Show simple item record

dc.contributor.authorVanli, N.D.en_US
dc.contributor.authorSayin, M.O.en_US
dc.contributor.authorErgüt, S.en_US
dc.contributor.authorKozat, S.S.en_US
dc.date.accessioned2016-02-08T12:03:25Z
dc.date.available2016-02-08T12:03:25Z
dc.date.issued2014en_US
dc.identifier.issn22195491
dc.identifier.urihttp://hdl.handle.net/11693/27868
dc.description.abstractWe study the problem of sequential prediction of real-valued sequences under the squared error loss function. While refraining from any statistical and structural assumptions on the underlying sequence, we introduce a competitive approach to this problem and compare the performance of a sequential algorithm with respect to the large and continuous class of parametric predictors. We define the performance difference between a sequential algorithm and the best parametric predictor as regret, and introduce a guaranteed worst-case lower bounds to this relative performance measure. In particular, we prove that for any sequential algorithm, there always exists a sequence for which this regret is lower bounded by zero. We then extend this result by showing that the prediction problem can be transformed into a parameter estimation problem if the class of parametric predictors satisfy a certain property, and provide a comprehensive lower bound to this case. © 2014 EURASIP.en_US
dc.language.isoEnglishen_US
dc.source.titleEuropean Signal Processing Conferenceen_US
dc.subjectlower bounden_US
dc.subjectSequential predictionen_US
dc.subjectworst-case performanceen_US
dc.subjectForecastingen_US
dc.subjectSequential switchingen_US
dc.subjectSignal processingen_US
dc.subjectLower boundsen_US
dc.subjectParameter estimation problemsen_US
dc.subjectRelative performanceen_US
dc.subjectSequential algorithmen_US
dc.subjectSequential predictionen_US
dc.subjectSquared error loss functionsen_US
dc.subjectStructural assumptionen_US
dc.subjectWorst-case performanceen_US
dc.subjectParameter estimationen_US
dc.titleComprehensive lower bounds on sequential predictionen_US
dc.typeConference Paperen_US
dc.departmentDepartment of Electrical and Electronics Engineering
dc.citation.spage1193en_US
dc.citation.epage1196en_US
dc.publisherEuropean Signal Processing Conference, EUSIPCOen_US


Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record