Matches in SemOpenAlex for { <https://semopenalex.org/work/W2901271368> ?p ?o ?g. }
Showing items 1 to 88 of
88
with 100 items per page.
- W2901271368 abstract "We study the support recovery problem for a high-dimensional signal observed with additive noise. With suitable parametrization of the signal sparsity and magnitude of its non-zero components, we characterize a phase-transition phenomenon akin to the signal detection problem studied by Ingster in 1998. Specifically, if the signal magnitude is above the so-called strong classification boundary, we show that several classes of well-known procedures achieve asymptotically perfect support recovery as the dimension goes to infinity. This is so, for a very broad class of error distributions with light, rapidly varying tails which may have arbitrary dependence. Conversely, if the signal is below the boundary, then for a very broad class of error dependence structures, no thresholding estimators (including ones with data-dependent thresholds) can achieve perfect support recovery. The proofs of these results exploit a certain concentration of maxima phenomenon known as relative stability. We provide a complete characterization of the relative stability phenomenon for Gaussian triangular arrays in terms their correlation structure. The proof uses classic Sudakov-Fernique and Slepian lemma arguments along with a curious application of Ramsey's coloring theorem. We note that our study of the strong classification boundary is in a finer, point-wise, rather than minimax, sense. We also establish the Bayes optimality and sub-optimality of thresholding procedures. Consequently, we obtain a minimax-type characterization of the strong classification boundary for errors with log-concave densities." @default.
- W2901271368 created "2018-11-29" @default.
- W2901271368 creator A5016100876 @default.
- W2901271368 creator A5068784665 @default.
- W2901271368 date "2018-11-13" @default.
- W2901271368 modified "2023-10-16" @default.
- W2901271368 title "Fundamental Limits of Exact Support Recovery in High Dimensions" @default.
- W2901271368 cites W1487872891 @default.
- W2901271368 cites W1498464051 @default.
- W2901271368 cites W1500279823 @default.
- W2901271368 cites W1545211435 @default.
- W2901271368 cites W1965138864 @default.
- W2901271368 cites W1975001483 @default.
- W2901271368 cites W1976954310 @default.
- W2901271368 cites W1980620433 @default.
- W2901271368 cites W1981106668 @default.
- W2901271368 cites W2002743183 @default.
- W2901271368 cites W2034681107 @default.
- W2901271368 cites W2037586880 @default.
- W2901271368 cites W2069754508 @default.
- W2901271368 cites W2095689360 @default.
- W2901271368 cites W2109246257 @default.
- W2901271368 cites W2110065044 @default.
- W2901271368 cites W2115012618 @default.
- W2901271368 cites W2122992239 @default.
- W2901271368 cites W2140785063 @default.
- W2901271368 cites W2156540265 @default.
- W2901271368 cites W2320395259 @default.
- W2901271368 cites W2324099123 @default.
- W2901271368 cites W2788744072 @default.
- W2901271368 cites W2962706453 @default.
- W2901271368 cites W2963542956 @default.
- W2901271368 cites W2963549220 @default.
- W2901271368 cites W2963894057 @default.
- W2901271368 cites W3099354396 @default.
- W2901271368 cites W3102266093 @default.
- W2901271368 cites W3102479286 @default.
- W2901271368 cites W3104778099 @default.
- W2901271368 cites W411746464 @default.
- W2901271368 doi "https://doi.org/10.48550/arxiv.1811.05124" @default.
- W2901271368 hasPublicationYear "2018" @default.
- W2901271368 type Work @default.
- W2901271368 sameAs 2901271368 @default.
- W2901271368 citedByCount "1" @default.
- W2901271368 countsByYear W29012713682019 @default.
- W2901271368 crossrefType "posted-content" @default.
- W2901271368 hasAuthorship W2901271368A5016100876 @default.
- W2901271368 hasAuthorship W2901271368A5068784665 @default.
- W2901271368 hasBestOaLocation W29012713681 @default.
- W2901271368 hasConcept C105795698 @default.
- W2901271368 hasConcept C112972136 @default.
- W2901271368 hasConcept C119857082 @default.
- W2901271368 hasConcept C126255220 @default.
- W2901271368 hasConcept C134306372 @default.
- W2901271368 hasConcept C149728462 @default.
- W2901271368 hasConcept C185429906 @default.
- W2901271368 hasConcept C28826006 @default.
- W2901271368 hasConcept C33923547 @default.
- W2901271368 hasConcept C41008148 @default.
- W2901271368 hasConcept C62354387 @default.
- W2901271368 hasConceptScore W2901271368C105795698 @default.
- W2901271368 hasConceptScore W2901271368C112972136 @default.
- W2901271368 hasConceptScore W2901271368C119857082 @default.
- W2901271368 hasConceptScore W2901271368C126255220 @default.
- W2901271368 hasConceptScore W2901271368C134306372 @default.
- W2901271368 hasConceptScore W2901271368C149728462 @default.
- W2901271368 hasConceptScore W2901271368C185429906 @default.
- W2901271368 hasConceptScore W2901271368C28826006 @default.
- W2901271368 hasConceptScore W2901271368C33923547 @default.
- W2901271368 hasConceptScore W2901271368C41008148 @default.
- W2901271368 hasConceptScore W2901271368C62354387 @default.
- W2901271368 hasLocation W29012713681 @default.
- W2901271368 hasOpenAccess W2901271368 @default.
- W2901271368 hasPrimaryLocation W29012713681 @default.
- W2901271368 hasRelatedWork W1926349254 @default.
- W2901271368 hasRelatedWork W1973573083 @default.
- W2901271368 hasRelatedWork W1993095755 @default.
- W2901271368 hasRelatedWork W2075006000 @default.
- W2901271368 hasRelatedWork W2111275671 @default.
- W2901271368 hasRelatedWork W2152704622 @default.
- W2901271368 hasRelatedWork W2618253902 @default.
- W2901271368 hasRelatedWork W2805040974 @default.
- W2901271368 hasRelatedWork W2970093652 @default.
- W2901271368 hasRelatedWork W4294304999 @default.
- W2901271368 isParatext "false" @default.
- W2901271368 isRetracted "false" @default.
- W2901271368 magId "2901271368" @default.
- W2901271368 workType "article" @default.