%0 Journal Article
%T Predicting the outcomes of every process for which an asymptotically accurate stationary predictor exists is impossible
%A Daniil Ryabko
%A Boris Ryabko
%J Statistics
%D 2015
%I arXiv
%X The problem of prediction consists in forecasting the conditional distribution of the next outcome given the past. Assume that the source generating the data is such that there is a stationary ergodic predictor whose error converges to zero (in a certain sense). The question is whether there is a universal predictor for all such sources, that is, a predictor whose error goes to zero if any of the sources that have this property is chosen to generate the data. This question is answered in the negative, contrasting a number of previously established positive results concerning related but smaller sets of processes.
%U http://arxiv.org/abs/1509.07776v1