Competing with Markov prediction strategies

Simple item page
dc.creatorVovk, Vladimir
dc.date2006-07-28
dc.date.accessioned2026-07-07T07:16:26Z
dc.date.available2026-07-07T07:16:26Z
dc.descriptionAssuming that the loss function is convex in the prediction, we construct a prediction strategy universal for the class of Markov prediction strategies, not necessarily continuous. Allowing randomization, we remove the requirement of convexity.
dc.description11 pages
dc.identifierhttps://arxiv.org/abs/cs/0607136
dc.identifierhttp://arxiv.org/abs/cs/0607136
dc.identifier.urihttp://salesiana.dossiersoluciones.com/handle/123456789/113593
dc.subjectMachine Learning
dc.titleCompeting with Markov prediction strategies
dc.typetext

Files

Collections

arXiv