Abstract
In this chapter we consider the general pattern recognition problem: Given the observation X and the training data D n = ((X 1, Y 1),..., (X n , Y n )) of independent identically distributed random variable pairs, we estimate the label Y by the decision
. The error probability is
. Obviously, the average error probability E L n = P{Y ≠ g n (X)} is completely determined by the distribution of the pair (X, Y), and the classifier g n . We have seen in Chapter 6 that there exist classification rules such as the cubic histogram rule with properly chosen cube sizes such that lim n→∞ E L n = L* for all possible distributions. The next question is whether there are classification rules with E L n tending to the Bayes risk at a specified rate for all distributions. Disappointingly, such rules do not exist.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
Author information
Authors and Affiliations
Rights and permissions
Copyright information
© 1996 Springer Science+Business Media New York
About this chapter
Cite this chapter
Devroye, L., Györfi, L., Lugosi, G. (1996). Slow Rates of Convergence. In: A Probabilistic Theory of Pattern Recognition. Stochastic Modelling and Applied Probability, vol 31. Springer, New York, NY. https://doi.org/10.1007/978-1-4612-0711-5_7
Download citation
DOI: https://doi.org/10.1007/978-1-4612-0711-5_7
Publisher Name: Springer, New York, NY
Print ISBN: 978-1-4612-6877-2
Online ISBN: 978-1-4612-0711-5
eBook Packages: Springer Book Archive