Defensive forecasting

Simple item page
dc.creatorVovk, Vladimir
dc.creatorTakemura, Akimichi
dc.creatorShafer, Glenn
dc.date2005-05-30
dc.date.accessioned2026-07-07T03:23:03Z
dc.date.available2026-07-07T03:23:03Z
dc.descriptionWe consider how to make probability forecasts of binary labels. Our main mathematical result is that for any continuous gambling strategy used for detecting disagreement between the forecasts and the actual labels, there exists a forecasting strategy whose forecasts are ideal as far as this gambling strategy is concerned. A forecasting strategy obtained in this way from a gambling strategy demonstrating a strong law of large numbers is simplified and studied empirically.
dc.description15 pages, 2 figures, to appear in the AIStats'2005 electronic proceedings
dc.identifierhttps://arxiv.org/abs/cs/0505083
dc.identifierhttp://arxiv.org/abs/cs/0505083
dc.identifierProceedings of the Tenth International Workshop on Artificial Intelligence and Statistics, 2005, pages 365--372.
dc.identifier.urihttp://salesiana.dossiersoluciones.com/handle/123456789/32797
dc.subjectMachine Learning
dc.subjectArtificial Intelligence
dc.subjectI.2.6; I.5.1
dc.titleDefensive forecasting
dc.typetext

Files

Collections

arXiv