Highly efficient nonlinear regression for big data with lexicographical splitting

dc.citation.epage398en_US
dc.citation.issueNumber3en_US
dc.citation.spage391en_US
dc.citation.volumeNumber11en_US
dc.contributor.authorNeyshabouri, M. M.en_US
dc.contributor.authorDemir, O.en_US
dc.contributor.authorDelibalta, I.en_US
dc.contributor.authorKozat, S. S.en_US
dc.date.accessioned2018-04-12T11:13:48Z
dc.date.available2018-04-12T11:13:48Z
dc.date.issued2017en_US
dc.departmentDepartment of Electrical and Electronics Engineeringen_US
dc.description.abstractThis paper considers the problem of online piecewise linear regression for big data applications. We introduce an algorithm, which sequentially achieves the performance of the best piecewise linear (affine) model with optimal partition of the space of the regressor vectors in an individual sequence manner. To this end, our algorithm constructs a class of 2 D sequential piecewise linear models over a set of partitions of the regressor space and efficiently combines them in the mixture-of-experts setting. We show that the algorithm is highly efficient with computational complexity of only O(mD2) , where m is the dimension of the regressor vectors. This efficient computational complexity is achieved by efficiently representing all of the 2 D models using a “lexicographical splitting graph.” We analyze the performance of our algorithm without any statistical assumptions, i.e., our results are guaranteed to hold. Furthermore, we demonstrate the effectiveness of our algorithm over the well-known data sets in the machine learning literature with computational complexity fraction of the state of the art.en_US
dc.description.provenanceMade available in DSpace on 2018-04-12T11:13:48Z (GMT). No. of bitstreams: 1 bilkent-research-paper.pdf: 179475 bytes, checksum: ea0bedeb05ac9ccfb983c327e155f0c2 (MD5) Previous issue date: 2017en
dc.identifier.doi10.1007/s11760-016-0972-8en_US
dc.identifier.issn1863-1703
dc.identifier.urihttp://hdl.handle.net/11693/37451
dc.language.isoEnglishen_US
dc.publisherSpringer Londonen_US
dc.relation.isversionofhttp://dx.doi.org/10.1007/s11760-016-0972-8en_US
dc.source.titleSignal, Image and Video Processingen_US
dc.subjectLexicographical splittingen_US
dc.subjectNonlinear regressionen_US
dc.subjectOnline learningen_US
dc.subjectPiecewise linearen_US
dc.titleHighly efficient nonlinear regression for big data with lexicographical splittingen_US
dc.typeArticleen_US

Files

Original bundle

Now showing 1 - 1 of 1
Loading...
Thumbnail Image
Name:
Highly efficient nonlinear regression for big data with lexicographical splitting.pdf
Size:
723.85 KB
Format:
Adobe Portable Document Format
Description:
Full printable version