Computational limits to nonparametric estimation for ergodic processes

Details Computational limits to nonparametric estimation for ergodic processes Computational limits to nonparametric estimation for ergodic processes

2010-02-08

arxiv.org/abs/1002.1559v2

Computer Science

Information Theory

submitted to IEEE trans IT

Scientific paper

A new negative result for nonparametric estimation of binary ergodic processes is shown. I The problem of estimation of distribution with any degree of accuracy is studied. Then it is shown that for any countable class of estimators there is a zero-entropy binary ergodic process that is inconsistent with the class of estimators. Our result is different from other negative results for universal forecasting scheme of ergodic processes.

Affiliated with

Also associated with

No associations

Rating

Computational limits to nonparametric estimation for ergodic processes 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 Computational limits to nonparametric estimation for ergodic processes, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Computational limits to nonparametric estimation for ergodic processes will most certainly appreciate the feedback.

Rate now

Comments { 0 }

Profile ID: LFWR-SCP-O-307860