A Limit Theorem in Singular Regression Problem

Details A Limit Theorem in Singular Regression Problem A Limit Theorem in Singular Regression Problem

2009-01-16

arxiv.org/abs/0901.2376v1

Computer Science

Learning

16 pages

Scientific paper

In statistical problems, a set of parameterized probability distributions is used to estimate the true probability distribution. If Fisher information matrix at the true distribution is singular, then it has been left unknown what we can estimate about the true distribution from random samples. In this paper, we study a singular regression problem and prove a limit theorem which shows the relation between the singular regression problem and two birational invariants, a real log canonical threshold and a singular fluctuation. The obtained theorem has an important application to statistics, because it enables us to estimate the generalization error from the training error without any knowledge of the true probability distribution.

Affiliated with

Also associated with

No associations

Rating

A Limit Theorem in Singular Regression Problem 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 A Limit Theorem in Singular Regression Problem, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and A Limit Theorem in Singular Regression Problem will most certainly appreciate the feedback.

Rate now

Comments { 0 }

Profile ID: LFWR-SCP-O-126873