Fast learning rates for plug-in classifiers

Details Fast learning rates for plug-in classifiers Fast learning rates for plug-in classifiers

2007-08-17

arxiv.org/abs/0708.2321v1

Annals of Statistics 2007, Vol. 35, No. 2, 608-633

Mathematics

Statistics Theory

Published at http://dx.doi.org/10.1214/009053606000001217 in the Annals of Statistics (http://www.imstat.org/aos/) by the Inst

Scientific paper

10.1214/009053606000001217

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.

Affiliated with

Also associated with

No associations

Rating

Fast learning rates for plug-in classifiers does not yet have a rating. At this time, there are no reviews or comments for this scientific paper.

If you have personal experience with Fast learning rates for plug-in classifiers, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Fast learning rates for plug-in classifiers will most certainly appreciate the feedback.

Rate now

Comments { 0 }

Profile ID: LFWR-SCP-O-5744