Prediction with Expert Advice by Following the Perturbed Leader for General Weights

Simple item page
dc.contributor.authorHutter, Marcus
dc.contributor.authorPoland, Jan
dc.coverage.spatialPadova Italy
dc.date.accessioned2015-12-10T22:43:01Z
dc.date.createdOctober 2-5 2004
dc.date.issued2004
dc.date.updated2016-02-24T11:44:57Z
dc.description.abstractWhen applying aggregating strategies to Prediction with Expert Advice, the learning rate must be adaptively tuned. The natural choice of √complexity/current loss renders the analysis of Weighted Majority derivatives quite complicated. In particular, for
dc.identifier.isbn3540233563
dc.identifier.urihttp://hdl.handle.net/1885/58022
dc.publisherSpringer
dc.relation.ispartofseriesInternational Conference on Algorithmic Learning Theory (ALT 2004)
dc.rightsCopyright Information: © Springer-Verlag Berlin Heidelberg 2004. http://www.sherpa.ac.uk/romeo/issn/0302-9743/..."Author's post-print on any open access repository after 12 months after publication" from SHERPA/RoMEO site (as at 1/09/15).
dc.sourceAlgorithmic Learning Theory: 15th International Conference, ALT 2004, Pedova, Italy, October 2004, Proceedings
dc.source.urihttp://www.informatik.uni-trier.de/~ley/db/conf/alt/alt2004.html
dc.source.urihttp://springerlink.metapress.com/content/1fgled31qrluyh11/fulltext.pdf
dc.subjectKeywords: Computational complexity; Decision theory; Expert systems; Forecasting; Learning systems; Perturbation techniques; Polynomials; Problem solving; Set theory; Theorem proving; Adaptive learning rate; Prediction with expert advice (PEA); Random variables; Ra
dc.titlePrediction with Expert Advice by Following the Perturbed Leader for General Weights
dc.typeConference paper
local.bibliographicCitation.lastpage293
local.bibliographicCitation.startpage279
local.contributor.affiliationHutter, Marcus, College of Engineering and Computer Science, ANU
local.contributor.affiliationPoland, Jan, IDSIA-Istituto Dalle Molle di Studi sull Intelligenza Artificiale
local.contributor.authoremailu4350841@anu.edu.au
local.contributor.authoruidHutter, Marcus, u4350841
local.description.embargo2037-12-31
local.description.notesImported from ARIES
local.description.refereedYes
local.identifier.absfor080299 - Computation Theory and Mathematics not elsewhere classified
local.identifier.ariespublicationu8803936xPUB424
local.identifier.scopusID2-s2.0-21844436185
local.identifier.uidSubmittedByu8803936
local.type.statusPublished Version

Downloads

Original bundle
Now showing 1 - 1 of 1
No Thumbnail Available
Name:
01_Hutter_Prediction_with_Expert_Advice_2004.pdf
Size:
224.41 KB
Format:
Adobe Portable Document Format
Download

Collections

ANU Research Publications

DSpace software copyright © 2002-2024 LYRASIS