On the number of iterations for the matching pursuit algorithm

Show simple item record

dc.contributor.author Li, F en
dc.contributor.author Triggs, Christopher en
dc.contributor.author Dumitrescu, B en
dc.contributor.author Giurcaneanu, Ciprian en
dc.coverage.spatial Kos, Greece en
dc.date.accessioned 2018-10-16T01:48:40Z en
dc.date.issued 2017 en
dc.identifier.isbn 978-0-9928626-7-1 en
dc.identifier.issn 2076-1465 en
dc.identifier.uri http://hdl.handle.net/2292/41954 en
dc.description.abstract We address the problem of selecting, from a given dictionary, a subset of predictors whose linear combination provides the best description for the vector of measurements. To this end, we apply the well-known matching pursuit algorithm (MPA). Even if there are theoretical results on the performance of MPA, there is no widely accepted rule for stopping the algorithm. In this work, we focus on stopping rules based on information theoretic criteria (ITC). The key point is to evaluate the degrees of freedom (df) for the model produced at each iteration. This is traditionally done by computing the trace of the hat matrix which maps the data vector to its estimate. We prove some theoretical results concerning the hat matrix. One of them provides an upper bound on the increase of df from the m-th to the (m + 1)-th iteration. Based on the properties of the hat matrix, we propose novel ITC for selecting the number of iterations. All of them are obtained by modifying criteria designed for variable selection in the classical linear model. For assessing the performance of the novel criteria, we conduct a simulation study. en
dc.publisher IEEE en
dc.relation.ispartof Eusipco 2017 en
dc.relation.ispartofseries Proceedings 25th European Signal Processing Conference en
dc.rights Items in ResearchSpace are protected by copyright, with all rights reserved, unless otherwise indicated. Previously published items are made available in accordance with the copyright policy of the publisher. en
dc.rights.uri https://researchspace.auckland.ac.nz/docs/uoa-docs/rights.htm en
dc.title On the number of iterations for the matching pursuit algorithm en
dc.type Conference Item en
dc.identifier.doi 10.23919/EUSIPCO.2017.8081193 en
pubs.begin-page 181 en
dc.rights.holder Copyright: The author en
pubs.author-url http://www.eurasip.org/Proceedings/Eusipco/Eusipco2017/papers/1570346793.pdf en
pubs.end-page 185 en
pubs.finish-date 2017-09-01 en
pubs.start-date 2017-08-29 en
dc.rights.accessrights http://purl.org/eprint/accessRights/RestrictedAccess en
pubs.subtype Proceedings en
pubs.elements-id 690087 en
pubs.org-id Science en
pubs.org-id Statistics en
pubs.record-created-at-source-date 2017-10-11 en
pubs.online-publication-date 2017-10-18 en

Files in this item

Find Full text

This item appears in the following Collection(s)

Show simple item record


Search ResearchSpace