Skip to main content
Springer Nature Link
Log in

The Study of Leave-One-Out Error-Based Classification Learning Algorithm for Generalization Performance

  • Conference paper
Advances in Natural Computation (ICNC 2006)

Part of the book series: Lecture Notes in Computer Science ((LNTCS,volume 4221))

Included in the following conference series:

  • 1409 Accesses

Abstract

This note mainly focuses on a theoretical analysis of the generalization ability of classification learning algorithm. The explicit bound is derived on the relative difference between the generalization error and leave-one-out error for classification learning algorithm under the condition of leave-one-out stability by using Markov’s inequality, and then this bound is used to estimate the generalization error of classification learning algorithm. We compare the result in this paper with previous results in the end.

Supported in part by NSFC under grant 60403011.

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

Access this chapter

Log in via an institution

Institutional subscriptions

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

Similar content being viewed by others

References

  1. Alon, N., Ben-David, S., Cesa-Bianchi, N., Haussler, D.: Scale-sensitive dimensions, uniform convergence, and learnability. Journal of the ACM 44, 615–631 (1997)

    Article  MATH  MathSciNet  Google Scholar 

  2. Bousquet, O., Elisseeff, A.: Stability and generalization. Journal Machine Learning Research 2, 499–526 (2001)

    Article  MathSciNet  Google Scholar 

  3. Cucker, F., Smale, S.: On the mathematical foundations of learning. Bulletin of the American Mathematical Society 39, 1–49 (2002)

    Article  MATH  MathSciNet  Google Scholar 

  4. Devroye, L., Wagner, T.: Distribution-free inequalities for the deleted and holdout error estimates. IEEE trans. inform. theory 25, 202–207 (1979)

    Article  MATH  MathSciNet  Google Scholar 

  5. Devroye, L., Wagner, T.: Distribution-free performance bounds for potential function rules. IEEE Trans. Inform. Theory 25, 601–604 (1979)

    Article  MATH  MathSciNet  Google Scholar 

  6. Kearns, M., Ron, D.: Algorithmic stability and sanity-check bounds for leave-one-out cross-validation. Neural Computation 11, 1427–1453 (1999)

    Article  Google Scholar 

  7. Kutin, S., Niyogi, P.: Almost-everywhere algorithmic stability and generalization error. In: Proceedings of Uncertainty in AI, Edmonton, Canda (2002)

    Google Scholar 

  8. McDiarmid, C.: On the method of bounded defferences. London Mathematical Lecture Note Series. vol. 141, pp. 148–188 (1989)

    Google Scholar 

  9. Mukherjee, S., Rifkin, R., Poggio, T.: Regression and classification with regularization. Lectures Notes in Statistics, vol. 171, pp. 107–124 (2002)

    Google Scholar 

  10. Rogers, W., Wagner, T.: A finite sample distribution-free performance bound for local discrimination rules. Annals of Statistics 6, 506–514 (1978)

    Article  MATH  MathSciNet  Google Scholar 

  11. Vapnik, V.N.: Statistical Learning Theroy. Wiley, NewYork (1998)

    Google Scholar 

Download references

Author information

Authors and Affiliations

  1. Faculty of Mathematics and Computer Science, Hubei University, Wuhan, 430062, P.R. China

    Bin Zou, Jie Xu & Luoqing Li

  2. College of Computer Science, Huazhong University of Science and Technology, Wuhan, 430074, P.R. China

    Jie Xu

Authors
  1. Bin Zou
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Jie Xu
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Luoqing Li
    View author publications

    You can also search for this author in PubMed Google Scholar

Editor information

Editors and Affiliations

  1. Life Science Research Center, School of Electronic Engineering, Xidian University, 710071, Xi’an, Shaanxi, China

    Licheng Jiao

  2. School of Electrical and Electronic Engineering, Nanyang Technological University, Block S1, Nanyang Avenue, 639798, Singapore

    Lipo Wang

  3. School of Electronic Engineering, Xidian Univ., 710071, Xi’an, P.R. China

    Xin-bo Gao

  4. College of Mathematics and Information Science, Hebei Normal University, 050016, Shijiazhuang, Hebei, P.R. China

    Jing Liu

  5. Multi-Agent Systems Lab,Department of Computer Science, University of Science and Technology of China, 230026, Hefei, China

    Feng Wu

Rights and permissions

Reprints and permissions

Copyright information

© 2006 Springer-Verlag Berlin Heidelberg

About this paper

Cite this paper

Zou, B., Xu, J., Li, L. (2006). The Study of Leave-One-Out Error-Based Classification Learning Algorithm for Generalization Performance. In: Jiao, L., Wang, L., Gao, Xb., Liu, J., Wu, F. (eds) Advances in Natural Computation. ICNC 2006. Lecture Notes in Computer Science, vol 4221. Springer, Berlin, Heidelberg. https://doi.org/10.1007/11881070_2

Download citation

  • DOI: https://doi.org/10.1007/11881070_2

  • Publisher Name: Springer, Berlin, Heidelberg

  • Print ISBN: 978-3-540-45901-9

  • Online ISBN: 978-3-540-45902-6

  • eBook Packages: Computer ScienceComputer Science (R0)

Publish with us

Policies and ethics