View in EDS

CoCoA: A General Framework for Communication-Efficient Distributed Optimization.

Saved in:
Bibliographic Details
Title: CoCoA: A General Framework for Communication-Efficient Distributed Optimization.
Authors: Smith, Virginia1 SMITHV@STANFORD.EDU, Forte, Simone2 SIMONE.FORTE@GESS.ETHZ.CH, Chenxin Ma3 CHM514@LEHIGH.EDU, Takáč, Martin3 TAKAC.MT@GMAIL.COM, Jordan, Michael I.4 JORDAN@CS.BERKELEY.EDU, Jaggi, Martin5 MARTIN.JAGGI@EPFL.CH
Source: Journal of Machine Learning Research. 2018, Vol. 18 Issue 154-234, p1-49. 49p.
Subjects: Machine learning, Mathematical optimization, Convex functions, Stochastic convergence, Mathematical regularization
Abstract: The scale of modern datasets necessitates the development of efficient distributed optimization methods for machine learning. We present a general-purpose framework for distributed computing environments, CoCoA, that has an efficient communication scheme and is applicable to a wide variety of problems in machine learning and signal processing. We extend the framework to cover general non-strongly-convex regularizers, including L1-regularized problems like lasso, sparse logistic regression, and elastic net regularization, and show how earlier work can be derived as a special case. We provide convergence guarantees for the class of convex regularized loss minimization objectives, leveraging a novel approach in handling non-strongly-convex regularizers and non-smooth loss functions. The resulting framework has markedly improved performance over state-of-the-art methods, as we illustrate with an extensive set of experiments on real distributed datasets. [ABSTRACT FROM AUTHOR]
Copyright of Journal of Machine Learning Research is the property of Microtome Publishing 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: Engineering Source
FullText Text:
  Availability: 0
Header DbId: egs
DbLabel: Engineering Source
An: 131240443
AccessLevel: 6
PubType: Academic Journal
PubTypeId: academicJournal
PreciseRelevancyScore: 0
IllustrationInfo
Items – Name: Title
  Label: Title
  Group: Ti
  Data: CoCoA: A General Framework for Communication-Efficient Distributed Optimization.
– Name: Author
  Label: Authors
  Group: Au
  Data: <searchLink fieldCode="AR" term="%22Smith%2C+Virginia%22">Smith, Virginia</searchLink><relatesTo>1</relatesTo><i> SMITHV@STANFORD.EDU</i><br /><searchLink fieldCode="AR" term="%22Forte%2C+Simone%22">Forte, Simone</searchLink><relatesTo>2</relatesTo><i> SIMONE.FORTE@GESS.ETHZ.CH</i><br /><searchLink fieldCode="AR" term="%22Chenxin+Ma%22">Chenxin Ma</searchLink><relatesTo>3</relatesTo><i> CHM514@LEHIGH.EDU</i><br /><searchLink fieldCode="AR" term="%22Takáč%2C+Martin%22">Takáč, Martin</searchLink><relatesTo>3</relatesTo><i> TAKAC.MT@GMAIL.COM</i><br /><searchLink fieldCode="AR" term="%22Jordan%2C+Michael+I%2E%22">Jordan, Michael I.</searchLink><relatesTo>4</relatesTo><i> JORDAN@CS.BERKELEY.EDU</i><br /><searchLink fieldCode="AR" term="%22Jaggi%2C+Martin%22">Jaggi, Martin</searchLink><relatesTo>5</relatesTo><i> MARTIN.JAGGI@EPFL.CH</i>
– Name: TitleSource
  Label: Source
  Group: Src
  Data: <searchLink fieldCode="JN" term="%22Journal+of+Machine+Learning+Research%22">Journal of Machine Learning Research</searchLink>. 2018, Vol. 18 Issue 154-234, p1-49. 49p.
– Name: Subject
  Label: Subjects
  Group: Su
  Data: <searchLink fieldCode="DE" term="%22Machine+learning%22">Machine learning</searchLink><br /><searchLink fieldCode="DE" term="%22Mathematical+optimization%22">Mathematical optimization</searchLink><br /><searchLink fieldCode="DE" term="%22Convex+functions%22">Convex functions</searchLink><br /><searchLink fieldCode="DE" term="%22Stochastic+convergence%22">Stochastic convergence</searchLink><br /><searchLink fieldCode="DE" term="%22Mathematical+regularization%22">Mathematical regularization</searchLink>
– Name: Abstract
  Label: Abstract
  Group: Ab
  Data: The scale of modern datasets necessitates the development of efficient distributed optimization methods for machine learning. We present a general-purpose framework for distributed computing environments, CoCoA, that has an efficient communication scheme and is applicable to a wide variety of problems in machine learning and signal processing. We extend the framework to cover general non-strongly-convex regularizers, including L1-regularized problems like lasso, sparse logistic regression, and elastic net regularization, and show how earlier work can be derived as a special case. We provide convergence guarantees for the class of convex regularized loss minimization objectives, leveraging a novel approach in handling non-strongly-convex regularizers and non-smooth loss functions. The resulting framework has markedly improved performance over state-of-the-art methods, as we illustrate with an extensive set of experiments on real distributed datasets. [ABSTRACT FROM AUTHOR]
– Name: AbstractSuppliedCopyright
  Label:
  Group: Ab
  Data: <i>Copyright of Journal of Machine Learning Research is the property of Microtome Publishing 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=egs&AN=131240443
RecordInfo BibRecord:
  BibEntity:
    Languages:
      – Code: eng
        Text: English
    PhysicalDescription:
      Pagination:
        PageCount: 49
        StartPage: 1
    Subjects:
      – SubjectFull: Machine learning
        Type: general
      – SubjectFull: Mathematical optimization
        Type: general
      – SubjectFull: Convex functions
        Type: general
      – SubjectFull: Stochastic convergence
        Type: general
      – SubjectFull: Mathematical regularization
        Type: general
    Titles:
      – TitleFull: CoCoA: A General Framework for Communication-Efficient Distributed Optimization.
        Type: main
  BibRelationships:
    HasContributorRelationships:
      – PersonEntity:
          Name:
            NameFull: Smith, Virginia
      – PersonEntity:
          Name:
            NameFull: Forte, Simone
      – PersonEntity:
          Name:
            NameFull: Chenxin Ma
      – PersonEntity:
          Name:
            NameFull: Takáč, Martin
      – PersonEntity:
          Name:
            NameFull: Jordan, Michael I.
      – PersonEntity:
          Name:
            NameFull: Jaggi, Martin
    IsPartOfRelationships:
      – BibEntity:
          Dates:
            – D: 01
              M: 08
              Text: 2018
              Type: published
              Y: 2018
          Identifiers:
            – Type: issn-print
              Value: 15324435
          Numbering:
            – Type: volume
              Value: 18
            – Type: issue
              Value: 154-234
          Titles:
            – TitleFull: Journal of Machine Learning Research
              Type: main
ResultId 1