Iterative Hessian Sketch with momentum

Simple item page
buir.contributor.authorÖzaslan, İbrahim Kurban
buir.contributor.authorArıkan, Orhan
buir.contributor.orcidArıkan, Orhan|0000-0002-3698-8888
dc.citation.epage7474en_US
dc.citation.spage7470en_US
dc.contributor.authorÖzaslan, İbrahim Kurbanen_US
dc.contributor.authorPilancı, M.en_US
dc.contributor.authorArıkan, Orhanen_US
dc.coverage.spatialBrighton, United Kingdomen_US
dc.date.accessioned2020-01-28T11:32:26Z
dc.date.available2020-01-28T11:32:26Z
dc.date.issued2019
dc.departmentDepartment of Electrical and Electronics Engineeringen_US
dc.descriptionDate of Conference: 12-17 May 2019en_US
dc.descriptionConference Name: 44th IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2019en_US
dc.description.abstractWe propose a novel randomized linear least squares solver which is an improvement of Iterative Hessian Sketch and randomized preconditioning. In the proposed Momentum-IHS technique (M-IHS), Heavy Ball Method is used to accelerate the convergence of iterations. It is shown that for any full rank data matrix, rate of convergence depends on the ratio between the feature size and the sketch size. Unlike the Conjugate Gradient technique, the rate of convergence is unaffected by either the condition number or the eigenvalue spectrum of the data matrix. As demonstrated over many examples, the proposed M-IHS provides compatible performance with the state of the art randomized preconditioning methods such as LSRN or Blendenpik and yet, it provides a completely different perspective in the area of iterative solvers which can pave the way for future developments.en_US
dc.description.provenanceSubmitted by Zeynep Aykut (zeynepay@bilkent.edu.tr) on 2020-01-28T11:32:26Z No. of bitstreams: 1 Iterative_hessian_sketch_with_momentum.pdf: 393100 bytes, checksum: 5a99f7fea3ccc562458ef3cf0b30223d (MD5)en
dc.description.provenanceMade available in DSpace on 2020-01-28T11:32:26Z (GMT). No. of bitstreams: 1 Iterative_hessian_sketch_with_momentum.pdf: 393100 bytes, checksum: 5a99f7fea3ccc562458ef3cf0b30223d (MD5) Previous issue date: 2019en
dc.description.sponsorshipThe Institute of Electrical and Electronics Engineers Signal Processing Societyen_US
dc.identifier.doi10.1109/ICASSP.2019.8682720en_US
dc.identifier.eisbn9781479981311
dc.identifier.eissn2379-190X
dc.identifier.isbn9781479981328
dc.identifier.issn1520-6149
dc.identifier.urihttp://hdl.handle.net/11693/52875
dc.language.isoEnglishen_US
dc.publisherInstitute of Electrical and Electronics Engineers Inc.en_US
dc.relation.isversionofhttps://dx.doi.org/10.1109/ICASSP.2019.8682720en_US
dc.source.titleProceedings of the 44th IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2019en_US
dc.subjectIterative Hessian Sketchen_US
dc.subjectMomentumen_US
dc.subjectRandomized preconditioningen_US
dc.subjectIll Conditionen_US
dc.subjectFirst order iterative solversen_US
dc.titleIterative Hessian Sketch with momentumen_US
dc.typeConference Paperen_US

Files

Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
Iterative_hessian_sketch_with_momentum.pdf
Size:
383.89 KB
Format:
Adobe Portable Document Format
Description:
View / Download
Download
License bundle
Now showing 1 - 1 of 1
No Thumbnail Available
Name:
license.txt
Size:
1.71 KB
Format:
Item-specific license agreed upon to submission
Description:
Download

Collections

Scholarly Publications - Electrical and Electronics Engineering