Double Ramp Loss Based Reject Option Classifier

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.

Open PDF

Document Details

Document Type
Technical Report
Publication Date
May 22, 2015
Accession Number
AD1015845

Entities

People

  • Kalpit Desai
  • Naresh Manwani
  • Ramasubramanian Sundararajan
  • Sanand Sasidharan

Tags

DTIC Thesaurus Topics

  • Algorithms
  • Boundaries
  • Classification
  • Data Mining
  • Diseases And Disorders
  • Information Science
  • Ionosphere
  • Iterations
  • Kernel Functions
  • Learning
  • Machine Learning
  • Parkinson'S Disease
  • Rejection
  • Supervised Machine Learning

Fields of Study

  • Computer science

Readers

  • Computational Modeling and Simulation
  • Fluid Mechanics and Fluid Dynamics.
  • Regression Analysis.

Technology Areas

  • AI & ML
  • AI & ML - Bayesian Inference
  • AI & ML - Machine Learning Algorithms
  • AI & ML - Neural Networks