Abstract
In the problem of classification (or pattern recognition), given a set of n samples, we attempt to construct a classifier g n with a small misclassification error. It is important to study the convergence rates of the misclassification error as n tends to infinity. It is known that such a rate can't exist for the set of all distributions. In this paper we obtain the optimal convergence rates for a class of distributions \({\fancyscript D}\) (λ,ω) in multicategory classification and nonstandard binary classification.
Similar content being viewed by others
References
Devroye, L., Györfi, L., Lugosi, G.: A probability theory of pattern recognition, Springer Verlag, New York, 1996
Vapnik, V.: Statistical learning theory, Wiley, New York, 1998
Lee, Y., Lin, Y., Wahba, G.: Multicategory support vector machines, theory, and application to the classification of microarray data and satellite radiance data. Journal of American Statistical Association, 2002
Chen, D. R., Xiang, D. H.: The consistency of multicategory support vector machines. Adv. in Comput. Math., 24, 155–169 (2006)
Wu, Q., Zhou, D. X.: Analysis of support vector machine classification. submitted, 2003
Chen, D. R., Wu, Q., Ying, Y., Zhou, D. X.: Support vector machine soft margin classifier: error analysis. J. Machine Learning Research, 5, 1143–1175 (2004)
Antos, A.: Performance limits of nonparametric estimators, Ph D thesis, University of Budapest, 1999
Antos, A., Kégl, B., Linder, T., Lugosi, G.: Data-dependent margin-based generalization bounds for classification. Journal of Machine Learning Research, 3, 73–98 (2002)
Yang, Y. H.: Minimax nonparametric classification-part I: rates of convergence. IEEE Transaction on Information Theory, 7, 2271–2284 (1999)
Yang, Y. H.: Minimax nonparametric classification-part II: model selection for adaptation. IEEE Transaction on Information Theory, 7, 2285–2292 (1999)
Cucker, F., Smale, S.: On the Mathematical foundations of learning. Bulletin of the American Mathematical Society, 39, 1–49 (2001)
Lorentz, G. G.: Metric entropy and approximation. Bull. Amer. Math. Soc., 72, 903–937 (1966)
Author information
Authors and Affiliations
Corresponding author
Additional information
Research supported in part by NSF of China under Grants 10571010 and 10171007. The work was partially done while the first author was visiting the Institute for Mathematical Sciences, National University of Singapore in 2003. The visit was supported by the Institute
Rights and permissions
About this article
Cite this article
Chen, D.R., You, X. Minimax Optimal Rates of Convergence for Multicategory Classifications. Acta Math Sinica 23, 1419–1426 (2007). https://doi.org/10.1007/s10114-005-0880-2
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s10114-005-0880-2