Theory choice, non-epistemic values, and machine learning.

I use a theorem from machine learning, called the "No Free Lunch" theorem (NFL) to support the claim that non-epistemic values are essential to theory choice. I argue that NFL entails that predictive accuracy is insufficient to favor a given theory over others, and that NFL challenges our ability to...

Descripción completa

Detalles Bibliográficos
Publicado en:Synthese Vol. 198; no. 11; pp. 11081 - 11102
Autor principal: Dotan, Ravit
Formato: Artículo
Publicado: Springer Nature Nov2021
Materias:
Acceso en línea:Ver este registro en EBSCOhost
fields @attributes:
  recordID: 1
pdfLink:
plink: https://search.ebscohost.com/login.aspx?direct=true&db=hlh&AN=152624466&site=ehost-live
header:
  @attributes:
    shortDbName: hlh
    uiTerm: 152624466
    longDbName: Humanities International Complete
    uiTag: AN
  controlInfo:
    bkinfo:
    jinfo:
      jid:
        00397857
        4LI
      jtl: Synthese
      issn: 00397857
      maglogo: N
    pubinfo:
      dt: Nov2021
      vid: 198
      iid: 11
      pid: 237
      pub: Springer Nature
    artinfo:
      ui:
        152624466
        10.1007/s11229-020-02773-2
      ppf: 11081
      ppct: 21
      formats:
        fmt:
          @attributes:
            type: P
            size: 362KB
      tig:
        atl: Theory choice, non-epistemic values, and machine learning.
      aug:
        au: Dotan, Ravit
        affil: UC Berkeley (Philosophy), Berkeley, CA, USA
      su:
        National Football League
        Machine learning
        Virtue epistemology
        Machine theory
        Philosophy of science
      sug:
        subj:
          National Football League
          Machine learning
          Virtue epistemology
          Machine theory
          Philosophy of science
      keyword:
        Epistemic values
        General philosophy of science
        No free lunch theorem
        Theory choice
      ab: I use a theorem from machine learning, called the "No Free Lunch" theorem (NFL) to support the claim that non-epistemic values are essential to theory choice. I argue that NFL entails that predictive accuracy is insufficient to favor a given theory over others, and that NFL challenges our ability to give a purely epistemic justification for using other traditional epistemic virtues in theory choice. In addition, I argue that the natural way to overcome NFL's challenge is to use non-epistemic values. If my argument holds, non-epistemic values are entangled in theory choice regardless of human limitations and regardless of the subject matter. Thereby, my argument overcomes objections to the main lines of argument revealing the role of values in theory choice. At the end of the paper, I argue that, contrary to common conception, the epistemic challenge arising from NFL is distinct from Hume's problem of induction and other forms of underdetermination.
      pubtype: Academic Journal
      doctype: Article
      src: R
    language: English
    refInfo:
    copyright:
      @attributes:
        flag: Y
      custom: Synthese is a copyright of Springer, 2021. All Rights Reserved.
      item: Synthese
      holder: Springer Nature
      dt:
        @attributes:
          year: 2021
    holdings:
      @attributes:
        islocal: N