2014/01/15 by Xiao Yang, Yang, Xiao, Andrew R. Barron +1
Computer Science · Mathematics · #FOS: Computer and information sciences #Information Theory (cs.IT) #Methodology (stat.ME) #cs.IT #math.IT #stat.ME
paper · pdf · doi:10.48550/arxiv.1401.3760
arxiv created 2014/01/15 · arxiv updated 2014/01/17
This paper introduces a convenient strategy for coding and predicting sequences of independent, identically distributed random variables generated from a large alphabet of size m. In particular, the size of the sample is allowed to be variable. The employment of a Poisson model and tilting method simplifies the implementation and analysis through independence. The resulting strategy is optimal within the class of distributions satisfying a moment condition, and is close to optimal for the class of all i.i.d distributions on strings of a given length. Moreover, the method can be used to code and predict strings with a condition on the tail of the ordered counts. It can also be applied to distributions in an envelope class.