Cost-sensitive Multiclass Classification Risk Bounds

Bernardo Avila Pires 1 Mohammad Ghavamzadeh 2 Csaba Szepesvari 1
2 SEQUEL - Sequential Learning
LIFL - Laboratoire d'Informatique Fondamentale de Lille, LAGIS - Laboratoire d'Automatique, Génie Informatique et Signal, Inria Lille - Nord Europe
Abstract : A commonly used approach to multiclass classification is to replace the 0-1 loss with a convex surrogate so as to make empirical risk minimization computationally tractable. Previous work has uncovered sufficient and necessary conditions for the consistency of the resulting procedures. In this paper, we strengthen these results by showing how the 0-1 excess loss of a predictor can be upper bounded as a function of the excess loss of the predictor measured using the convex surrogate. The bound is developed for the case of cost-sensitive multiclass classification and a convex surrogate loss that goes back to the work of Lee, Lin and Wahba. The bounds are as easy to calculate as in binary classification. Furthermore, we also show that our analysis extends to the analysis of the recently introduced "Simplex Coding" scheme.
Document type :
Conference papers
Complete list of metadatas

https://hal.inria.fr/hal-00840485
Contributor : Mohammad Ghavamzadeh <>
Submitted on : Tuesday, July 2, 2013 - 3:35:56 PM
Last modification on : Thursday, February 21, 2019 - 10:52:49 AM
Long-term archiving on : Wednesday, April 5, 2017 - 6:16:12 AM

File

icml2013multiclass.pdf
Files produced by the author(s)

Identifiers

  • HAL Id : hal-00840485, version 1

Collections

Citation

Bernardo Avila Pires, Mohammad Ghavamzadeh, Csaba Szepesvari. Cost-sensitive Multiclass Classification Risk Bounds. International Conference on Machine Learning, Jun 2013, Atlanta, United States. ⟨hal-00840485⟩

Share

Metrics

Record views

600

Files downloads

225