Improved Vapnik Cervonenkis bounds

Details Improved Vapnik Cervonenkis bounds Improved Vapnik Cervonenkis bounds

2004-10-11

arxiv.org/abs/math/0410280v1

Mathematics

Statistics Theory

Scientific paper

We give a new proof of VC bounds where we avoid the use of symmetrization and
use a shadow sample of arbitrary size. We also improve on the variance term.
This results in better constants, as shown on numerical examples. Moreover our
bounds still hold for non identically distributed independent random variables.
Keywords: Statistical learning theory, PAC-Bayesian theorems, VC dimension.

Affiliated with

Also associated with

No associations

Rating

Improved Vapnik Cervonenkis bounds 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 Improved Vapnik Cervonenkis bounds, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Improved Vapnik Cervonenkis bounds will most certainly appreciate the feedback.

Rate now

Comments { 0 }

Profile ID: LFWR-SCP-O-714841