发表机构
Federal University of Reconcavo da Bahia; Federal University of São Carlos(巴伊亚州雷孔卡沃联邦大学; 圣卡洛斯联邦大学)
机构由 AI 辅助整理,请以论文原文为准。AI 中文总结
针对无界记忆平稳链,在合并耦合假设下证明熵率与转移熵率插件估计量的非渐近集中不等式,并在均匀非零性与指数混合条件下控制偏差,获得一致性与集中性,适用于非全局连续的g函数。
AI 中文摘要
我们研究了平稳有限字母表且具有无界记忆的链的熵率和转移熵率的插件估计量。在一种基于过去耦合的合并假设下,我们建立了估计量期望周围的非渐近集中不等式。在额外的均匀非零性和指数β混合假设下,我们控制了相应的偏差,并获得了熵率和转移熵率周围的集中性,以及几乎必然的一致性。这些结果适用于由g函数控制的链,这些g函数不必是全局连续的。
英文摘要
We study plug-in estimators of the entropy rate and the transfer entropy rate for stationary finite-alphabet chains with unbounded memory. Under a coalescent coupling-from-the-past assumption, we establish non-asymptotic concentration inequalities around the expectations of the estimators. Under additional uniform non-nullness and exponential beta-mixing assumptions, we control the corresponding biases and obtain concentration around the entropy and transfer entropy rates, together with almost-sure consistency. The results apply to chains governed by g-functions that need not be globally continuous.
Comments49 pages, 6 figures