Prediction with Expert Advice in Games with Unbounded One-Step Gains

Simple item page
dc.creatorV'yugin, Vladimir V.
dc.date2008-06-26
dc.date.accessioned2026-07-07T09:47:07Z
dc.date.available2026-07-07T09:47:07Z
dc.descriptionThe games of prediction with expert advice are considered in this paper. We present some modification of Kalai and Vempala algorithm of following the perturbed leader for the case of unrestrictedly large one-step gains. We show that in general case the cumulative gain of any probabilistic prediction algorithm can be much worse than the gain of some expert of the pool. Nevertheless, we give the lower bound for this cumulative gain in general case and construct a universal algorithm which has the optimal performance; we also prove that in case when one-step gains of experts of the pool have ``limited deviations'' the performance of our algorithm is close to the performance of the best expert.
dc.description16 pages
dc.identifierhttps://arxiv.org/abs/0806.4391
dc.identifierhttp://arxiv.org/abs/0806.4391
dc.identifier.urihttp://salesiana.dossiersoluciones.com/handle/123456789/163759
dc.subjectMachine Learning
dc.subjectArtificial Intelligence
dc.subjectI.2.6
dc.titlePrediction with Expert Advice in Games with Unbounded One-Step Gains
dc.typetext

Files

Collections

arXiv