2.50
Hdl Handle:
http://hdl.handle.net/10547/279178
Title:
Supermartingales in prediction with expert advice
Authors:
Chernov, Alexey; Kalnishkan, Yuri; Zhdanov, Fedor; Vovk, Vladimir
Abstract:
The paper applies the method of defensive forecasting, based on the use of game-theoretic supermartingales, to prediction with expert advice. In the traditional setting of a countable number of experts and a finite number of outcomes, the Defensive Forecasting Algorithm is very close to the well-known Aggregating Algorithm. Not only the performance guarantees but also the predictions are the same for these two methods of fundamentally different nature. The paper also discusses a new setting where the experts can give advice conditional on the learner's future decision. Both the algorithms can be adapted to the new setting and give the same performance guarantees as in the traditional setting. Finally, an application of defensive forecasting to a setting with several loss functions is outlined.
Citation:
Chernov, A., Kalnishkan, Y., Zhdanov, F. and Vovk, V., (2010) 'Supermartingales in prediction with expert advice' 411 (29-30):2647-2669 Theoretical Computer Science
Publisher:
Elsevier
Journal:
Theoretical Computer Science
Issue Date:
2010
URI:
http://hdl.handle.net/10547/279178
DOI:
10.1016/j.tcs.2010.04.003
Additional Links:
http://linkinghub.elsevier.com/retrieve/pii/S0304397510001982
Type:
Article
Language:
en
ISSN:
0304-3975
Appears in Collections:
Centre for Research in Distributed Technologies (CREDIT)

Full metadata record

DC FieldValue Language
dc.contributor.authorChernov, Alexeyen_GB
dc.contributor.authorKalnishkan, Yurien_GB
dc.contributor.authorZhdanov, Fedoren_GB
dc.contributor.authorVovk, Vladimiren_GB
dc.date.accessioned2013-04-07T16:46:49Z-
dc.date.available2013-04-07T16:46:49Z-
dc.date.issued2010-
dc.identifier.citationChernov, A., Kalnishkan, Y., Zhdanov, F. and Vovk, V., (2010) 'Supermartingales in prediction with expert advice' 411 (29-30):2647-2669 Theoretical Computer Scienceen_GB
dc.identifier.issn0304-3975-
dc.identifier.doi10.1016/j.tcs.2010.04.003-
dc.identifier.urihttp://hdl.handle.net/10547/279178-
dc.description.abstractThe paper applies the method of defensive forecasting, based on the use of game-theoretic supermartingales, to prediction with expert advice. In the traditional setting of a countable number of experts and a finite number of outcomes, the Defensive Forecasting Algorithm is very close to the well-known Aggregating Algorithm. Not only the performance guarantees but also the predictions are the same for these two methods of fundamentally different nature. The paper also discusses a new setting where the experts can give advice conditional on the learner's future decision. Both the algorithms can be adapted to the new setting and give the same performance guarantees as in the traditional setting. Finally, an application of defensive forecasting to a setting with several loss functions is outlined.en_GB
dc.language.isoenen
dc.publisherElsevieren_GB
dc.relation.urlhttp://linkinghub.elsevier.com/retrieve/pii/S0304397510001982en_GB
dc.rightsArchived with thanks to Theoretical Computer Scienceen_GB
dc.titleSupermartingales in prediction with expert adviceen
dc.typeArticleen
dc.identifier.journalTheoretical Computer Scienceen_GB
All Items in UOBREP are protected by copyright, with all rights reserved, unless otherwise indicated.