Journal
ANNALS OF STATISTICS
Volume 35, Issue 2, Pages 608-633Publisher
INST MATHEMATICAL STATISTICS
DOI: 10.1214/009053606000001217
Keywords
classification; statistical learning; fast rates of convergence; excess risk; plug-in classifiers; minimax lower bounds
Categories
Ask authors/readers for more resources
It has been recently shown that, under the margin (or low noise) assumption, there exist classifiers attaining fast rates of convergence of the excess Bayes risk, that is, rates faster than n(-1/2). The work on this subject has suggested the following two conjectures: (i) the best achievable fast rate is of the order n(-1), and (ii) the plug-in classifiers generally converge more slowly than the classifiers based on empirical risk minimization. We show that both conjectures are not correct. In particular, we construct plug-in classifiers that can achieve not only fast, but also super-fast rates, that is, rates faster than n-1. We establish minimax lower bounds showing that the obtained rates cannot be improved.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available