An inexact successive quadratic approximation method for L-1 regularized optimization

Basit Öğe Kaydı
dc.authorwosidNocedal, Jorge/B-7255-2009
dc.authorwosidOztoprak, Figen/ABH-1969-2021
dc.contributor.authorByrd, Richard H.
dc.contributor.authorNocedal, Jorge
dc.contributor.authorOztoprak, Figen
dc.date.accessioned2024-07-18T20:40:38Z
dc.date.available2024-07-18T20:40:38Z
dc.date.issued2016
dc.departmentİstanbul Bilgi Üniversitesien_US
dc.description.abstractWe study a Newton-like method for the minimization of an objective function that is the sum of a smooth function and an regularization term. This method, which is sometimes referred to in the literature as a proximal Newton method, computes a step by minimizing a piecewise quadratic model of the objective function . In order to make this approach efficient in practice, it is imperative to perform this inner minimization inexactly. In this paper, we give inexactness conditions that guarantee global convergence and that can be used to control the local rate of convergence of the iteration. Our inexactness conditions are based on a semi-smooth function that represents a (continuous) measure of the optimality conditions of the problem, and that embodies the soft-thresholding iteration. We give careful consideration to the algorithm employed for the inner minimization, and report numerical results on two test sets originating in machine learning.en_US
dc.description.sponsorshipNational Science Foundation [DMS-1216554, DMS-0810213]; Department of Energy [DE-SC0001774]; ONR [N00014-14-1-0313 P00002]; US Department of Energy [DE-FG02-87ER25047]; Scientific and Technological Research Council of Turkey [113M500]; U.S. Department of Energy (DOE) [DE-FG02-87ER25047, DE-SC0001774] Funding Source: U.S. Department of Energy (DOE)en_US
dc.description.sponsorshipRichard H. Byrd was supported by National Science Foundation Grant DMS-1216554 and Department of Energy Grant DE-SC0001774.; Jorge Nocedal was supported by National Science Foundation Grant DMS-0810213, and by ONR Grant N00014-14-1-0313 P00002.; Figen Oztoprak was supported by US Department of Energy Grant DE-FG02-87ER25047 and by Scientific and Technological Research Council of Turkey Grant Number 113M500. Part of this work was completed while the author was at Istanbul Technical University.en_US
dc.identifier.doi10.1007/s10107-015-0941-y
dc.identifier.endpage396en_US
dc.identifier.issn0025-5610
dc.identifier.issn1436-4646
dc.identifier.issue2en_US
dc.identifier.scopus2-s2.0-84940213672en_US
dc.identifier.scopusqualityQ1en_US
dc.identifier.startpage375en_US
dc.identifier.urihttps://doi.org/10.1007/s10107-015-0941-y
dc.identifier.urihttps://hdl.handle.net/11411/7149
dc.identifier.volume157en_US
dc.identifier.wosWOS:000376925300003en_US
dc.identifier.wosqualityQ1en_US
dc.indekslendigikaynakWeb of Scienceen_US
dc.indekslendigikaynakScopusen_US
dc.language.isoenen_US
dc.publisherSpringer Heidelbergen_US
dc.relation.ispartofMathematical Programmingen_US
dc.relation.publicationcategoryMakale - Uluslararası Hakemli Dergi - Kurum Öğretim Elemanıen_US
dc.rightsinfo:eu-repo/semantics/closedAccessen_US
dc.subjectSparse Optimizationen_US
dc.subjectInexact Proximal Newtonen_US
dc.subjectOrthant-Based Quasi-Newtonen_US
dc.subjectNewtonen_US
dc.subjectSelectionen_US
dc.titleAn inexact successive quadratic approximation method for L-1 regularized optimization
dc.typeArticle

Dosyalar

Koleksiyon

Web of Science Indexed Publications
Scopus Indexed Publications