Learning the ergodic decomposition
Statistics Theory
2014-06-26 v1 Probability
Machine Learning
Statistics Theory
Abstract
A Bayesian agent learns about the structure of a stationary process from ob- serving past outcomes. We prove that his predictions about the near future become ap- proximately those he would have made if he knew the long run empirical frequencies of the process.
Cite
@article{arxiv.1406.6670,
title = {Learning the ergodic decomposition},
author = {Nabil Al-Najjar and Eran Shmaya},
journal= {arXiv preprint arXiv:1406.6670},
year = {2014}
}