Optimal rates of aggregation in classification under low noise assumption

Details Optimal rates of aggregation in classification under low noise assumption Optimal rates of aggregation in classification under low noise assumption

2006-03-18

arxiv.org/abs/math/0603447v2

Bernoulli 13, 4 (2007) 1000-1022

Mathematics

Statistics Theory

Scientific paper

10.3150/07-BEJ6044

In the same spirit as Tsybakov (2003), we define the optimality of an aggregation procedure in the problem of classification. Using an aggregate with exponential weights, we obtain an optimal rate of convex aggregation for the hinge risk under the margin assumption. Moreover we obtain an optimal rate of model selection aggregation under the margin assumption for the excess Bayes risk.

Affiliated with

Also associated with

No associations

Rating

Optimal rates of aggregation in classification under low noise assumption 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 Optimal rates of aggregation in classification under low noise assumption, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Optimal rates of aggregation in classification under low noise assumption will most certainly appreciate the feedback.

Rate now

Comments { 0 }

Profile ID: LFWR-SCP-O-489796