Predicting non-stationary processes

Date

Authors

Ryabko, Daniil

Hutter, Marcus

Publisher

Pergamon Press

Abstract

Suppose we are given two probability measures on the set of one-way infinite finite-alphabet sequences. Consider the question of when one of the measures predicts the other, that is, when conditional probabilities converge (in a certain sense), if one of

Keywords

Keywords: Convergence of numerical methods; Problem solving; Local absolute continuity; Non-stationary measures; Sequence prediction; Probability distributions Absolute/KL divergence; Average/expected criteria; Local absolute continuity; Mixtures of measures; Non-stationary measures; Sequence prediction

URI

http://hdl.handle.net/1885/52135

Collections

ANU Research Publications

Source

Applied Mathematics Letters

Type

Journal article

DOI

10.1016/j.aml.2007.04.004

Restricted until

2037-12-31

Downloads

File

Description

01_Ryabko_Predicting_non-stationary_2008.pdf (254.18 KB)