A Simple Randomized Algorithm for Consistent Sequential Prediction of Ergodic time Series
A Simple Randomized Algorithm for Consistent Sequential Prediction of Ergodic time Series
复制标题
遍历时间序列一致顺序预测的简单随机算法
DOI：
--
复制
发表时间：
1998
期刊：
影响因子：
--
通讯作者：
G. Morvai
中科院分区：
文献类型：
--
作者：
L. Györfi;G. Lugosi;G. Morvai
我们提出了一个简单的随机过程的预测的二进制序列。该算法使用的想法，从最近的发展理论的预测个别序列。我们证明，如果序列是平稳且各态历经的随机过程的实现，那么平均错误数几乎肯定会收敛到贝叶斯预测器给出的最优值。
We present a simple randomized procedure for the prediction of a binary sequence. The algorithm uses ideas from recent developments of the theory of the prediction of individual sequences. We show that if the sequence is a realization of a stationary and ergodic random process then the average number of mistakes converges, almost surely, to that of the optimum, given by the Bayes predictor.