arXivDaily arXiv每日学术速递 周一至周五更新
北美退伍军人节(Veterans Day),12 日无更新
arXiv 0810.4341cs.ITcond-mat.othermath.ITphysics.data-an
收藏

基于圈展开的隐马尔可夫过程的熵

Entropy of Hidden Markov Processes via Cycle Expansion

Armen E. Allahverdyan

摘要:

隐马尔可夫过程是现代概率建模的基本工具之一。然而,它们的熵的表征仍然是一个悬而未决的问题。在这里,HMP的熵是通过zeta函数的循环展开计算的,这是一种从动力系统理论中采用的方法。对于一类HMP,这种方法产生的熵和矩母函数的精确结果。后者允许估计,通过的HMP的大偏差的概率,通过的HMP界。更一般地,该方法通过收敛级数提供了矩母函数和熵的表示。

英文摘要:

Hidden Markov Processes (HMP) is one of the basic tools of the modern probabilistic modeling. The characterization of their entropy remains however an open problem. Here the entropy of HMP is calculated via the cycle expansion of the zeta-function, a method adopted from the theory of dynamical systems. For a class of HMP this method produces exact results both for the entropy and the moment-generating function. The latter allows to estimate, via the Chernoff bound, the probabilities of large deviations for the HMP. More generally, the method offers a representation of the moment-generating function and of the entropy via convergent series.

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。

↑