On Generalized Computable Universal Priors and their Convergence

Simple item page
dc.creatorHutter, Marcus
dc.date2005-03-11
dc.date.accessioned2026-07-07T09:46:43Z
dc.date.available2026-07-07T09:46:43Z
dc.descriptionSolomonoff 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.
dc.description22 pages
dc.identifierhttps://arxiv.org/abs/cs/0503026
dc.identifierhttp://arxiv.org/abs/cs/0503026
dc.identifierTheoretical Computer Science, 364 (2006) 27-41
dc.identifier.urihttp://salesiana.dossiersoluciones.com/handle/123456789/163623
dc.subjectMachine Learning
dc.subjectComputational Complexity
dc.subjectProbability
dc.subjectI.2.6; E.4; G.3
dc.titleOn Generalized Computable Universal Priors and their Convergence
dc.typetext

Files

Collections

arXiv