Academic Journal
View in EDS

Parallel and Distributed Methods for Constrained Nonconvex Optimization?Part I: Theory.

Bibliographic Details
Title: Parallel and Distributed Methods for Constrained Nonconvex Optimization?Part I: Theory.
Authors: Scutari, Gesualdo, Facchinei, Francisco, Lampariello, Lorenzo
Source: IEEE Transactions on Signal Processing; Apr2017, Vol. 65 Issue 8, p1929-1944, 16p
Subject Terms: Distributed algorithms, Distributed computing, Distributed computing management, Distributed computing software, Distributed computing equipment
Abstract: In this two-part paper, we propose a general algorithmic framework for the minimization of a nonconvex smooth function subject to nonconvex smooth constraints, and also consider extensions to some structured, nonsmooth problems. The algorithm solves a sequence of (separable) strongly convex problems and maintains feasibility at each iteration. Convergence to a stationary solution of the original nonconvex optimization is established. Our framework is very general and flexible and unifies several existing successive convex approximation (SCA)-based algorithms. More importantly, and differently from current SCA approaches, it naturally leads to distributed and parallelizable implementations for a large class of nonconvex problems. This Part I is devoted to the description of the framework in its generality. In Part II, we customize our general methods to several (multiagent) optimization problems in communications, networking, and machine learning; the result is a new class of centralized and distributed algorithms that compare favorably to existing ad-hoc (centralized) schemes. [ABSTRACT FROM PUBLISHER]
Copyright of IEEE Transactions on Signal Processing is the property of IEEE and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)
Database: Complementary Index
FullText Links:
  – Type: other
Text:
  Availability: 0
Header DbId: edb
DbLabel: Complementary Index
An: 124146017
RelevancyScore: 853
AccessLevel: 6
PubType: Academic Journal
PubTypeId: academicJournal
PreciseRelevancyScore: 853.472534179688
IllustrationInfo
Items – Name: Title
  Label: Title
  Group: Ti
  Data: Parallel and Distributed Methods for Constrained Nonconvex Optimization?Part I: Theory.
– Name: Author
  Label: Authors
  Group: Au
  Data: <searchLink fieldCode="AR" term="%22Scutari%2C+Gesualdo%22">Scutari, Gesualdo</searchLink><br /><searchLink fieldCode="AR" term="%22Facchinei%2C+Francisco%22">Facchinei, Francisco</searchLink><br /><searchLink fieldCode="AR" term="%22Lampariello%2C+Lorenzo%22">Lampariello, Lorenzo</searchLink>
– Name: TitleSource
  Label: Source
  Group: Src
  Data: IEEE Transactions on Signal Processing; Apr2017, Vol. 65 Issue 8, p1929-1944, 16p
– Name: Subject
  Label: Subject Terms
  Group: Su
  Data: <searchLink fieldCode="DE" term="%22Distributed+algorithms%22">Distributed algorithms</searchLink><br /><searchLink fieldCode="DE" term="%22Distributed+computing%22">Distributed computing</searchLink><br /><searchLink fieldCode="DE" term="%22Distributed+computing+management%22">Distributed computing management</searchLink><br /><searchLink fieldCode="DE" term="%22Distributed+computing+software%22">Distributed computing software</searchLink><br /><searchLink fieldCode="DE" term="%22Distributed+computing+equipment%22">Distributed computing equipment</searchLink>
– Name: Abstract
  Label: Abstract
  Group: Ab
  Data: In this two-part paper, we propose a general algorithmic framework for the minimization of a nonconvex smooth function subject to nonconvex smooth constraints, and also consider extensions to some structured, nonsmooth problems. The algorithm solves a sequence of (separable) strongly convex problems and maintains feasibility at each iteration. Convergence to a stationary solution of the original nonconvex optimization is established. Our framework is very general and flexible and unifies several existing successive convex approximation (SCA)-based algorithms. More importantly, and differently from current SCA approaches, it naturally leads to distributed and parallelizable implementations for a large class of nonconvex problems. This Part I is devoted to the description of the framework in its generality. In Part II, we customize our general methods to several (multiagent) optimization problems in communications, networking, and machine learning; the result is a new class of centralized and distributed algorithms that compare favorably to existing ad-hoc (centralized) schemes. [ABSTRACT FROM PUBLISHER]
– Name: Abstract
  Label:
  Group: Ab
  Data: <i>Copyright of IEEE Transactions on Signal Processing is the property of IEEE and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract.</i> (Copyright applies to all Abstracts.)
PLink https://search.ebscohost.com/login.aspx?direct=true&site=eds-live&db=edb&AN=124146017
RecordInfo BibRecord:
  BibEntity:
    Identifiers:
      – Type: doi
        Value: 10.1109/TSP.2016.2637317
    Languages:
      – Code: eng
        Text: English
    PhysicalDescription:
      Pagination:
        PageCount: 16
        StartPage: 1929
    Subjects:
      – SubjectFull: Distributed algorithms
        Type: general
      – SubjectFull: Distributed computing
        Type: general
      – SubjectFull: Distributed computing management
        Type: general
      – SubjectFull: Distributed computing software
        Type: general
      – SubjectFull: Distributed computing equipment
        Type: general
    Titles:
      – TitleFull: Parallel and Distributed Methods for Constrained Nonconvex Optimization?Part I: Theory.
        Type: main
  BibRelationships:
    HasContributorRelationships:
      – PersonEntity:
          Name:
            NameFull: Scutari, Gesualdo
      – PersonEntity:
          Name:
            NameFull: Facchinei, Francisco
      – PersonEntity:
          Name:
            NameFull: Lampariello, Lorenzo
    IsPartOfRelationships:
      – BibEntity:
          Dates:
            – D: 15
              M: 04
              Text: Apr2017
              Type: published
              Y: 2017
          Identifiers:
            – Type: issn-print
              Value: 1053587X
          Numbering:
            – Type: volume
              Value: 65
            – Type: issue
              Value: 8
          Titles:
            – TitleFull: IEEE Transactions on Signal Processing
              Type: main
ResultId 1