2.50
Hdl Handle:
http://hdl.handle.net/10547/279180
Title:
Prediction with expert evaluators’ advice
Authors:
Chernov, Alexey; Vovk, Vladimir
Abstract:
We introduce a new protocol for prediction with expert advice in which each expert evaluates the learner’s and his own performance using a loss function that may change over time and may be different from the loss functions used by the other experts. The learner’s goal is to perform better or not much worse than each expert, as evaluated by that expert, for all experts simultaneously. If the loss functions used by the experts are all proper scoring rules and all mixable, we show that the defensive forecasting algorithm enjoys the same performance guarantee as that attainable by the Aggregating Algorithm in the standard setting and known to be optimal. This result is also applied to the case of “specialist” experts. In this case, the defensive forecasting algorithm reduces to a simple modification of the Aggregating Algorithm.
Citation:
Chernov. A. and Vovk, V., (2009) 'Prediction with Expert Evaluators’ Advice' in Algorithmic Learning Theory, proceedings of the 20th International Conference, ALT 2009, vol. 5809: 8-22
Publisher:
Springer
Journal:
Algorithmic Learning Theory
Issue Date:
2009
URI:
http://hdl.handle.net/10547/279180
DOI:
10.1007/978-3-642-04414-4_6
Additional Links:
http://link.springer.com/chapter/10.1007%2F978-3-642-04414-4_6?LI=true
Type:
Conference papers, meetings and proceedings
Language:
en
ISBN:
9783642044137
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.accessioned2013-04-07T16:48:40Z-
dc.date.available2013-04-07T16:48:40Z-
dc.date.issued2009-
dc.identifier.citationChernov. A. and Vovk, V., (2009) 'Prediction with Expert Evaluators’ Advice' in Algorithmic Learning Theory, proceedings of the 20th International Conference, ALT 2009, vol. 5809: 8-22en_GB
dc.identifier.isbn9783642044137-
dc.identifier.doi10.1007/978-3-642-04414-4_6-
dc.identifier.urihttp://hdl.handle.net/10547/279180-
dc.description.abstractWe introduce a new protocol for prediction with expert advice in which each expert evaluates the learner’s and his own performance using a loss function that may change over time and may be different from the loss functions used by the other experts. The learner’s goal is to perform better or not much worse than each expert, as evaluated by that expert, for all experts simultaneously. If the loss functions used by the experts are all proper scoring rules and all mixable, we show that the defensive forecasting algorithm enjoys the same performance guarantee as that attainable by the Aggregating Algorithm in the standard setting and known to be optimal. This result is also applied to the case of “specialist” experts. In this case, the defensive forecasting algorithm reduces to a simple modification of the Aggregating Algorithm.en_GB
dc.language.isoenen
dc.publisherSpringeren_GB
dc.relation.urlhttp://link.springer.com/chapter/10.1007%2F978-3-642-04414-4_6?LI=trueen_GB
dc.titlePrediction with expert evaluators’ adviceen
dc.typeConference papers, meetings and proceedingsen
dc.identifier.journalAlgorithmic Learning Theoryen_GB
All Items in UOBREP are protected by copyright, with all rights reserved, unless otherwise indicated.