On semimeasures predicting Martin-Lof random sequences

Date

Authors

Hutter, Marcus

Muchnik, Andrej

Publisher

Elsevier

Abstract

Solomonoff's central result on induction is that the prediction of a universal semimeasure M converges rapidly and with probability 1 to the true sequence generating predictor μ, if the latter is computable. Hence, M is eligible as a universal sequence p

Keywords

Keywords: Convergence of numerical methods; Data structures; Probability distributions; Problem solving; Algorithmic information theory; Mixture distributions; Predictive convergence; Quasimeasures; Sequence prediction; Supermartingales; Universal enumerable semime Algorithmic information theory; Martin-Löf randomness; Mixture distributions; Predictive convergence; Quasimeasures; Sequence prediction; Supermartingales; Universal enumerable semimeasure

URI

http://hdl.handle.net/1885/50998

Collections

ANU Research Publications

Source

Theoretical Computer Science

Type

Journal article

DOI

10.1016/j.tcs.2007.03.040

Restricted until

2037-12-31

Downloads

File

Description

01_Hutter_On_semimeasures_predicting_2007.pdf (405.87 KB)