Suboptimal behaviour of Bayes and MDL in classification under misspecification

Details Suboptimal behaviour of Bayes and MDL in classification under misspecification Suboptimal behaviour of Bayes and MDL in classification under misspecification

2004-06-10

arxiv.org/abs/math/0406221v1

Mathematics

Statistics Theory

This is a slightly longer version of our paper at the COLT (Computational Learning Theory) 2004 Conference, containing two ext

Scientific paper

We show that forms of Bayesian and MDL inference that are often applied to
classification problems can be *inconsistent*. This means there exists a
learning problem such that for all amounts of data the generalization errors of
the MDL classifier and the Bayes classifier relative to the Bayesian posterior
both remain bounded away from the smallest achievable generalization error.

Affiliated with

Also associated with

No associations

Rating

Suboptimal behaviour of Bayes and MDL in classification under misspecification 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 Suboptimal behaviour of Bayes and MDL in classification under misspecification, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Suboptimal behaviour of Bayes and MDL in classification under misspecification will most certainly appreciate the feedback.

Rate now

Comments { 0 }

Profile ID: LFWR-SCP-O-668647