Zobraziť v EDS

Optimal sampling in unbiased active learning

Uložené v:
Podrobná bibliografia
Názov: Optimal sampling in unbiased active learning
Autori: Imberg, Henrik, 1991, Jonasson, Johan, 1966, Axelson-Fisk, Marina, 1972
Zdroj: Statistical sampling in machine learning 23rd International Conference on Artificial Intelligence and Statistics (AISTATS), Online Proceedings of Machine Learning Research. 108:559-569
Predmety: Optimal design, Weighted loss, Sampling weights, Generalised linear models, Unequal probability sampling, Active learning
Popis: A common belief in unbiased active learning is that, in order to capture the most informative instances, the sampling probabilities should be proportional to the uncertainty of the class labels. We argue that this produces suboptimal predictions and present sampling schemes for unbiased pool-based active learning that minimise the actual prediction error, and demonstrate a better predictive performance than competing methods on a number of benchmark datasets. In contrast, both probabilistic and deterministic uncertainty sampling performed worse than simple random sampling on some of the datasets.
Popis súboru: electronic
Prístupová URL adresa: https://research.chalmers.se/publication/536361
https://research.chalmers.se/publication/520253
https://research.chalmers.se/publication/519957
http://proceedings.mlr.press/v108/imberg20a/imberg20a.pdf
Databáza: SwePub
FullText Text:
  Availability: 0
CustomLinks:
  – Url: https://research.chalmers.se/publication/536361#
    Name: EDS - SwePub (s4221598)
    Category: fullText
    Text: View record in SwePub
  – Url: https://resolver.ebscohost.com/openurl?sid=EBSCO:edsswe&genre=article&issn=26403498&ISBN=&volume=108&issue=&date=20200101&spage=559&pages=559-569&title=Statistical sampling in machine learning 23rd International Conference on Artificial Intelligence and Statistics (AISTATS), Online Proceedings of Machine Learning Research&atitle=Optimal%20sampling%20in%20unbiased%20active%20learning&aulast=Imberg%2C%20Henrik&id=DOI:
    Name: Full Text Finder
    Category: fullText
    Text: Full Text Finder
    Icon: https://imageserver.ebscohost.com/branding/images/FTF.gif
    MouseOverText: Full Text Finder
  – Url: https://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=EBSCO&SrcAuth=EBSCO&DestApp=WOS&ServiceName=TransferToWoS&DestLinkType=GeneralSearchSummary&Func=Links&author=Imberg%20H
    Name: ISI
    Category: fullText
    Text: Nájsť tento článok vo Web of Science
    Icon: https://imagesrvr.epnet.com/ls/20docs.gif
    MouseOverText: Nájsť tento článok vo Web of Science
Header DbId: edsswe
DbLabel: SwePub
An: edsswe.oai.research.chalmers.se.53697c5a.3025.4aa0.90a9.a6ec8b31f08b
RelevancyScore: 909
AccessLevel: 6
PubType: Conference
PubTypeId: conference
PreciseRelevancyScore: 909.1474609375
IllustrationInfo
Items – Name: Title
  Label: Title
  Group: Ti
  Data: Optimal sampling in unbiased active learning
– Name: Author
  Label: Authors
  Group: Au
  Data: <searchLink fieldCode="AR" term="%22Imberg%2C+Henrik%22">Imberg, Henrik</searchLink>, 1991<br /><searchLink fieldCode="AR" term="%22Jonasson%2C+Johan%22">Jonasson, Johan</searchLink>, 1966<br /><searchLink fieldCode="AR" term="%22Axelson-Fisk%2C+Marina%22">Axelson-Fisk, Marina</searchLink>, 1972
– Name: TitleSource
  Label: Source
  Group: Src
  Data: <i>Statistical sampling in machine learning 23rd International Conference on Artificial Intelligence and Statistics (AISTATS), Online Proceedings of Machine Learning Research</i>. 108:559-569
– Name: Subject
  Label: Subject Terms
  Group: Su
  Data: <searchLink fieldCode="DE" term="%22Optimal+design%22">Optimal design</searchLink><br /><searchLink fieldCode="DE" term="%22Weighted+loss%22">Weighted loss</searchLink><br /><searchLink fieldCode="DE" term="%22Sampling+weights%22">Sampling weights</searchLink><br /><searchLink fieldCode="DE" term="%22Generalised+linear+models%22">Generalised linear models</searchLink><br /><searchLink fieldCode="DE" term="%22Unequal+probability+sampling%22">Unequal probability sampling</searchLink><br /><searchLink fieldCode="DE" term="%22Active+learning%22">Active learning</searchLink>
– Name: Abstract
  Label: Description
  Group: Ab
  Data: A common belief in unbiased active learning is that, in order to capture the most informative instances, the sampling probabilities should be proportional to the uncertainty of the class labels. We argue that this produces suboptimal predictions and present sampling schemes for unbiased pool-based active learning that minimise the actual prediction error, and demonstrate a better predictive performance than competing methods on a number of benchmark datasets. In contrast, both probabilistic and deterministic uncertainty sampling performed worse than simple random sampling on some of the datasets.
– Name: Format
  Label: File Description
  Group: SrcInfo
  Data: electronic
– Name: URL
  Label: Access URL
  Group: URL
  Data: <link linkTarget="URL" linkTerm="https://research.chalmers.se/publication/536361" linkWindow="_blank">https://research.chalmers.se/publication/536361</link><br /><link linkTarget="URL" linkTerm="https://research.chalmers.se/publication/520253" linkWindow="_blank">https://research.chalmers.se/publication/520253</link><br /><link linkTarget="URL" linkTerm="https://research.chalmers.se/publication/519957" linkWindow="_blank">https://research.chalmers.se/publication/519957</link><br /><link linkTarget="URL" linkTerm="http://proceedings.mlr.press/v108/imberg20a/imberg20a.pdf" linkWindow="_blank">http://proceedings.mlr.press/v108/imberg20a/imberg20a.pdf</link>
PLink https://erproxy.cvtisr.sk/sfx/access?url=https://search.ebscohost.com/login.aspx?direct=true&site=eds-live&db=edsswe&AN=edsswe.oai.research.chalmers.se.53697c5a.3025.4aa0.90a9.a6ec8b31f08b
RecordInfo BibRecord:
  BibEntity:
    Languages:
      – Text: English
    PhysicalDescription:
      Pagination:
        PageCount: 11
        StartPage: 559
    Subjects:
      – SubjectFull: Optimal design
        Type: general
      – SubjectFull: Weighted loss
        Type: general
      – SubjectFull: Sampling weights
        Type: general
      – SubjectFull: Generalised linear models
        Type: general
      – SubjectFull: Unequal probability sampling
        Type: general
      – SubjectFull: Active learning
        Type: general
    Titles:
      – TitleFull: Optimal sampling in unbiased active learning
        Type: main
  BibRelationships:
    HasContributorRelationships:
      – PersonEntity:
          Name:
            NameFull: Imberg, Henrik
      – PersonEntity:
          Name:
            NameFull: Jonasson, Johan
      – PersonEntity:
          Name:
            NameFull: Axelson-Fisk, Marina
    IsPartOfRelationships:
      – BibEntity:
          Dates:
            – D: 01
              M: 01
              Type: published
              Y: 2020
          Identifiers:
            – Type: issn-print
              Value: 26403498
            – Type: issn-locals
              Value: SWEPUB_FREE
            – Type: issn-locals
              Value: CTH_SWEPUB
          Numbering:
            – Type: volume
              Value: 108
          Titles:
            – TitleFull: Statistical sampling in machine learning 23rd International Conference on Artificial Intelligence and Statistics (AISTATS), Online Proceedings of Machine Learning Research
              Type: main
ResultId 1