Predicting the outcomes of every process for which an asymptotically accurate stationary predictor exists is impossible - Archive ouverte HAL Access content directly
Conference Papers Year :

Predicting the outcomes of every process for which an asymptotically accurate stationary predictor exists is impossible

(1) , (2)
1
2
Daniil Ryabko
• Function : Author
Boris Ryabko
• Function : Author

Abstract

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 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.

Dates and versions

hal-01165876 , version 1 (24-06-2015)

Identifiers

• HAL Id : hal-01165876 , version 1

Cite

Daniil Ryabko, Boris Ryabko. Predicting the outcomes of every process for which an asymptotically accurate stationary predictor exists is impossible. International Symposium on Information Theory, Jun 2015, Hong Kong, Hong Kong SAR China. pp.1204-1206. ⟨hal-01165876⟩

100 View