Matches in SemOpenAlex for { <https://semopenalex.org/work/W3089321292> ?p ?o ?g. }
- W3089321292 abstract "The support vector machine (SVM) is a well-established classification method whose name refers to the particular training examples, called support vectors, that determine the maximum margin separating hyperplane. The SVM classifier is known to enjoy good generalization properties when the number of support vectors is small compared to the number of training examples. However, recent research has shown that in sufficiently high-dimensional linear classification problems, the SVM can generalize well despite a proliferation of support vectors where all training examples are support vectors. In this paper, we identify new deterministic equivalences for this phenomenon of support vector proliferation, and use them to (1) substantially broaden the conditions under which the phenomenon occurs in high-dimensional settings, and (2) prove a nearly matching converse result." @default.
- W3089321292 created "2020-10-01" @default.
- W3089321292 creator A5023545041 @default.
- W3089321292 creator A5061246300 @default.
- W3089321292 creator A5087204171 @default.
- W3089321292 date "2020-09-22" @default.
- W3089321292 modified "2023-09-25" @default.
- W3089321292 title "On the proliferation of support vectors in high dimensions" @default.
- W3089321292 cites W1530699444 @default.
- W3089321292 cites W1560153690 @default.
- W3089321292 cites W1605479404 @default.
- W3089321292 cites W1607832978 @default.
- W3089321292 cites W1965187358 @default.
- W3089321292 cites W2018199527 @default.
- W3089321292 cites W2021045253 @default.
- W3089321292 cites W2027040307 @default.
- W3089321292 cites W2032291279 @default.
- W3089321292 cites W2060430274 @default.
- W3089321292 cites W2087347434 @default.
- W3089321292 cites W2089880431 @default.
- W3089321292 cites W2110503949 @default.
- W3089321292 cites W2111049014 @default.
- W3089321292 cites W2137285073 @default.
- W3089321292 cites W2149175418 @default.
- W3089321292 cites W2151509918 @default.
- W3089321292 cites W2156135142 @default.
- W3089321292 cites W2161278885 @default.
- W3089321292 cites W2161920802 @default.
- W3089321292 cites W2579923771 @default.
- W3089321292 cites W2626872000 @default.
- W3089321292 cites W26816478 @default.
- W3089321292 cites W2787248994 @default.
- W3089321292 cites W2944156084 @default.
- W3089321292 cites W2948069823 @default.
- W3089321292 cites W2965497096 @default.
- W3089321292 cites W2967536008 @default.
- W3089321292 cites W3005822671 @default.
- W3089321292 cites W3014316192 @default.
- W3089321292 cites W3018252856 @default.
- W3089321292 cites W3025991882 @default.
- W3089321292 cites W3033836058 @default.
- W3089321292 cites W3104969455 @default.
- W3089321292 cites W3111350549 @default.
- W3089321292 cites W3119651796 @default.
- W3089321292 cites W3168158992 @default.
- W3089321292 cites W744717813 @default.
- W3089321292 doi "https://doi.org/10.48550/arxiv.2009.10670" @default.
- W3089321292 hasPublicationYear "2020" @default.
- W3089321292 type Work @default.
- W3089321292 sameAs 3089321292 @default.
- W3089321292 citedByCount "4" @default.
- W3089321292 countsByYear W30893212922020 @default.
- W3089321292 countsByYear W30893212922021 @default.
- W3089321292 crossrefType "posted-content" @default.
- W3089321292 hasAuthorship W3089321292A5023545041 @default.
- W3089321292 hasAuthorship W3089321292A5061246300 @default.
- W3089321292 hasAuthorship W3089321292A5087204171 @default.
- W3089321292 hasBestOaLocation W30893212921 @default.
- W3089321292 hasConcept C105795698 @default.
- W3089321292 hasConcept C111472728 @default.
- W3089321292 hasConcept C114614502 @default.
- W3089321292 hasConcept C119857082 @default.
- W3089321292 hasConcept C12267149 @default.
- W3089321292 hasConcept C125168437 @default.
- W3089321292 hasConcept C134306372 @default.
- W3089321292 hasConcept C138885662 @default.
- W3089321292 hasConcept C139532973 @default.
- W3089321292 hasConcept C153180895 @default.
- W3089321292 hasConcept C154945302 @default.
- W3089321292 hasConcept C165064840 @default.
- W3089321292 hasConcept C173102733 @default.
- W3089321292 hasConcept C177148314 @default.
- W3089321292 hasConcept C199360897 @default.
- W3089321292 hasConcept C2524010 @default.
- W3089321292 hasConcept C2776809875 @default.
- W3089321292 hasConcept C2778029271 @default.
- W3089321292 hasConcept C3019722297 @default.
- W3089321292 hasConcept C33923547 @default.
- W3089321292 hasConcept C41008148 @default.
- W3089321292 hasConcept C50335755 @default.
- W3089321292 hasConcept C68693459 @default.
- W3089321292 hasConcept C774472 @default.
- W3089321292 hasConcept C95623464 @default.
- W3089321292 hasConceptScore W3089321292C105795698 @default.
- W3089321292 hasConceptScore W3089321292C111472728 @default.
- W3089321292 hasConceptScore W3089321292C114614502 @default.
- W3089321292 hasConceptScore W3089321292C119857082 @default.
- W3089321292 hasConceptScore W3089321292C12267149 @default.
- W3089321292 hasConceptScore W3089321292C125168437 @default.
- W3089321292 hasConceptScore W3089321292C134306372 @default.
- W3089321292 hasConceptScore W3089321292C138885662 @default.
- W3089321292 hasConceptScore W3089321292C139532973 @default.
- W3089321292 hasConceptScore W3089321292C153180895 @default.
- W3089321292 hasConceptScore W3089321292C154945302 @default.
- W3089321292 hasConceptScore W3089321292C165064840 @default.
- W3089321292 hasConceptScore W3089321292C173102733 @default.
- W3089321292 hasConceptScore W3089321292C177148314 @default.
- W3089321292 hasConceptScore W3089321292C199360897 @default.
- W3089321292 hasConceptScore W3089321292C2524010 @default.
- W3089321292 hasConceptScore W3089321292C2776809875 @default.