Accession Number : AD1015845

Title :   Double Ramp Loss Based Reject Option Classifier

Descriptive Note : Conference Paper

Corporate Author : Data Mining Laboratory, GE Global Research, JFWTC, Whitefield Bangalore India

Personal Author(s) : Manwani,Naresh ; Desai,Kalpit ; Sasidharan,Sanand ; Sundararajan,Ramasubramanian

Full Text :

Report Date : 22 May 2015

Pagination or Media Count : 13

Abstract : The performance of a reject option classifiers is quantified using 0 d 1 loss where d (0, .5) is the loss for rejection. In this paper, we propose double ramp loss function which gives a continuous upper bound for (0 d 1) loss. Our approach is based on minimizing regularized risk under the double ramp loss using difference of convex programming. We show the effectiveness of our approach through experiments on synthetic and benchmark datasets. Our approach performs better than the state of the art reject option classification approaches.

Descriptors :   classification , supervised machine learning , algorithms , kernel functions , data mining , ionosphere , optimization , intervals , convergence , mathematical prediction , algorithms

Distribution Statement : APPROVED FOR PUBLIC RELEASE