Show simple item record

dc.contributor.authorBianchi, Pascal
dc.contributor.authorHachem, Walid
dc.contributor.authorSalim, Adil
dc.date.accessioned2020-07-23T09:31:23Z
dc.date.available2020-07-23T09:31:23Z
dc.date.issued2020-07-14
dc.date.submitted2019-08-19
dc.identifier.citationBianchi, P., Hachem, W., & Salim, A. (2020). A fully stochastic primal-dual algorithm. Optimization Letters. doi:10.1007/s11590-020-01614-y
dc.identifier.issn1862-4480
dc.identifier.issn1862-4472
dc.identifier.doi10.1007/s11590-020-01614-y
dc.identifier.urihttp://hdl.handle.net/10754/664383
dc.description.abstractA new stochastic primal-dual algorithm for solving a composite optimization problem is proposed. It is assumed that all the functions / operators that enter the optimization problem are given as statistical expectations. These expectations are unknown but revealed across time through i.i.d realizations. The proposed algorithm is proven to converge to a saddle point of the Lagrangian function. In the framework of the monotone operator theory, the convergence proof relies on recent results on the stochastic Forward Backward algorithm involving random monotone operators. An example of convex optimization under stochastic linear constraints is considered.
dc.publisherSpringer Science and Business Media LLC
dc.relation.urlhttp://link.springer.com/10.1007/s11590-020-01614-y
dc.relation.urlhttp://arxiv.org/pdf/1901.08170
dc.rightsArchived with thanks to Optimization Letters
dc.rightsThis file is an open access version redistributed from: http://arxiv.org/pdf/1901.08170
dc.titleA fully stochastic primal-dual algorithm
dc.typeArticle
dc.contributor.departmentVisual Computing Center (VCC)
dc.contributor.departmentComputer, Electrical and Mathematical Sciences and Engineering (CEMSE) Division
dc.identifier.journalOptimization Letters
dc.rights.embargodate2021-07-14
dc.eprint.versionPost-print
dc.contributor.institutionLTCI, Télécom Paris, IP Paris, 75013, Paris, France
dc.contributor.institutionLIGM, CNRS, University Gustave Eiffel, 77454, Marne-la-Vallée, France
dc.identifier.arxivid1901.08170
kaust.personSalim, Adil
dc.date.accepted2020-06-29
dc.identifier.eid2-s2.0-85087936962
refterms.dateFOA2022-12-07T13:59:07Z
dc.date.published-online2020-07-14
dc.date.published-print2021-03


Files in this item

Thumbnail
Name:
1901.08170.pdf
Size:
180.9Kb
Format:
PDF
Description:
Accepted Manuscript

This item appears in the following Collection(s)

Show simple item record