Competing with stationary prediction strategies

Simple item page
dc.creatorVovk, Vladimir
dc.date2006-07-13
dc.date.accessioned2026-07-07T07:16:20Z
dc.date.available2026-07-07T07:16:20Z
dc.descriptionIn this paper we introduce the class of stationary prediction strategies and construct a prediction algorithm that asymptotically performs as well as the best continuous stationary strategy. We make mild compactness assumptions but no stochastic assumptions about the environment. In particular, no assumption of stationarity is made about the environment, and the stationarity of the considered strategies only means that they do not depend explicitly on time; we argue that it is natural to consider only stationary strategies even for highly non-stationary environments.
dc.description20 pages
dc.identifierhttps://arxiv.org/abs/cs/0607067
dc.identifierhttp://arxiv.org/abs/cs/0607067
dc.identifier.urihttp://salesiana.dossiersoluciones.com/handle/123456789/113556
dc.subjectMachine Learning
dc.titleCompeting with stationary prediction strategies
dc.typetext

Files

Collections

arXiv