Adaptive mixture methods based on Bregman divergences

Simple item page
dc.citation.epage97en_US
dc.citation.issueNumber1en_US
dc.citation.spage86en_US
dc.citation.volumeNumber23en_US
dc.contributor.authorDonmez, M. A.en_US
dc.contributor.authorInan, H. A.en_US
dc.contributor.authorKozat, S. S.en_US
dc.date.accessioned2016-02-08T09:41:50Z
dc.date.available2016-02-08T09:41:50Z
dc.date.issued2013en_US
dc.departmentDepartment of Electrical and Electronics Engineeringen_US
dc.description.abstractWe investigate adaptive mixture methods that linearly combine outputs of m constituent filters running in parallel to model a desired signal. We use Bregman divergences and obtain certain multiplicative updates to train the linear combination weights under an affine constraint or without any constraints. We use unnormalized relative entropy and relative entropy to define two different Bregman divergences that produce an unnormalized exponentiated gradient update and a normalized exponentiated gradient update on the mixture weights, respectively. We then carry out the mean and the mean-square transient analysis of these adaptive algorithms when they are used to combine outputs of m constituent filters. We illustrate the accuracy of our results and demonstrate the effectiveness of these updates for sparse mixture systems.en_US
dc.description.provenanceMade available in DSpace on 2016-02-08T09:41:50Z (GMT). No. of bitstreams: 1 bilkent-research-paper.pdf: 70227 bytes, checksum: 26e812c6f5156f83f0e77b261a471b5a (MD5) Previous issue date: 2013en
dc.identifier.doi10.1016/j.dsp.2012.09.006en_US
dc.identifier.issn1051-2004
dc.identifier.urihttp://hdl.handle.net/11693/21144
dc.language.isoEnglishen_US
dc.publisherElsevieren_US
dc.relation.isversionofhttp://dx.doi.org/10.1016/j.dsp.2012.09.006en_US
dc.source.titleDigital Signal Processing: A Review Journalen_US
dc.subjectAdaptive mixtureen_US
dc.subjectAffine mixtureen_US
dc.subjectBregman divergenceen_US
dc.subjectMultiplicative updateen_US
dc.subjectAffine Constraintsen_US
dc.subjectBregman divergencesen_US
dc.subjectDesired signalen_US
dc.subjectLinear combinationsen_US
dc.subjectMean-squareen_US
dc.subjectMixture methoden_US
dc.subjectMultiplicative updatesen_US
dc.subjectRelative entropyen_US
dc.subjectRunning-inen_US
dc.subjectAdaptive algorithmsen_US
dc.subjectEntropyen_US
dc.subjectMixturesen_US
dc.titleAdaptive mixture methods based on Bregman divergencesen_US
dc.typeArticleen_US

Files

Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
Adaptive mixture methods based on Bregman divergences.pdf
Size:
1.61 MB
Format:
Adobe Portable Document Format
Description:
Full Printable Version
Download

Collections

Department of Electrical and Electronics Engineering