Logarithmic regret bound over diffusion based distributed estimation

Simple item page
dc.citation.epage8291en_US
dc.citation.spage8287en_US
dc.contributor.authorSayın, Muhammed O.en_US
dc.contributor.authorVanlı, Nuri Denizcanen_US
dc.contributor.authorKozat, Süleyman Serdaren_US
dc.coverage.spatialFlorence, Italyen_US
dc.date.accessioned2016-02-08T11:51:41Zen_US
dc.date.available2016-02-08T11:51:41Zen_US
dc.date.issued2014en_US
dc.departmentDepartment of Electrical and Electronics Engineeringen_US
dc.descriptionDate of Conference: 4-9 May 2014en_US
dc.descriptionConference Name: 39th International Conference on Acoustics, Speech and Signal Processing, IEEE 2014en_US
dc.description.abstractWe provide a logarithmic upper-bound on the regret function of the diffusion implementation for the distributed estimation. For certain learning rates, the bound shows guaranteed performance convergence of the distributed least mean square (DLMS) algorithms to the performance of the best estimation generated with hindsight of spatial and temporal data. We use a new cost definition for distributed estimation based on the widely-used statistical performance measures and the corresponding global regret function. Then, for certain learning rates, we provide an upper-bound on the global regret function without any statistical assumptions.en_US
dc.identifier.doi10.1109/ICASSP.2014.6855217en_US
dc.identifier.issn1520-6149en_US
dc.identifier.urihttp://hdl.handle.net/11693/27374
dc.language.isoEnglishen_US
dc.publisherIEEEen_US
dc.relation.isversionofhttps://doi.org/10.1109/ICASSP.2014.6855217en_US
dc.source.titleProceedings of the 39th International Conference on Acoustics, Speech and Signal Processing, IEEE 2014en_US
dc.subjectEstimationen_US
dc.subjectSignal processingen_US
dc.subjectCost definitionen_US
dc.subjectDistributeden_US
dc.subjectDistributed estimationen_US
dc.subjectGuaranteed performanceen_US
dc.subjectLearning ratesen_US
dc.subjectLeast mean squaresen_US
dc.subjectRegreten_US
dc.subjectStatistical performance measuresen_US
dc.subjectDiffusionen_US
dc.titleLogarithmic regret bound over diffusion based distributed estimationen_US
dc.typeConference Paperen_US

Files

Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
Logarithmic regret bound over diffusion based distributed estimation.pdf
Size:
110.86 KB
Format:
Adobe Portable Document Format
Description:
Full printable version
Download

Collections

Department of Electrical and Electronics Engineering