Cover Image
QR Code

A Dilemma for Solomonoff Prediction.

The framework of Solomonoff prediction assigns prior probability to hypotheses inversely proportional to their Kolmogorov complexity. There are two well-known problems. First, the Solomonoff prior is relative to a choice of universal Turing machine. Second, the Solomonoff prior is not computable. Ho...

Full description

Published in:Philosophy of Science Vol. 90; no. 2; pp. 288 - 307
Main Author: Neth, Sven
Format: Article
Published: Cambridge University Press Apr2023
Subjects:
Kolmogorov complexity
Turing machines
Dilemma
Forecasting
Online Access:View this record in EBSCOhost
fields @attributes:
  recordID: 1
pdfLink:
plink: https://search.ebscohost.com/login.aspx?direct=true&db=hlh&AN=164158591&site=ehost-live
header:
  @attributes:
    shortDbName: hlh
    uiTerm: 164158591
    longDbName: Humanities International Complete
    uiTag: AN
  controlInfo:
    bkinfo:
    jinfo:
      jid:
        00318248
        PSC
      jtl: Philosophy of Science
      issn: 00318248
      maglogo: N
    pubinfo:
      dt: Apr2023
      vid: 90
      iid: 2
      pid: 15979
      pub: Cambridge University Press
    artinfo:
      ui:
        164158591
        10.1017/psa.2022.72
      ppf: 288
      ppct: 19
      formats:
        fmt:
          – @attributes:
              type: T
          – @attributes:
              type: P
              size: 238KB
      tig:
        atl: A Dilemma for Solomonoff Prediction.
      aug:
        au: Neth, Sven
        affil: University of California, Berkeley, Berkeley, CA, US
      su:
        Kolmogorov complexity
        Turing machines
        Dilemma
        Forecasting
      sug:
        subj:
          Kolmogorov complexity
          Turing machines
          Dilemma
          Forecasting
      ab: The framework of Solomonoff prediction assigns prior probability to hypotheses inversely proportional to their Kolmogorov complexity. There are two well-known problems. First, the Solomonoff prior is relative to a choice of universal Turing machine. Second, the Solomonoff prior is not computable. However, there are responses to both problems. Different Solomonoff priors converge with more and more data. Further, there are computable approximations to the Solomonoff prior. I argue that there is a tension between these two responses. This is because computable approximations to Solomonoff prediction do not always converge.
      pubtype: Academic Journal
      doctype: Article
      src: R
    language: English
    refInfo:
    copyright:
      @attributes:
        flag: Y
      custom: Copyright of Philosophy of Science is the property of Cambridge University Press 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.
      item: Philosophy of Science
      holder: Cambridge University Press
      dt:
        @attributes:
          year: 2023
    holdings:
      @attributes:
        islocal: N