; 78Oh+'0HP|
$TU Delft Repository search results0TU Delft Repository search results (max. 1000)TU Delft LibraryTU Delft Library@E@Q@E@Q՜.+,0HPX`hp
x
WorksheetFeuilles de calcul
B=%r8X"1Calibri1Calibri1Calibri1
Calibri 83ffff̙̙3f3fff3f3f33333f33333./TU Delft Repositoryg[B!uuidrepository linktitleauthorcontributorpublication yearabstract
subject topiclanguagepublication type publisherisbnissnpatent
patent statusbibliographic noteaccess restrictionembargo datefaculty
departmentresearch group programmeprojectcoordinates)uuid:becaa8c9-7e5a-46c3-aaca-87763b45a28aDhttp://resolver.tudelft.nl/uuid:becaa8c9-7e5a-46c3-aaca-87763b45a28a>Projected estimators for robust semi-supervised classificationKrijthe, J.H. (TU Delft Pattern Recognition and Bioinformatics; Leiden University Medical Center); Loog, M. (TU Delft Pattern Recognition and Bioinformatics; University of Copenhagen)For semi-supervised techniques to be applied safely in practice we at least want methods to outperform their supervised counterparts. We study this question for classification using the well-known quadratic surrogate loss function. Unlike other approaches to semi-supervised learning, the procedure proposed in this work does not rely on assumptions that are not intrinsic to the classifier at hand. Using a projection of the supervised estimate onto a set of constraints imposed by the unlabeled data, we find we can safely improve over the supervised solution in terms of this quadratic loss. More specifically, we prove that, measured on the labeled and unlabeled training data, this semi-supervised procedure never gives a lower quadratic loss than the supervised alternative. To our knowledge this is the first approach that offers such strong, albeit conservative, guarantees for improvement over the supervised solution. The characteristics of our approach are explicated using benchmark datasets to further understand the similarities and differences between the quadratic loss criterion used in the theoretical results and the classification accuracy typically considered in practice.BLeast squares classification; Projection; Semi-supervised learningenjournal article&Pattern Recognition and Bioinformatics
*+&ffffff?'ffffff?(?)?"dXX333333?333333?U}}}}}}}}}} }
}}}
}}}}}}}}}}}}
@
!"#$%&'()*+,-./0123456789:;<=>?@ABCDEFGHIJKLMNOPQRSTUVWXYZ[\]^_`abcdefghijklmnopqrstuvwxyz{|}~
!"#$%&'()*+,-./0123456789:;<=>?@ABCDEFGHIJKLMNOPQRSTUVWXYZ[\]^_`abcdefghijklmnopqrstuvwxyz{|}~
!"#$%&'()*+,-./0123456789:;<=>?@ABCDEFGHIJKLMNOPQRSTUVWXYZ[\]^_`abcdefghijklmnopqrstuvwxyz{|}~
!"#$%&'()*+,-./0123456789:;<=>?@ABCDEFGHIJKLMNOPQRSTUVWXYZ[\]^_`abcdefghijklmnopqrstuvwxyz{|}~
!"#$%&'()*+,-./0123456789:;<=>?@ABCDEFGHIJKLMNOPQRSTUVWXYZ[\]^_`abcdefghijklmnopqrstuvwxyz{|}~
!"#$%&'()*+,-./0123456789:;<=>?@ABCDEFGHIJKLMNOPQRSTUVWXYZ[\]^_`abcdefghijklmnopqrstuvwxyz{|}~
!"#$%&'()*+,-./0123456789:;<=>?@ABCDEFGHIJKLMNOPQRSTUVWXYZ[\]^_`abcdefghijklmnopqrstuvwxyz{|}~
!"#$%&'()*+,-./0123456789:;<=>?@ABCDEFGHIJKLMNOPQRSTUVWXYZ[\]^_`abcdefghijklmnopqrstuvwxyz{|}~>@ddyKyKhttp://resolver.tudelft.nl/uuid:becaa8c9-7e5a-46c3-aaca-87763b45a28agg
Root Entry FE@QE@Q@SummaryInformation( F<Workbook FfDocumentSummaryInformation8 F
!"#$%&'()*+,-./0123456