default.
• W3100205528 cites W1971265470 @default.
• W3100205528 cites W1981106668 @default.
• W3100205528 cites W1991108537 @default.
• W3100205528 cites W2003702553 @default.
• W3100205528 cites W2008233728 @default.
• W3100205528 cites W2029394273 @default.
• W3100205528 cites W2049701820 @default.
• W3100205528 cites W2064921494 @default.
• W3100205528 cites W2083134779 @default.
• W3100205528 cites W2109363337 @default.
• W3100205528 cites W2110065044 @default.
• W3100205528 cites W2116357410 @default.
• W3100205528 cites W2118250684 @default.
• W3100205528 cites W2131759077 @default.
• W3100205528 cites W2133264613 @default.
• W3100205528 cites W2138550913 @default.
• W3100205528 cites W2484064052 @default.
• W3100205528 cites W3104778099 @default.
• W3100205528 cites W3105074488 @default.
• W3100205528 doi "https://doi.org/10.1098/rsta.2009.0129" @default.
• W3100205528 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/19805453" @default.
• W3100205528 hasPublicationYear "2009" @default.
• W3100205528 type Work @default.
• W3100205528 sameAs 3100205528 @default.
• W3100205528 citedByCount "62" @default.
• W3100205528 countsByYear W31002055282012 @default.
• W3100205528 countsByYear W31002055282013 @default.
• W3100205528 countsByYear W31002055282014 @default.
• W3100205528 countsByYear W31002055282015 @default.
• W3100205528 countsByYear W31002055282016 @default.
• W3100205528 countsByYear W31002055282017 @default.
• W3100205528 countsByYear W31002055282018 @default.
• W3100205528 countsByYear W31002055282019 @default.
• W3100205528 countsByYear W31002055282020 @default.
• W3100205528 countsByYear W31002055282021 @default.
• W3100205528 countsByYear W31002055282022 @default.
• W3100205528 countsByYear W31002055282023 @default.
• W3100205528 crossrefType "journal-article" @default.
• W3100205528 hasAuthorship W3100205528A5065355421 @default.
• W3100205528 hasAuthorship W3100205528A5083038132 @default.
• W3100205528 hasBestOaLocation W31002055282 @default.
• W3100205528 hasConcept C105795698 @default.
• W3100205528 hasConcept C111472728 @default.
• W3100205528 hasConcept C11413529 @default.
• W3100205528 hasConcept C114614502 @default.
• W3100205528 hasConcept C115961682 @default.
• W3100205528 hasConcept C118615104 @default.
• W3100205528 hasConcept C134306372 @default.
• W3100205528 hasConcept C138885662 @default.
• W3100205528 hasConcept C148483581 @default.
• W3100205528 hasConcept C151201525 @default.
• W3100205528 hasConcept C153180895 @default.
• W3100205528 hasConcept C154945302 @default.
• W3100205528 hasConcept C191178318 @default.
• W3100205528 hasConcept C2776401178 @default.
• W3100205528 hasConcept C2776639384 @default.
• W3100205528 hasConcept C2778112365 @default.
• W3100205528 hasConcept C33923547 @default.
• W3100205528 hasConcept C41008148 @default.
• W3100205528 hasConcept C41895202 @default.
• W3100205528 hasConcept C54355233 @default.
• W3100205528 hasConcept C86803240 @default.
• W3100205528 hasConcept C89128539 @default.
• W3100205528 hasConceptScore W3100205528C105795698 @default.
• W3100205528 hasConceptScore W3100205528C111472728 @default.
• W3100205528 hasConceptScore W3100205528C11413529 @default.
• W3100205528 hasConceptScore W3100205528C114614502 @default.
• W3100205528 hasConceptScore W3100205528C115961682 @default.
• W3100205528 hasConceptScore W3100205528C118615104 @default.
• W3100205528 hasConceptScore W3100205528C134306372 @default.
• W3100205528 hasConceptScore W3100205528C138885662 @default.
• W3100205528 hasConceptScore W3100205528C148483581 @default.
• W3100205528 hasConceptScore W3100205528C151201525 @default.
• W3100205528 hasConceptScore W3100205528C153180895 @default.
• W3100205528 hasConceptScore W3100205528C154945302 @default.
• W3100205528 hasConceptScore W3100205528C191178318 @default.
• W3100205528 hasConceptScore W3100205528C2776401178 @default.
• W3100205528 hasConceptScore W3100205528C2776639384 @default.
• W3100205528 hasConceptScore W3100205528C2778112365 @default.
• W3100205528 hasConceptScore W3100205528C33923547 @default.
• W3100205528 hasConceptScore W3100205528C41008148 @default.
• W3100205528 hasConceptScore W3100205528C41895202 @default.
• W3100205528 hasConceptScore W3100205528C54355233 @default.
• W3100205528 hasConceptScore W3100205528C86803240 @default.
• W3100205528 hasConceptScore W3100205528C89128539 @default.
• W3100205528 hasIssue "1906" @default.
• W3100205528 hasLocation W31002055281 @default.
• W3100205528 hasLocation W31002055282 @default.

• next