FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W3100712906> ?p ?o ?g. }

• W3100712906 abstract "Consider a two-class classification problem where the number of features is much larger than the sample size. The features are masked by Gaussian noise with mean zero and covariance matrix $Sigma$, where the precision matrix $Omega=Sigma^{-1}$ is unknown but is presumably sparse. The useful features, also unknown, are sparse and each contributes weakly (i.e., rare and weak) to the classification decision. By obtaining a reasonably good estimate of $Omega$, we formulate the setting as a linear regression model. We propose a two-stage classification method where we first select features by the method of Innovated Thresholding (IT), and then use the retained features and Fisher’s LDA for classification. In this approach, a crucial problem is how to set the threshold of IT. We approach this problem by adapting the recent innovation of Higher Criticism Thresholding (HCT). We find that when useful features are rare and weak, the limiting behavior of HCT is essentially just as good as the limiting behavior of ideal threshold, the threshold one would choose if the underlying distribution of the signals is known (if only). Somewhat surprisingly, when $Omega$ is sufficiently sparse, its off-diagonal coordinates usually do not have a major influence over the classification decision. Compared to recent work in the case where $Omega$ is the identity matrix [Proc. Natl. Acad. Sci. USA 105 (2008) 14790–14795; Philos. Trans. R. Soc. Lond. Ser. A Math. Phys. Eng. Sci. 367 (2009) 4449–4470], the current setting is much more general, which needs a new approach and much more sophisticated analysis. One key component of the analysis is the intimate relationship between HCT and Fisher’s separation. Another key component is the tight large-deviation bounds for empirical processes for data with unconventional correlation structures, where graph theory on vertex coloring plays an important role." @default.
• W3100712906 created "2020-11-23" @default.
• W3100712906 creator A5075757275 @default.
• W3100712906 creator A5079340751 @default.
• W3100712906 creator A5083038132 @default.
• W3100712906 date "2013-10-01" @default.
• W3100712906 modified "2023-10-16" @default.
• W3100712906 title "Optimal classification in sparse Gaussian graphic model" @default.
• W3100712906 cites W1587510588 @default.
• W3100712906 cites W1768730780 @default.
• W3100712906 cites W1971265470 @default.
• W3100712906 cites W1981106668 @default.
• W3100712906 cites W1989727964 @default.
• W3100712906 cites W1996213317 @default.
• W3100712906 cites W2001619934 @default.
• W3100712906 cites W2029394273 @default.
• W3100712906 cites W2049701820 @default.
• W3100712906 cites W2049704395 @default.
• W3100712906 cites W2051605894 @default.
• W3100712906 cites W2064921494 @default.
• W3100712906 cites W2074682976 @default.
• W3100712906 cites W2083134779 @default.
• W3100712906 cites W2097581234 @default.
• W3100712906 cites W2116063398 @default.
• W3100712906 cites W2116357410 @default.
• W3100712906 cites W2118250684 @default.
• W3100712906 cites W2131759077 @default.
• W3100712906 cites W2132555912 @default.
• W3100712906 cites W2135046866 @default.
• W3100712906 cites W2138550913 @default.
• W3100712906 cites W3099354396 @default.
• W3100712906 cites W3100205528 @default.
• W3100712906 cites W3101788651 @default.
• W3100712906 cites W3102266093 @default.
• W3100712906 cites W3104038823 @default.
• W3100712906 cites W3104778099 @default.
• W3100712906 cites W3105340263 @default.
• W3100712906 cites W4237496336 @default.
• W3100712906 cites W4238253035 @default.
• W3100712906 cites W4244934246 @default.
• W3100712906 doi "https://doi.org/10.1214/13-aos1163" @default.
• W3100712906 hasPublicationYear "2013" @default.
• W3100712906 type Work @default.
• W3100712906 sameAs 3100712906 @default.
• W3100712906 citedByCount "30" @default.
• W3100712906 countsByYear W31007129062014 @default.
• W3100712906 countsByYear W31007129062015 @default.
• W3100712906 countsByYear W31007129062016 @default.
• W3100712906 countsByYear W31007129062018 @default.
• W3100712906 countsByYear W31007129062019 @default.
• W3100712906 countsByYear W31007129062020 @default.
• W3100712906 countsByYear W31007129062021 @default.
• W3100712906 countsByYear W31007129062022 @default.
• W3100712906 countsByYear W31007129062023 @default.
• W3100712906 crossrefType "journal-article" @default.
• W3100712906 hasAuthorship W3100712906A5075757275 @default.
• W3100712906 hasAuthorship W3100712906A5079340751 @default.
• W3100712906 hasAuthorship W3100712906A5083038132 @default.
• W3100712906 hasBestOaLocation W31007129061 @default.
• W3100712906 hasConcept C106487976 @default.
• W3100712906 hasConcept C11413529 @default.
• W3100712906 hasConcept C114614502 @default.
• W3100712906 hasConcept C115961682 @default.
• W3100712906 hasConcept C121332964 @default.
• W3100712906 hasConcept C130367717 @default.
• W3100712906 hasConcept C153180895 @default.
• W3100712906 hasConcept C154945302 @default.
• W3100712906 hasConcept C159985019 @default.
• W3100712906 hasConcept C163716315 @default.
• W3100712906 hasConcept C191178318 @default.
• W3100712906 hasConcept C192562407 @default.
• W3100712906 hasConcept C2524010 @default.
• W3100712906 hasConcept C2779557605 @default.
• W3100712906 hasConcept C28826006 @default.
• W3100712906 hasConcept C33923547 @default.
• W3100712906 hasConcept C41008148 @default.
• W3100712906 hasConcept C62520636 @default.
• W3100712906 hasConceptScore W3100712906C106487976 @default.
• W3100712906 hasConceptScore W3100712906C11413529 @default.
• W3100712906 hasConceptScore W3100712906C114614502 @default.
• W3100712906 hasConceptScore W3100712906C115961682 @default.
• W3100712906 hasConceptScore W3100712906C121332964 @default.
• W3100712906 hasConceptScore W3100712906C130367717 @default.
• W3100712906 hasConceptScore W3100712906C153180895 @default.
• W3100712906 hasConceptScore W3100712906C154945302 @default.
• W3100712906 hasConceptScore W3100712906C159985019 @default.
• W3100712906 hasConceptScore W3100712906C163716315 @default.
• W3100712906 hasConceptScore W3100712906C191178318 @default.
• W3100712906 hasConceptScore W3100712906C192562407 @default.
• W3100712906 hasConceptScore W3100712906C2524010 @default.
• W3100712906 hasConceptScore W3100712906C2779557605 @default.
• W3100712906 hasConceptScore W3100712906C28826006 @default.
• W3100712906 hasConceptScore W3100712906C33923547 @default.
• W3100712906 hasConceptScore W3100712906C41008148 @default.
• W3100712906 hasConceptScore W3100712906C62520636 @default.
• W3100712906 hasIssue "5" @default.
• W3100712906 hasLocation W31007129061 @default.
• W3100712906 hasLocation W31007129062 @default.
• W3100712906 hasLocation W31007129063 @default.
• W3100712906 hasLocation W31007129064 @default.

• next