Statistical Learning of Arbitrary Computable Classifiers

Details Statistical Learning of Arbitrary Computable Classifiers Statistical Learning of Arbitrary Computable Classifiers

2008-06-22

arxiv.org/abs/0806.3537v2

Computer Science

Learning

Expanded the section on prior work and added references

Scientific paper

Statistical learning theory chiefly studies restricted hypothesis classes, particularly those with finite Vapnik-Chervonenkis (VC) dimension. The fundamental quantity of interest is the sample complexity: the number of samples required to learn to a specified level of accuracy. Here we consider learning over the set of all computable labeling functions. Since the VC-dimension is infinite and a priori (uniform) bounds on the number of samples are impossible, we let the learning algorithm decide when it has seen sufficient samples to have learned. We first show that learning in this setting is indeed possible, and develop a learning algorithm. We then show, however, that bounding sample complexity independently of the distribution is impossible. Notably, this impossibility is entirely due to the requirement that the learning algorithm be computable, and not due to the statistical nature of the problem.

Affiliated with

Also associated with

No associations

Rating

Statistical Learning of Arbitrary Computable 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 Statistical Learning of Arbitrary Computable Classifiers, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Statistical Learning of Arbitrary Computable Classifiers will most certainly appreciate the feedback.

Rate now

Comments { 0 }

Profile ID: LFWR-SCP-O-620712