Publication:
A Partial parametric path algorithm for multiclass classification

Simple item page
dc.affiliation.dptoUC3M. Departamento de Estadísticaes
dc.contributor.authorLiu, Ling
dc.contributor.authorMartín Barragán, Belén
dc.contributor.authorPrieto Fernández, Francisco Javier
dc.contributor.editorUniversidad Carlos III de Madrid. Departamento de Estadísticaes
dc.date.accessioned2016-02-26T14:35:54Z
dc.date.available2016-02-26T14:35:54Z
dc.date.issued2016-02
dc.description.abstractThe objective functions of Support Vector Machine methods (SVMs) often includeparameters to weigh the relative importance of margins and training accuracies.The values of these parameters have a direct effect both on the optimal accuraciesand the misclassification costs. Usually, a grid search is used to find appropriatevalues for them. This method requires the repeated solution of quadraticprograms for different parameter values, and it may imply a large computationalcost, especially in a setting of multiclass SVMs and large training datasets. Formulti-class classification problems, in the presence of different misclassificationcosts, identifying a desirable set of values for these parameters becomes evenmore relevant. In this paper, we propose a partial parametric path algorithm, basedon the property that the path of optimal solutions of the SVMs with respect tothe preceding parameters is piecewise linear. This partial parametric path algorithmrequires the solution of just one quadratic programming problem, and anumber of linear systems of equations. Thus it can significantly reduce the computationalrequirements of the algorithm. To systematically explore the differentweights to assign to the misclassification costs, we combine the partial parametricpath algorithm with a variable neighborhood search method. Our numerical experimentsshow the efficiency and reliability of the proposed partial parametricpath algorithm.en
dc.format.mimetypeapplication/pdf
dc.identifier.issn2387-0303es
dc.identifier.urihttps://hdl.handle.net/10016/22390
dc.identifier.uxxiDT/0000001444es
dc.language.isoenges
dc.relation.ispartofseriesUC3M Working Papers Statistics and Econometricsen
dc.relation.ispartofseries16-03
dc.rightsAtribución-NoComercial-SinDerivadas 3.0 España*
dc.rights.accessRightsopen accessen
dc.rights.urihttp://creativecommons.org/licenses/by-nc-nd/3.0/es/*
dc.subject.otherMulti-class SVMen
dc.subject.otherPiecewise linearityen
dc.subject.otherPartial parametric path algorithmen
dc.subject.otherVariable neighborhood searchen
dc.titleA Partial parametric path algorithm for multiclass classificationen
dc.typeworking paper*
dc.type.hasVersionSMUR*
dspace.entity.typePublication
Files
Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
ws1603.pdf
Size:
3.28 MB
Format:
Adobe Portable Document Format
Download
Collections
DES - Working Papers. Statistics and Econometrics. WS