Matches in SemOpenAlex for { <https://semopenalex.org/work/W2523000601> ?p ?o ?g. }
- W2523000601 endingPage "1377" @default.
- W2523000601 startingPage "1368" @default.
- W2523000601 abstract "Many high dimensional sparse learning problems are formulated as nonconvex optimization. A popular approach to solve these nonconvex optimization problems is through convex relaxations such as linear and semidefinite programming. In this paper, we study the statistical limits of convex relaxations. Particularly, we consider two problems: Mean estimation for sparse principal submatrix and edge probability estimation for stochastic block model. We exploit the sum-of-squares relaxation hierarchy to sharply characterize the limits of a broad class of convex relaxations. Our result shows statistical optimality needs to be compromised for achieving computational tractability using convex relaxations. Compared with existing results on computational lower bounds for statistical problems, which consider general polynomialtime algorithms and rely on computational hardness hypotheses on problems like planted clique detection, our theory focuses on a broad class of convex relaxations and does not rely on unproven hypotheses." @default.
- W2523000601 created "2016-09-30" @default.
- W2523000601 creator A5019708503 @default.
- W2523000601 creator A5051448391 @default.
- W2523000601 creator A5078210646 @default.
- W2523000601 date "2016-06-19" @default.
- W2523000601 modified "2023-09-23" @default.
- W2523000601 title "On the statistical limits of convex relaxations: a case study" @default.
- W2523000601 cites W129224317 @default.
- W2523000601 cites W1579375382 @default.
- W2523000601 cites W1803708361 @default.
- W2523000601 cites W1859301526 @default.
- W2523000601 cites W1890589357 @default.
- W2523000601 cites W1914749871 @default.
- W2523000601 cites W1949284707 @default.
- W2523000601 cites W1967184028 @default.
- W2523000601 cites W1967344706 @default.
- W2523000601 cites W2004531067 @default.
- W2523000601 cites W2023348178 @default.
- W2523000601 cites W2030365814 @default.
- W2523000601 cites W2033515640 @default.
- W2523000601 cites W2046360729 @default.
- W2523000601 cites W2049143039 @default.
- W2523000601 cites W2062307640 @default.
- W2523000601 cites W2077397558 @default.
- W2523000601 cites W2106264302 @default.
- W2523000601 cites W2132001804 @default.
- W2523000601 cites W2133361319 @default.
- W2523000601 cites W2133404041 @default.
- W2523000601 cites W2133676097 @default.
- W2523000601 cites W2145799156 @default.
- W2523000601 cites W2146777332 @default.
- W2523000601 cites W2171194443 @default.
- W2523000601 cites W2336235046 @default.
- W2523000601 cites W2757458919 @default.
- W2523000601 cites W2963050003 @default.
- W2523000601 cites W2963161367 @default.
- W2523000601 cites W2963970515 @default.
- W2523000601 cites W2964064174 @default.
- W2523000601 cites W2964145111 @default.
- W2523000601 cites W2964207886 @default.
- W2523000601 cites W3104095169 @default.
- W2523000601 cites W340056678 @default.
- W2523000601 hasPublicationYear "2016" @default.
- W2523000601 type Work @default.
- W2523000601 sameAs 2523000601 @default.
- W2523000601 citedByCount "0" @default.
- W2523000601 crossrefType "proceedings-article" @default.
- W2523000601 hasAuthorship W2523000601A5019708503 @default.
- W2523000601 hasAuthorship W2523000601A5051448391 @default.
- W2523000601 hasAuthorship W2523000601A5078210646 @default.
- W2523000601 hasConcept C101901036 @default.
- W2523000601 hasConcept C112680207 @default.
- W2523000601 hasConcept C114614502 @default.
- W2523000601 hasConcept C12108790 @default.
- W2523000601 hasConcept C126255220 @default.
- W2523000601 hasConcept C15744967 @default.
- W2523000601 hasConcept C157972887 @default.
- W2523000601 hasConcept C2524010 @default.
- W2523000601 hasConcept C2776029896 @default.
- W2523000601 hasConcept C2777035058 @default.
- W2523000601 hasConcept C2777210771 @default.
- W2523000601 hasConcept C33923547 @default.
- W2523000601 hasConcept C41008148 @default.
- W2523000601 hasConcept C77805123 @default.
- W2523000601 hasConcept C79187972 @default.
- W2523000601 hasConceptScore W2523000601C101901036 @default.
- W2523000601 hasConceptScore W2523000601C112680207 @default.
- W2523000601 hasConceptScore W2523000601C114614502 @default.
- W2523000601 hasConceptScore W2523000601C12108790 @default.
- W2523000601 hasConceptScore W2523000601C126255220 @default.
- W2523000601 hasConceptScore W2523000601C15744967 @default.
- W2523000601 hasConceptScore W2523000601C157972887 @default.
- W2523000601 hasConceptScore W2523000601C2524010 @default.
- W2523000601 hasConceptScore W2523000601C2776029896 @default.
- W2523000601 hasConceptScore W2523000601C2777035058 @default.
- W2523000601 hasConceptScore W2523000601C2777210771 @default.
- W2523000601 hasConceptScore W2523000601C33923547 @default.
- W2523000601 hasConceptScore W2523000601C41008148 @default.
- W2523000601 hasConceptScore W2523000601C77805123 @default.
- W2523000601 hasConceptScore W2523000601C79187972 @default.
- W2523000601 hasLocation W25230006011 @default.
- W2523000601 hasOpenAccess W2523000601 @default.
- W2523000601 hasPrimaryLocation W25230006011 @default.
- W2523000601 hasRelatedWork W1503792852 @default.
- W2523000601 hasRelatedWork W1997911226 @default.
- W2523000601 hasRelatedWork W2099957749 @default.
- W2523000601 hasRelatedWork W2140637471 @default.
- W2523000601 hasRelatedWork W2158898601 @default.
- W2523000601 hasRelatedWork W2608089402 @default.
- W2523000601 hasRelatedWork W2611961450 @default.
- W2523000601 hasRelatedWork W2793637818 @default.
- W2523000601 hasRelatedWork W2962862352 @default.
- W2523000601 hasRelatedWork W2963170522 @default.
- W2523000601 hasRelatedWork W2964772384 @default.
- W2523000601 hasRelatedWork W2987956242 @default.
- W2523000601 hasRelatedWork W3040463754 @default.
- W2523000601 hasRelatedWork W3094857757 @default.