Fisher information and stochastic complexity
Fisher information and stochastic complexity
复制标题
DOI：
10.1109/18.481776
复制
发表时间：
1996-01-01
影响因子：
2.5
通讯作者：
Rissanen, JJ
中科院分区：
文献类型：
--
作者：
Rissanen, JJ
通过考虑Fisher信息和消除两部码的固有冗余性，给出了一类参数过程的随机复杂度和相应的普适过程的更精确的码长。主要的条件是最大似然估计满足中心极限定理，从所谓的最大似然编码也可以得到相同的码长。
By taking into account the Fisher information and removing an inherent redundancy in earlier two-part codes, a sharper code length as the stochastic complexity and the associated universal process are derived for a class of parametric processes. The main condition required is that the maximum-likelihood estimates satisfy the Central Limit Theorem, The same code length is also obtained from the so-called maximum-likelihood code.