Title :
Fisher information and stochastic complexity
Author :
Rissanen, Jorma J.
Author_Institution :
IBM Almaden Res. Center, San Jose, CA, USA
fDate :
1/1/1996 12:00:00 AM
Abstract :
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
Keywords :
codes; computational complexity; information theory; maximum likelihood estimation; stochastic processes; Fisher information; central limit theorem; code length; maximum-likelihood code; maximum-likelihood estimate; parametric processes; redundancy; stochastic complexity; two-part codes; universal process; Bayesian methods; Channel capacity; Entropy; Helium; Information theory; Markov processes; Mutual information; Senior members; Statistics; Stochastic processes;
Journal_Title :
Information Theory, IEEE Transactions on
