Skip to main content

Learning with Rejection

  • Conference paper
  • First Online:
Algorithmic Learning Theory (ALT 2016)

Part of the book series: Lecture Notes in Computer Science ((LNAI,volume 9925))

Included in the following conference series:

Abstract

We introduce a novel framework for classification with a rejection option that consists of simultaneously learning two functions: a classifier along with a rejection function. We present a full theoretical analysis of this framework including new data-dependent learning bounds in terms of the Rademacher complexities of the classifier and rejection families as well as consistency and calibration results. These theoretical guarantees guide us in designing new algorithms that can exploit different kernel-based hypothesis sets for the classifier and rejection functions. We compare and contrast our general framework with the special case of confidence-based rejection for which we devise alternative loss functions and algorithms as well. We report the results of several experiments showing that our kernel-based algorithms can yield a notable improvement over the best existing confidence-based rejection algorithm.

This is a preview of subscription content, log in via an institution to check access.

Access this chapter

Subscribe and save

Springer+ Basic
$34.99 /Month
  • Get 10 units per month
  • Download Article/Chapter or eBook
  • 1 Unit = 1 Article or 1 Chapter
  • Cancel anytime
Subscribe now

Buy Now

Chapter
USD 29.95
Price excludes VAT (USA)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever
eBook
USD 39.99
Price excludes VAT (USA)
  • Available as EPUB and PDF
  • Read on any device
  • Instant download
  • Own it forever
Softcover Book
USD 54.99
Price excludes VAT (USA)
  • Compact, lightweight edition
  • Dispatched in 3 to 5 business days
  • Free shipping worldwide - see info

Tax calculation will be finalised at checkout

Purchases are for personal use only

Institutional subscriptions

Similar content being viewed by others

References

  1. Bartlett, P., Wegkamp, M.: Classification with a reject option using a hinge loss. JMLR 9, 1823–1840 (2008)

    MathSciNet  MATH  Google Scholar 

  2. Bounsiar, A., Grall, E., Beauseroy, P.: Kernel based rejection method for supervised classification. WASET 3, 312–321 (2007)

    Google Scholar 

  3. Capitaine, H.L., Frelicot, C.: An optimum class-rejective decision rule and its evaluation. In: ICPR (2010)

    Google Scholar 

  4. Chaudhuri, K., Zhang, C.: Beyond disagreement-based agnostic active learning. In: NIPS (2014)

    Google Scholar 

  5. Chow, C.: An optimum character recognition system using decision function. IEEE T. C. (1957)

    Google Scholar 

  6. Chow, C.: On optimum recognition error and reject trade-off. IEEE T. C. (1970)

    Google Scholar 

  7. Cortes, C., DeSalvo, G., Mohri, M.: Learning with rejection. In: arXiv (2016)

    Google Scholar 

  8. I. Cvx Research. CVX: Matlab software for disciplined convex programming, version 2.0, August 2012

    Google Scholar 

  9. DeSalvo, G., Mohri, M., Syed, U.: Learning with deep cascades. In: Chaudhuri, K., Gentile, C., Zilles, S. (eds.) ALT 2015. LNCS, vol. 9355, pp. 254–269. Springer, Heidelberg (2015). doi:10.1007/978-3-319-24486-0_17

    Chapter  Google Scholar 

  10. Dubuisson, B., Masson, M.: Statistical decision rule with incomplete knowledge about classes. Pattern Recognit. 26, 155–165 (1993)

    Article  Google Scholar 

  11. El-Yaniv, R., Wiener, Y.: On the foundations of noise-free selective classification. JMLR 11, 1605–1641 (2010)

    MathSciNet  MATH  Google Scholar 

  12. El-Yaniv, R., Wiener, Y.: Agnostic selective classification. In: NIPS (2011)

    Google Scholar 

  13. Elkan, C.: The foundations of cost-sensitive learning. In: IJCAI (2001)

    Google Scholar 

  14. Freund, Y., Mansour, Y., Schapire, R.: Generalization bounds for averaged classifiers. Ann. Stat. (2004)

    Google Scholar 

  15. Fumera, G., Roli, F.: Support vector machines with embedded reject option. In: ICPR (2002)

    Google Scholar 

  16. Fumera, G., Roli, F., Giacinto, G.: Multiple reject thresholds for improving classification reliability. In: ICAPR (2000)

    Google Scholar 

  17. Grandvalet, Y., Keshet, J., Rakotomamonjy, A., Canu, S.: Suppport vector machines with a reject option. In: NIPS (2008)

    Google Scholar 

  18. Herbei, R., Wegkamp, M.: Classification with reject option. Can. J. Stat. (2005)

    Google Scholar 

  19. Koltchinskii, V., Panchenko, D.: Empirical margin distributions and bounding the generalization error of combined classifiers. Ann. Stat. 30, 1–50 (2002)

    MathSciNet  MATH  Google Scholar 

  20. Landgrebe, T., Tax, D., Paclik, P., Duin, R.: Interaction between classification and reject performance for distance-based reject-option classifiers. PRL 27, 908–917 (2005)

    Article  Google Scholar 

  21. Ledoux, M., Talagrand, M.: Probability in Banach Spaces: Isoperimetry and Processes. Springer, New York (1991)

    Book  MATH  Google Scholar 

  22. Littman, M., Li, L., Walsh, T.: Knows what it knows: a framework for self-aware learning. In: ICML (2008)

    Google Scholar 

  23. Long, P.M., Servedio, R.A.: Consistency versus realizable H-consistency for multiclass classification. In: ICML, vol. 3, pp. 801–809 (2013)

    Google Scholar 

  24. Melvin, I., Weston, J., Leslie, C.S., Noble, W.S.: Combining classifiers for improved classification of proteins from sequence or structure. BMCB 9, 1 (2008)

    Google Scholar 

  25. Mohri, M., Rostamizadeh, A., Talwalkar, A.: Foundations of Machine Learning. The MIT Press, Cambridge (2012)

    MATH  Google Scholar 

  26. Pereira, C.S., Pires, A.: On optimal reject rules and ROC curves. PRL 26, 943–952 (2005)

    Article  Google Scholar 

  27. Pietraszek, T.: Optimizing abstaining classifiers using ROC. In: ICML (2005)

    Google Scholar 

  28. Tax, D., Duin, R.: Growing a multi-class classifier with a reject option. Pattern Recognit. Lett. 29, 1565–1570 (2008)

    Article  Google Scholar 

  29. Tortorella, F.: An optimal reject rule for binary classifiers. In: ICAPR (2001)

    Google Scholar 

  30. Trapeznikov, K., Saligrama, V.: Supervised sequential classification under budget constraints. In: AISTATS (2013)

    Google Scholar 

  31. Wang, J., Trapeznikov, K., Saligrama, V.: An LP for sequential learning under budgets. In: JMLR (2014)

    Google Scholar 

  32. Yuan, M., Wegkamp, M.: Classification methods with reject option based on convex risk minimizations. In: JMLR (2010)

    Google Scholar 

  33. Yuan, M., Wegkamp, M.: SVMs with a reject option. In: Bernoulli (2011)

    Google Scholar 

  34. Zhang, C., Chaudhuri, K.: The extended Littlestone’s dimension for learning with mistakes and abstentions. In: COLT (2016)

    Google Scholar 

Download references

Acknowledgments

This work was partly funded by NSF IIS-1117591, CCF-1535987, and DGE-1342536.

Author information

Authors and Affiliations

Authors

Corresponding author

Correspondence to Giulia DeSalvo .

Editor information

Editors and Affiliations

Rights and permissions

Reprints and permissions

Copyright information

© 2016 Springer International Publishing Switzerland

About this paper

Cite this paper

Cortes, C., DeSalvo, G., Mohri, M. (2016). Learning with Rejection. In: Ortner, R., Simon, H., Zilles, S. (eds) Algorithmic Learning Theory. ALT 2016. Lecture Notes in Computer Science(), vol 9925. Springer, Cham. https://doi.org/10.1007/978-3-319-46379-7_5

Download citation

  • DOI: https://doi.org/10.1007/978-3-319-46379-7_5

  • Published:

  • Publisher Name: Springer, Cham

  • Print ISBN: 978-3-319-46378-0

  • Online ISBN: 978-3-319-46379-7

  • eBook Packages: Computer ScienceComputer Science (R0)

Publish with us

Policies and ethics