Show simple item record

dc.contributor.authorMonteleoni, Claire
dc.contributor.authorJaakkola, Tommi
dc.date.accessioned2019-10-23T23:19:29Z
dc.date.available2019-10-23T23:19:29Z
dc.date.created2017-01-05 00:28
dc.date.issued2005-12-22
dc.identifieroai:dspace.mit.edu:1721.1/30584
dc.identifierMIT-CSAIL-TR-2005-074
dc.identifierAIM-2005-032
dc.identifierhttp://hdl.handle.net/1721.1/30584
dc.identifier.urihttp://hdl.handle.net/20.500.12424/784311
dc.description.abstractWe consider an online learning scenario in which the learner can make predictions on the basis of a fixed set of experts. We derive upper and lower relative loss bounds for a class of universal learning algorithms involving a switching dynamics over the choice of the experts. On the basis of the performance bounds we provide the optimal a priori discretization of the switching-rate parameter that governs the switching dynamics. We demonstrate the algorithm in the context of wireless networks.
dc.format.medium8 p.
dc.languageen_US
dc.language.isoeng
dc.relation.ispartofMassachusetts Institute of Technology Computer Science and Artificial Intelligence Laboratory
dc.subjectAI
dc.subjectonline learning
dc.subjectregret bounds
dc.subjectnon-stationarity
dc.subjectHMM
dc.subjectwireless networks
dc.titleOnline Learning of Non-stationary Sequences
ge.collectioncodeOAIDATA
ge.dataimportlabelOAI metadata object
ge.identifier.legacyglobethics:10377635
ge.identifier.permalinkhttps://www.globethics.net/gel/10377635
ge.lastmodificationdate2017-01-05 00:28
ge.lastmodificationuseradmin@pointsoftware.ch (import)
ge.submissions0
ge.oai.exportid148934
ge.oai.repositoryid861
ge.oai.setnameCSAIL Technical Reports (July 1, 2003 - present)
ge.oai.setspechdl_1721.1_29807
ge.oai.streamid2
ge.setnameGlobeEthicsLib
ge.setspecglobeethicslib
ge.linkhttp://hdl.handle.net/1721.1/30584


This item appears in the following Collection(s)

Show simple item record