A Partial parametric path algorithm for multiclass classification

Repositorio e-Archivo

Mostrar el registro sencillo del ítem

dc.contributor.author Liu, Ling
dc.contributor.author Martín Barragán, Belén
dc.contributor.author Prieto Fernández, Francisco Javier
dc.contributor.editor Universidad Carlos III de Madrid. Departamento de Estadística
dc.date.accessioned 2016-02-26T14:35:54Z
dc.date.available 2016-02-26T14:35:54Z
dc.date.issued 2016-02
dc.identifier.issn 2387-0303
dc.identifier.uri http://hdl.handle.net/10016/22390
dc.description.abstract The 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.
dc.format.mimetype application/pdf
dc.language.iso eng
dc.relation.ispartofseries UC3M Working Papers Statistics and Econometrics
dc.relation.ispartofseries 16-03
dc.rights Atribución-NoComercial-SinDerivadas 3.0 España
dc.rights.uri http://creativecommons.org/licenses/by-nc-nd/3.0/es/
dc.subject.other Multi-class SVM
dc.subject.other Piecewise linearity
dc.subject.other Partial parametric path algorithm
dc.subject.other Variable neighborhood search
dc.title A Partial parametric path algorithm for multiclass classification
dc.type workingPaper
dc.rights.accessRights openAccess
dc.type.version submitedVersion
dc.identifier.uxxi DT/0000001444
 Find Full text

Ficheros en el ítem

*Click en la imagen del fichero para previsualizar.(Los elementos embargados carecen de esta funcionalidad)


El ítem tiene asociada la siguiente licencia:

Este ítem aparece en la(s) siguiente(s) colección(es)

Mostrar el registro sencillo del ítem