Rates of convergence in active learning

Details Rates of convergence in active learning Rates of convergence in active learning

2011-03-09

arxiv.org/abs/1103.1790v1

Annals of Statistics 2011, Vol. 39, No. 1, 333-361

Mathematics

Statistics Theory

Published in at http://dx.doi.org/10.1214/10-AOS843 the Annals of Statistics (http://www.imstat.org/aos/) by the Institute of

Scientific paper

10.1214/10-AOS843

We study the rates of convergence in generalization error achievable by active learning under various types of label noise. Additionally, we study the general problem of model selection for active learning with a nested hierarchy of hypothesis classes and propose an algorithm whose error rate provably converges to the best achievable error among classifiers in the hierarchy at a rate adaptive to both the complexity of the optimal classifier and the noise conditions. In particular, we state sufficient conditions for these rates to be dramatically faster than those achievable by passive learning.

Affiliated with

Also associated with

No associations

Rating

Rates of convergence in active learning 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 Rates of convergence in active learning, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Rates of convergence in active learning will most certainly appreciate the feedback.

Rate now

Comments { 0 }

Profile ID: LFWR-SCP-O-644491