PREDICTION IN THE WORST CASE
成果类型：
Note
署名作者：
FOSTER, DP
刊物名称：
ANNALS OF STATISTICS
ISSN/ISSBN：
0090-5364
DOI：
10.1214/aos/1176348140
发表日期：
1991
页码：
1084-1090
关键词：
摘要：
A predictor is a method of estimating the probability of future events over an infinite data sequence. One predictor is as strong as another if for all data sequences the former has at most the mean square error (MSE) of the latter. Given any countable set D of predictors, we explicitly construct a predictor S that is at least as strong as every element of D. Finite sample bounds are also given which hold uniformly on the space of all possible data.