arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1002.4453cs.ITcs.AImath.ITmath.PR
收藏

一般平稳各态历经源的非参数估计和在线预报

Nonparametric Estimation and On-Line Prediction for General Stationary Ergodic Sources

Osaka University(大阪大学)

Joe Suzuki

摘要:

本文提出了一种适用于一般平稳各态历经信源的非参数估计和在线预测的学习算法。我们准备直方图,每个直方图估计概率为有限分布,并将它们与权重混合以构建估计器。整个分析是以测度理论为基础的。无论源是离散的还是连续的,估计器都起作用。如果它是平稳遍历的,则理论上给出的Kullback-Leibler信息除以序列长度$n$的测度随着$n$趋于无穷大而收敛于零。特别地,对于连续源,该方法不需要存在概率密度函数。

英文摘要:

We proposed a learning algorithm for nonparametric estimation and on-line prediction for general stationary ergodic sources. We prepare histograms each of which estimates the probability as a finite distribution, and mixture them with weights to construct an estimator. The whole analysis is based on measure theory. The estimator works whether the source is discrete or continuous. If it is stationary ergodic, then the measure theoretically given Kullback-Leibler information divided by the sequence length $n$ converges to zero as $n$ goes to infinity. In particular, for continuous sources, the method does not require existence of a probability density function.

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。

↑