On Generalized Computable Universal Priors and their Convergence release_5zya6ovf5jf6vept2po7kpkjtq

by Marcus Hutter

Released as a report .

2005  

Abstract

Solomonoff unified Occam's razor and Epicurus' principle of multiple explanations to one elegant, formal, universal theory of inductive inference, which initiated the field of algorithmic information theory. His central result is that the posterior of the universal semimeasure M converges rapidly to the true sequence generating posterior mu, if the latter is computable. Hence, M is eligible as a universal predictor in case of unknown mu. The first part of the paper investigates the existence and convergence of computable universal (semi)measures for a hierarchy of computability classes: recursive, estimable, enumerable, and approximable. For instance, M is known to be enumerable, but not estimable, and to dominate all enumerable semimeasures. We present proofs for discrete and continuous semimeasures. The second part investigates more closely the types of convergence, possibly implied by universality: in difference and in ratio, with probability 1, in mean sum, and for Martin-Loef random sequences. We introduce a generalized concept of randomness for individual sequences and use it to exhibit difficulties regarding these issues. In particular, we show that convergence fails (holds) on generalized-random sequences in gappy (dense) Bernoulli classes.
In text/plain format

Archived Files and Locations

application/pdf  295.3 kB
file_wixa4zy2n5hdvmpgmv623ggpnq
arxiv.org (repository)
web.archive.org (webarchive)
Read Archived PDF
Preserved and Accessible
Type  report
Stage   submitted
Date   2005-03-11
Version   v1
Language   en ?
Number  IDSIA-05-05
arXiv  cs/0503026v1
Work Entity
access all versions, variants, and formats of this works (eg, pre-prints)
Catalog Record
Revision: eb9856c0-5942-4be2-b9ee-e3d17a6aa488
API URL: JSON