Kernel Support Vector Regression with imprecise output

Emilio Carrizosa(ecarrizosaus.es)
José Gordillo(jgordillous.es)
Frank Plastria(Frank.Plastriavub.ac.be)

Abstract: We consider a regression problem where uncertainty affects to the dependent variable of the elements of the database. A model based on the standard epsilon-Support Vector Regression approach is given, where two hyperplanes need to be constructed to predict the interval-valued dependent variable. By using the Hausdorff distance to measure the error between predicted and real intervals, a convex quadratic optimization problem is obtained. Non-linear regressors are introduced via the use of kernels and several numerical experiments are performed to test our methodology.

Keywords: Support Vector Regression, Kernels, Interval Data, Quadratic Programming

Category 1: Applications -- Science and Engineering (Data-Mining )

Category 2: Convex and Nonsmooth Optimization (Convex Optimization )

Category 3: Nonlinear Optimization (Quadratic Programming )

Citation:

Download: [PDF]

Entry Submitted: 01/31/2008
Entry Accepted: 01/31/2008
Entry Last Modified: 01/31/2008

Modify/Update this entry