IIIT Hyderabad Publications |
|||||||||
|
Sparse Reject Option Classifier using Successive Linear ProgrammingAuthors: kulin Shah,Naresh Manwani Conference: Thirty-Third AAAI Conference on Artificial Intelligence (AAAI-2019 2019) Location Honolulu, Hawaii, USA Date: 2019-01-27 Report no: IIIT/TR/2019/34 AbstractIn this paper, we propose an approach for learning sparse reject option classifiers using double ramp loss L dr . We use DC programming to find the risk minimizer. The algorithm solves a sequence of linear programs to learn the reject option classifier. We show that the loss L dr is Fisher consistent. We also show that the excess risk of loss L d is upper bounded by excess risk of L dr . We derive the generalization error bounds for the proposed approach. We show the effectiveness of the proposed approach by experimenting it on several real world datasets. The proposed approach not only performs comparable to the state of the art, it also successfully learns sparse classifiers. Full paper: pdf Centre for Cognitive Science |
||||||||
Copyright © 2009 - IIIT Hyderabad. All Rights Reserved. |