New Error Bounds for Solomonoff Prediction

Simple item page
dc.creatorHutter, Marcus
dc.date1999-12-13
dc.date2001-01-26
dc.date.accessioned2026-07-07T03:24:29Z
dc.date.available2026-07-07T03:24:29Z
dc.descriptionSolomonoff sequence prediction is a scheme to predict digits of binary strings without knowing the underlying probability distribution. We call a prediction scheme informed when it knows the true probability distribution of the sequence. Several new relations between universal Solomonoff sequence prediction and informed prediction and general probabilistic prediction schemes will be proved. Among others, they show that the number of errors in Solomonoff prediction is finite for computable distributions, if finite in the informed case. Deterministic variants will also be studied. The most interesting result is that the deterministic variant of Solomonoff prediction is optimal compared to any other probabilistic or deterministic prediction scheme apart from additive square root corrections only. This makes it well suited even for difficult prediction problems, where it does not suffice when the number of errors is minimal to within some factor greater than one. Solomonoff's original bound and the ones presented here complement each other in a useful way.
dc.description13 pages, Journal of Computer and System Science, minor changes to 1st version
dc.identifierhttps://arxiv.org/abs/cs/9912008
dc.identifierhttp://arxiv.org/abs/cs/9912008
dc.identifierJ. Computer and System Science 62:4 (2001) 653-667
dc.identifier.urihttp://salesiana.dossiersoluciones.com/handle/123456789/33342
dc.subjectArtificial Intelligence
dc.subjectMachine Learning
dc.subjectI.2.6; F.1.3; E.4; F.2
dc.titleNew Error Bounds for Solomonoff Prediction
dc.typetext

Files

Collections

arXiv