Matches in SemOpenAlex for { <https://semopenalex.org/work/W1539928323> ?p ?o ?g. }
Showing items 1 to 84 of
84
with 100 items per page.
- W1539928323 endingPage "308" @default.
- W1539928323 startingPage "304" @default.
- W1539928323 abstract "We provide small sample size bounds on the generalisation error of linear classifiers that take advantage of large observed margins on the training set and sparsity in the data dependent expansion coefficients. It is already known from results in the luckiness framework that both criteria independently have a large impact on the generalisation error. Our new results show that they can be combined which theoretically justifies learning algorithms like the Support Vector Machine [4] or the Relevance Vector Machine [12]. In contrast to previous studies we avoid using the classical technique of symmetrisation by a ghost sample but directly using the sparsity for the estimation of the generalisation error. We demonstrate that our result leads to practical useful results even in case of small sample size if the training set witnesses our prior belief in sparsity and large margins." @default.
- W1539928323 created "2016-06-24" @default.
- W1539928323 creator A5047980012 @default.
- W1539928323 creator A5051619646 @default.
- W1539928323 creator A5059907791 @default.
- W1539928323 date "2000-06-28" @default.
- W1539928323 modified "2023-09-23" @default.
- W1539928323 title "Sparsity vs. Large Margins for Linear Classifiers" @default.
- W1539928323 cites W1971361630 @default.
- W1539928323 cites W2014158063 @default.
- W1539928323 cites W2014384147 @default.
- W1539928323 cites W2017753243 @default.
- W1539928323 cites W2029538739 @default.
- W1539928323 cites W2098774896 @default.
- W1539928323 cites W2099579348 @default.
- W1539928323 cites W2106491486 @default.
- W1539928323 cites W2119821739 @default.
- W1539928323 cites W2137512539 @default.
- W1539928323 cites W2156909104 @default.
- W1539928323 cites W740415 @default.
- W1539928323 cites W2278676076 @default.
- W1539928323 cites W2531834939 @default.
- W1539928323 hasPublicationYear "2000" @default.
- W1539928323 type Work @default.
- W1539928323 sameAs 1539928323 @default.
- W1539928323 citedByCount "6" @default.
- W1539928323 countsByYear W15399283232012 @default.
- W1539928323 crossrefType "proceedings-article" @default.
- W1539928323 hasAuthorship W1539928323A5047980012 @default.
- W1539928323 hasAuthorship W1539928323A5051619646 @default.
- W1539928323 hasAuthorship W1539928323A5059907791 @default.
- W1539928323 hasConcept C105795698 @default.
- W1539928323 hasConcept C11413529 @default.
- W1539928323 hasConcept C119857082 @default.
- W1539928323 hasConcept C12267149 @default.
- W1539928323 hasConcept C129848803 @default.
- W1539928323 hasConcept C14948415 @default.
- W1539928323 hasConcept C153180895 @default.
- W1539928323 hasConcept C154945302 @default.
- W1539928323 hasConcept C158154518 @default.
- W1539928323 hasConcept C177264268 @default.
- W1539928323 hasConcept C17744445 @default.
- W1539928323 hasConcept C185592680 @default.
- W1539928323 hasConcept C198531522 @default.
- W1539928323 hasConcept C199360897 @default.
- W1539928323 hasConcept C199539241 @default.
- W1539928323 hasConcept C2776502983 @default.
- W1539928323 hasConcept C33923547 @default.
- W1539928323 hasConcept C41008148 @default.
- W1539928323 hasConcept C43617362 @default.
- W1539928323 hasConcept C51632099 @default.
- W1539928323 hasConcept C774472 @default.
- W1539928323 hasConceptScore W1539928323C105795698 @default.
- W1539928323 hasConceptScore W1539928323C11413529 @default.
- W1539928323 hasConceptScore W1539928323C119857082 @default.
- W1539928323 hasConceptScore W1539928323C12267149 @default.
- W1539928323 hasConceptScore W1539928323C129848803 @default.
- W1539928323 hasConceptScore W1539928323C14948415 @default.
- W1539928323 hasConceptScore W1539928323C153180895 @default.
- W1539928323 hasConceptScore W1539928323C154945302 @default.
- W1539928323 hasConceptScore W1539928323C158154518 @default.
- W1539928323 hasConceptScore W1539928323C177264268 @default.
- W1539928323 hasConceptScore W1539928323C17744445 @default.
- W1539928323 hasConceptScore W1539928323C185592680 @default.
- W1539928323 hasConceptScore W1539928323C198531522 @default.
- W1539928323 hasConceptScore W1539928323C199360897 @default.
- W1539928323 hasConceptScore W1539928323C199539241 @default.
- W1539928323 hasConceptScore W1539928323C2776502983 @default.
- W1539928323 hasConceptScore W1539928323C33923547 @default.
- W1539928323 hasConceptScore W1539928323C41008148 @default.
- W1539928323 hasConceptScore W1539928323C43617362 @default.
- W1539928323 hasConceptScore W1539928323C51632099 @default.
- W1539928323 hasConceptScore W1539928323C774472 @default.
- W1539928323 hasLocation W15399283231 @default.
- W1539928323 hasOpenAccess W1539928323 @default.
- W1539928323 hasPrimaryLocation W15399283231 @default.
- W1539928323 hasRelatedWork W1540007258 @default.
- W1539928323 hasRelatedWork W2148603752 @default.
- W1539928323 isParatext "false" @default.
- W1539928323 isRetracted "false" @default.
- W1539928323 magId "1539928323" @default.
- W1539928323 workType "article" @default.