Master algorithms for active experts problems based on increasing loss values

dc.contributor.authorPoland, Jan
dc.contributor.authorHutter, Marcus
dc.date.accessioned2015-09-01T04:52:46Z
dc.date.available2015-09-01T04:52:46Z
dc.description.abstractWe specify an experts algorithm with the following characteristics: (a) it uses only feedback from the actions actually chosen (bandit setup), (b) it can be applied with countably infinite expert classes, and (c) it copes with losses that may grow in time appropriately slowly. We prove loss bounds against an adaptive adversary. From this, we obtain master algorithms for ``active experts problems'', which means that the master's actions may influence the behavior of the adversary. Our algorithm can significantly outperform standard experts algorithms on such problems. Finally, we combine it with a universal expert class. This results in a (computationally infeasible) universal master algorithm which performs - in a certain sense - almost as well as any computable strategy, for any online problem.en_AU
dc.identifier.issn0929-0672en_AU
dc.identifier.urihttp://hdl.handle.net/1885/15052
dc.publisherBelgian-Dutch Conference on Machine Learning (Benelearn)en_AU
dc.relation.ispartofProceedings of the 14th Dutch-Belgium Conference on Machine Learning Benelearn'05en_AU
dc.rights© The Author(s)en_AU
dc.subjectPrediction with expert adviceen_AU
dc.subjectresponsive environmentsen_AU
dc.subjectpartial observation gameen_AU
dc.subjectuniversal learningen_AU
dc.subjectasymptotic optimalityen_AU
dc.titleMaster algorithms for active experts problems based on increasing loss valuesen_AU
dc.typeConference paperen_AU
local.bibliographicCitation.lastpage66en_AU
local.bibliographicCitation.startpage59en_AU
local.contributor.affiliationHutter, M., Research School of Computer Science, The Australian National Universityen_AU
local.contributor.authoremailmarcus.hutter@anu.edu.auen_AU
local.contributor.authoruidu4350841en_AU
local.identifier.uidSubmittedByu1005913en_AU
local.type.statusAccepted Versionen_AU

Downloads

Original bundle

Now showing 1 - 1 of 1
Loading...
Thumbnail Image
Name:
Poland and Hutter Master Algorithms for Active Experts Problems 2005.pdf
Size:
219.37 KB
Format:
Adobe Portable Document Format
Description:

License bundle

Now showing 1 - 1 of 1
No Thumbnail Available
Name:
license.txt
Size:
884 B
Format:
Item-specific license agreed upon to submission
Description:
Back to topicon-arrow-up-solid
 
APRU
IARU
 
edX
Group of Eight Member

Acknowledgement of Country

The Australian National University acknowledges, celebrates and pays our respects to the Ngunnawal and Ngambri people of the Canberra region and to all First Nations Australians on whose traditional lands we meet and work, and whose cultures are among the oldest continuing cultures in human history.


Contact ANUCopyrightDisclaimerPrivacyFreedom of Information

+61 2 6125 5111 The Australian National University, Canberra

TEQSA Provider ID: PRV12002 (Australian University) CRICOS Provider Code: 00120C ABN: 52 234 063 906