2.50
Hdl Handle:
http://hdl.handle.net/10547/279177
Title:
Prediction with advice of unknown number of experts
Authors:
Chernov, Alexey; Vovk, Vladimir
Abstract:
In the framework of prediction with expert advice, we consider a recently introduced kind of regret bounds: the bounds that depend on the effective instead of nominal number of experts. In contrast to the NormalHedge bound, which mainly depends on the effective number of experts and also weakly depends on the nominal one, we obtain a bound that does not contain the nominal number of experts at all. We use the defensive forecasting method and introduce an application of defensive forecasting to multivalued supermartingales.
Citation:
Chernov, A. and Vovk, V. (2010) Prediction with Advice of Unknown Number of Experts.
Issue Date:
2010
URI:
http://hdl.handle.net/10547/279177
Additional Links:
http://event.cwi.nl/uai2010/papers/UAI2010_0203.pdf
Type:
Working Paper
Language:
en
Appears in Collections:
Centre for Research in Distributed Technologies (CREDIT)

Full metadata record

DC FieldValue Language
dc.contributor.authorChernov, Alexeyen_GB
dc.contributor.authorVovk, Vladimiren_GB
dc.date.accessioned2013-04-07T16:46:12Z-
dc.date.available2013-04-07T16:46:12Z-
dc.date.issued2010-
dc.identifier.citationChernov, A. and Vovk, V. (2010) Prediction with Advice of Unknown Number of Experts.en_GB
dc.identifier.urihttp://hdl.handle.net/10547/279177-
dc.description.abstractIn the framework of prediction with expert advice, we consider a recently introduced kind of regret bounds: the bounds that depend on the effective instead of nominal number of experts. In contrast to the NormalHedge bound, which mainly depends on the effective number of experts and also weakly depends on the nominal one, we obtain a bound that does not contain the nominal number of experts at all. We use the defensive forecasting method and introduce an application of defensive forecasting to multivalued supermartingales.en_GB
dc.language.isoenen
dc.relation.urlhttp://event.cwi.nl/uai2010/papers/UAI2010_0203.pdfen_GB
dc.titlePrediction with advice of unknown number of expertsen
dc.typeWorking Paperen
All Items in UOBREP are protected by copyright, with all rights reserved, unless otherwise indicated.