Academic Journal

Wasserstein Barycenters can be Computed in Polynomial Time in Fixed Dimension.

Λεπτομέρειες βιβλιογραφικής εγγραφής
Τίτλος: Wasserstein Barycenters can be Computed in Polynomial Time in Fixed Dimension.
Συγγραφείς: Altschulerá, Jason M.1 JASONALT@MIT.EDU, Boix-Adser, Enric1 EBOIX@MIT.EDU
Πηγή: Journal of Machine Learning Research. 2021, Vol. 22, p1-19. 19p.
Θεματικοί όροι: Computational geometry, Polynomial time algorithms, Machine learning, Computer graphics
Περίληψη: Computing Wasserstein barycenters is a fundamental geometric problem with widespread applications in machine learning, statistics, and computer graphics. However, it is unknown whether Wasserstein barycenters can be computed in polynomial time, either exactly or to high precision (i.e., with polylog(1~") runtime dependence). This paper answers these questions in the affirmative for any fixed dimension. Our approach is to solve an exponential-size linear programming formulation by efficiently implementing the corresponding separation oracle using techniques from computational geometry. [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.)
Βάση Δεδομένων: Business Source Index
FullText Text:
  Availability: 0
CustomLinks:
  – Url: https://resolver.ebsco.com/c/fiv2js/result?sid=EBSCO:bsx&genre=article&issn=15324435&ISBN=&volume=22&issue=&date=20210101&spage=1&pages=1-19&title=Journal of Machine Learning Research&atitle=Wasserstein%20Barycenters%20can%20be%20Computed%20in%20Polynomial%20Time%20in%20Fixed%20Dimension.&aulast=Altschuler%C3%A1%2C%20Jason%20M.&id=DOI:
    Name: Full Text Finder (for New FTF UI) (ns324271)
    Category: fullText
    Text: Full Text Finder
    MouseOverText: Full Text Finder
Header DbId: bsx
DbLabel: Business Source Index
An: 155404632
RelevancyScore: 1239
AccessLevel: 6
PubType: Academic Journal
PubTypeId: academicJournal
PreciseRelevancyScore: 1239.40942382813
IllustrationInfo
Items – Name: Title
  Label: Title
  Group: Ti
  Data: Wasserstein Barycenters can be Computed in Polynomial Time in Fixed Dimension.
– Name: Author
  Label: Authors
  Group: Au
  Data: <searchLink fieldCode="AR" term="%22Altschulerá%2C+Jason+M%2E%22">Altschulerá, Jason M.</searchLink><relatesTo>1</relatesTo><i> JASONALT@MIT.EDU</i><br /><searchLink fieldCode="AR" term="%22Boix-Adser%2C+Enric%22">Boix-Adser, Enric</searchLink><relatesTo>1</relatesTo><i> EBOIX@MIT.EDU</i>
– Name: TitleSource
  Label: Source
  Group: Src
  Data: <searchLink fieldCode="JN" term="%22Journal+of+Machine+Learning+Research%22">Journal of Machine Learning Research</searchLink>. 2021, Vol. 22, p1-19. 19p.
– Name: Subject
  Label: Subject Terms
  Group: Su
  Data: <searchLink fieldCode="DE" term="%22Computational+geometry%22">Computational geometry</searchLink><br /><searchLink fieldCode="DE" term="%22Polynomial+time+algorithms%22">Polynomial time algorithms</searchLink><br /><searchLink fieldCode="DE" term="%22Machine+learning%22">Machine learning</searchLink><br /><searchLink fieldCode="DE" term="%22Computer+graphics%22">Computer graphics</searchLink>
– Name: Abstract
  Label: Abstract
  Group: Ab
  Data: Computing Wasserstein barycenters is a fundamental geometric problem with widespread applications in machine learning, statistics, and computer graphics. However, it is unknown whether Wasserstein barycenters can be computed in polynomial time, either exactly or to high precision (i.e., with polylog(1~") runtime dependence). This paper answers these questions in the affirmative for any fixed dimension. Our approach is to solve an exponential-size linear programming formulation by efficiently implementing the corresponding separation oracle using techniques from computational geometry. [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=bsx&AN=155404632
RecordInfo BibRecord:
  BibEntity:
    Languages:
      – Code: eng
        Text: English
    PhysicalDescription:
      Pagination:
        PageCount: 19
        StartPage: 1
    Subjects:
      – SubjectFull: Computational geometry
        Type: general
      – SubjectFull: Polynomial time algorithms
        Type: general
      – SubjectFull: Machine learning
        Type: general
      – SubjectFull: Computer graphics
        Type: general
    Titles:
      – TitleFull: Wasserstein Barycenters can be Computed in Polynomial Time in Fixed Dimension.
        Type: main
  BibRelationships:
    HasContributorRelationships:
      – PersonEntity:
          Name:
            NameFull: Altschulerá, Jason M.
      – PersonEntity:
          Name:
            NameFull: Boix-Adser, Enric
    IsPartOfRelationships:
      – BibEntity:
          Dates:
            – D: 01
              M: 01
              Text: 2021
              Type: published
              Y: 2021
          Identifiers:
            – Type: issn-print
              Value: 15324435
          Numbering:
            – Type: volume
              Value: 22
          Titles:
            – TitleFull: Journal of Machine Learning Research
              Type: main
ResultId 1