dc.contributor.author Vanlı, N. Denizcan en_US dc.contributor.author Sayın, Muhammed O. en_US dc.contributor.author Ergüt, S. en_US dc.contributor.author Kozat, Süleyman S. en_US dc.coverage.spatial Lisbon, Portugal dc.date.accessioned 2016-02-08T12:03:25Z dc.date.available 2016-02-08T12:03:25Z dc.date.issued 2014-09 en_US dc.identifier.issn 2219-5491 dc.identifier.uri http://hdl.handle.net/11693/27868 dc.description Date of Conference: 1-5 Sept. 2014 dc.description Conference name: 22nd European Signal Processing Conference (EUSIPCO) 2014 dc.description.abstract We 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. en_US dc.language.iso English en_US dc.source.title European Signal Processing Conference en_US dc.relation.isversionof https://ieeexplore.ieee.org/document/6952418 dc.subject Lower bound en_US dc.subject Sequential prediction en_US dc.subject Worst-case performance en_US dc.subject Forecasting en_US dc.subject Sequential switching en_US dc.subject Signal processing en_US dc.subject Parameter estimation problems en_US dc.subject Relative performance en_US dc.subject Sequential algorithm en_US dc.subject Sequential prediction en_US dc.subject Squared error loss functions en_US dc.subject Structural assumption en_US dc.subject Parameter estimation en_US dc.title Comprehensive lower bounds on sequential prediction en_US dc.type Conference Paper en_US dc.department Department of Electrical and Electronics Engineering en_US dc.citation.spage 1193 en_US dc.citation.epage 1196 en_US dc.publisher IEEE
﻿