2.50
Hdl Handle:
http://hdl.handle.net/10547/279179
Title:
Prediction with expert advice under discounted loss
Authors:
Chernov, Alexey; Zhdanov, Fedor
Abstract:
We study prediction with expert advice in the setting where the losses are accumulated with some discounting and the impact of old losses can gradually vanish. We generalize the Aggregating Algorithm and the Aggregating Algorithm for Regression, propose a new variant of exponentially weighted average algorithm, and prove bounds on the cumulative discounted loss
Citation:
Chernov, A. and Zhdanov. F. (2010) ' Prediction with Expert Advice under Discounted Loss' in Algorithmic Learning Theory, proceeding of the 21st International Conference, ALT 2010, vol. 6331: 255-269
Publisher:
Springer
Journal:
Algorithmic Learning Theory
Issue Date:
2010
URI:
http://hdl.handle.net/10547/279179
DOI:
10.1007/978-3-642-16108-7_22
Additional Links:
http://link.springer.com/chapter/10.1007%2F978-3-642-16108-7_22
Type:
Conference papers, meetings and proceedings
Language:
en
ISSN:
0302-9743
ISBN:
978-3-642-16107-0
Appears in Collections:
Centre for Research in Distributed Technologies (CREDIT)

Full metadata record

DC FieldValue Language
dc.contributor.authorChernov, Alexeyen_GB
dc.contributor.authorZhdanov, Fedoren_GB
dc.date.accessioned2013-04-07T16:47:36Z-
dc.date.available2013-04-07T16:47:36Z-
dc.date.issued2010-
dc.identifier.citationChernov, A. and Zhdanov. F. (2010) ' Prediction with Expert Advice under Discounted Loss' in Algorithmic Learning Theory, proceeding of the 21st International Conference, ALT 2010, vol. 6331: 255-269en_GB
dc.identifier.isbn978-3-642-16107-0-
dc.identifier.issn0302-9743-
dc.identifier.doi10.1007/978-3-642-16108-7_22-
dc.identifier.urihttp://hdl.handle.net/10547/279179-
dc.description.abstractWe study prediction with expert advice in the setting where the losses are accumulated with some discounting and the impact of old losses can gradually vanish. We generalize the Aggregating Algorithm and the Aggregating Algorithm for Regression, propose a new variant of exponentially weighted average algorithm, and prove bounds on the cumulative discounted lossen_GB
dc.language.isoenen
dc.publisherSpringeren_GB
dc.relation.urlhttp://link.springer.com/chapter/10.1007%2F978-3-642-16108-7_22en_GB
dc.titlePrediction with expert advice under discounted lossen
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.