Algorithmic Complexity Bounds on Future Prediction Errors

Simple item page
dc.creatorChernov, A.
dc.creatorHutter, M.
dc.creatorSchmidhuber, J.
dc.date2007-01-19
dc.date.accessioned2026-07-07T08:18:06Z
dc.date.available2026-07-07T08:18:06Z
dc.descriptionWe bound the future loss when predicting any (computably) stochastic sequence online. Solomonoff finitely bounded the total deviation of his universal predictor $M$ from the true distribution $mu$ by the algorithmic complexity of $mu$. Here we assume we are at a time $t>1$ and already observed $x=x_1...x_t$. We bound the future prediction performance on $x_{t+1}x_{t+2}...$ by a new variant of algorithmic complexity of $mu$ given $x$, plus the complexity of the randomness deficiency of $x$. The new complexity is monotone in its condition in the sense that this complexity can only decrease if the condition is prolonged. We also briefly discuss potential generalizations to Bayesian model classes and to classification problems.
dc.description21 pages
dc.identifierhttps://arxiv.org/abs/cs/0701120
dc.identifierhttp://arxiv.org/abs/cs/0701120
dc.identifierInformation and Computation, Vol.205,Nr.2 (2007) 242-261
dc.identifierdoi:10.1016/j.ic.2006.10.004
dc.identifier.urihttp://salesiana.dossiersoluciones.com/handle/123456789/134317
dc.subjectMachine Learning
dc.subjectArtificial Intelligence
dc.subjectInformation Theory
dc.titleAlgorithmic Complexity Bounds on Future Prediction Errors
dc.typetext

Files

Collections

arXiv