arXivDaily arXiv每日学术速递 周一至周五更新
arXiv math/0506080math.STmath.PRstat.TH
收藏

两个新的马尔可夫阶估计

Two new Markov order estimators

Yuval Peres, Paul Shields

摘要:

本文提出了两种新的估计有限字母表马尔可夫链阶数(记忆深度)的方法,一种是基于模式递归时间的熵估计,另一种是基于经验条件概率的比较.这两种方法的关键是当参数(顺序的候选者)通过真实顺序时发生的质变。我们还提出了扩展马尔可夫随机场的顺序估计。

英文摘要:

We present two new methods for estimating the order (memory depth) of a finite alphabet Markov chain from observation of a sample path. One method is based on entropy estimation via recurrence times of patterns, and the other relies on a comparison of empirical conditional probabilities. The key to both methods is a qualitative change that occurs when a parameter (a candidate for the order) passes the true order. We also present extensions to order estimation for Markov random fields.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑