FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W1576638180> ?p ?o ?g. }

• W1576638180 endingPage "1487" @default.
• W1576638180 startingPage "1461" @default.
• W1576638180 abstract "We propose a PAC-Bayes theorem for the sample-compression setting where each classifier is described by a compression subset of the training data and a message string of additional information. This setting, which is the appropriate one to describe many learning algorithms, strictly generalizes the usual data-independent setting where classifiers are represented only by data-independent message strings (or parameters taken from a continuous set). The proposed PAC-Bayes theorem for the sample-compression setting reduces to the PAC-Bayes theorem of Seeger (2002) and Langford (2005) when the compression subset of each classifier vanishes. For posteriors having all their weights on a single sample-compressed classifier, the general risk bound reduces to a bound similar to the tight sample-compression bound proposed in Laviolette et al. (2005). Finally, we extend our results to the case where each sample-compressed classifier of a data-dependent ensemble may abstain of predicting a class label." @default.
• W1576638180 created "2016-06-24" @default.
• W1576638180 creator A5034069136 @default.
• W1576638180 creator A5054812796 @default.
• W1576638180 date "2007-12-01" @default.
• W1576638180 modified "2023-09-24" @default.
• W1576638180 title "PAC-Bayes Risk Bounds for Stochastic Averages and Majority Votes of Sample-Compressed Classifiers" @default.
• W1576638180 cites W1583555936 @default.
• W1576638180 cites W1607832978 @default.
• W1576638180 cites W1628829797 @default.
• W1576638180 cites W1844922534 @default.
• W1576638180 cites W1988790447 @default.
• W1576638180 cites W2014384147 @default.
• W1576638180 cites W2019363670 @default.
• W1576638180 cites W2055913343 @default.
• W1576638180 cites W2098000447 @default.
• W1576638180 cites W2100136038 @default.
• W1576638180 cites W2111049014 @default.
• W1576638180 cites W2116314036 @default.
• W1576638180 cites W2128274109 @default.
• W1576638180 cites W2150434953 @default.
• W1576638180 cites W2164053026 @default.
• W1576638180 cites W2165265965 @default.
• W1576638180 cites W2170708028 @default.
• W1576638180 cites W2428981601 @default.
• W1576638180 cites W2478386780 @default.
• W1576638180 cites W2799061466 @default.
• W1576638180 cites W2912934387 @default.
• W1576638180 cites W65382156 @default.
• W1576638180 hasPublicationYear "2007" @default.
• W1576638180 type Work @default.
• W1576638180 sameAs 1576638180 @default.
• W1576638180 citedByCount "20" @default.
• W1576638180 countsByYear W15766381802012 @default.
• W1576638180 countsByYear W15766381802013 @default.
• W1576638180 countsByYear W15766381802014 @default.
• W1576638180 countsByYear W15766381802015 @default.
• W1576638180 countsByYear W15766381802016 @default.
• W1576638180 countsByYear W15766381802017 @default.
• W1576638180 countsByYear W15766381802018 @default.
• W1576638180 countsByYear W15766381802020 @default.
• W1576638180 crossrefType "journal-article" @default.
• W1576638180 hasAuthorship W1576638180A5034069136 @default.
• W1576638180 hasAuthorship W1576638180A5054812796 @default.
• W1576638180 hasConcept C107673813 @default.
• W1576638180 hasConcept C11413529 @default.
• W1576638180 hasConcept C12267149 @default.
• W1576638180 hasConcept C134306372 @default.
• W1576638180 hasConcept C143809311 @default.
• W1576638180 hasConcept C153180895 @default.
• W1576638180 hasConcept C154945302 @default.
• W1576638180 hasConcept C185207860 @default.
• W1576638180 hasConcept C185592680 @default.
• W1576638180 hasConcept C198531522 @default.
• W1576638180 hasConcept C207201462 @default.
• W1576638180 hasConcept C33923547 @default.
• W1576638180 hasConcept C41008148 @default.
• W1576638180 hasConcept C43617362 @default.
• W1576638180 hasConcept C52001869 @default.
• W1576638180 hasConcept C77553402 @default.
• W1576638180 hasConcept C78548338 @default.
• W1576638180 hasConcept C95623464 @default.
• W1576638180 hasConceptScore W1576638180C107673813 @default.
• W1576638180 hasConceptScore W1576638180C11413529 @default.
• W1576638180 hasConceptScore W1576638180C12267149 @default.
• W1576638180 hasConceptScore W1576638180C134306372 @default.
• W1576638180 hasConceptScore W1576638180C143809311 @default.
• W1576638180 hasConceptScore W1576638180C153180895 @default.
• W1576638180 hasConceptScore W1576638180C154945302 @default.
• W1576638180 hasConceptScore W1576638180C185207860 @default.
• W1576638180 hasConceptScore W1576638180C185592680 @default.
• W1576638180 hasConceptScore W1576638180C198531522 @default.
• W1576638180 hasConceptScore W1576638180C207201462 @default.
• W1576638180 hasConceptScore W1576638180C33923547 @default.
• W1576638180 hasConceptScore W1576638180C41008148 @default.
• W1576638180 hasConceptScore W1576638180C43617362 @default.
• W1576638180 hasConceptScore W1576638180C52001869 @default.
• W1576638180 hasConceptScore W1576638180C77553402 @default.
• W1576638180 hasConceptScore W1576638180C78548338 @default.
• W1576638180 hasConceptScore W1576638180C95623464 @default.
• W1576638180 hasIssue "52" @default.
• W1576638180 hasLocation W15766381801 @default.
• W1576638180 hasOpenAccess W1576638180 @default.
• W1576638180 hasPrimaryLocation W15766381801 @default.
• W1576638180 hasRelatedWork W1607832978 @default.
• W1576638180 hasRelatedWork W1628829797 @default.
• W1576638180 hasRelatedWork W1999376700 @default.
• W1576638180 hasRelatedWork W2014384147 @default.
• W1576638180 hasRelatedWork W2019363670 @default.
• W1576638180 hasRelatedWork W2100136038 @default.
• W1576638180 hasRelatedWork W2103012681 @default.
• W1576638180 hasRelatedWork W2116314036 @default.
• W1576638180 hasRelatedWork W2116942894 @default.
• W1576638180 hasRelatedWork W2130464645 @default.
• W1576638180 hasRelatedWork W2148603752 @default.
• W1576638180 hasRelatedWork W2149991487 @default.
• W1576638180 hasRelatedWork W2150434953 @default.
• W1576638180 hasRelatedWork W2165265965 @default.

• next