A NOTE ON THE LEARNING-THEORETIC CHARACTERIZATIONS OF RANDOMNESS AND CONVERGENCE.

Recently, a connection has been established between two branches of computability theory, namely between algorithmic randomness and algorithmic learning theory. Learning-theoretical characterizations of several notions of randomness were discovered. We study such characterizations based on the asymp...

Descripción completa

Detalles Bibliográficos
Publicado en:Review of Symbolic Logic Vol. 15; no. 3; pp. 807 - 823
Autor principal: STEIFER, TOMASZ
Formato: Artículo
Publicado: Cambridge University Press Sep2022
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=158569953&site=ehost-live
header:
  @attributes:
    shortDbName: hlh
    uiTerm: 158569953
    longDbName: Humanities International Complete
    uiTag: AN
  controlInfo:
    bkinfo:
    jinfo:
      jid:
        17550203
        8OI1
      jtl: Review of Symbolic Logic
      issn: 17550203
      maglogo: N
    pubinfo:
      dt: Sep2022
      vid: 15
      iid: 3
      pid: 15979
      pub: Cambridge University Press
    artinfo:
      ui:
        158569953
        10.1017/S1755020321000125
      ppf: 807
      ppct: 16
      formats:
      tig:
        atl: A NOTE ON THE LEARNING-THEORETIC CHARACTERIZATIONS OF RANDOMNESS AND CONVERGENCE.
      aug:
        au: STEIFER, TOMASZ
        affil: INSTITUTE OF FUNDAMENTAL TECHNOLOGICAL RESEARCH POLISH ACADEMY OF SCIENCES UL. PAWINSKIEGO 5B, 02-106, WARSZAWA, POLAND E-mail
      su:
        Algorithmic randomness
        Computable functions
        Random variables
        Problem solving
        Kolmogorov complexity
      sug:
        subj:
          Algorithmic randomness
          Computable functions
          Random variables
          Problem solving
          Kolmogorov complexity
      keyword:
        03D32
        algorithmic randomness
        effectivization
        learning theory
      ab: Recently, a connection has been established between two branches of computability theory, namely between algorithmic randomness and algorithmic learning theory. Learning-theoretical characterizations of several notions of randomness were discovered. We study such characterizations based on the asymptotic density of positive answers. In particular, this note provides a new learning-theoretic definition of weak 2-randomness, solving the problem posed by (Zaffora Blando, Rev. Symb. Log. 2019). The note also highlights the close connection between these characterizations and the problem of convergence on random sequences.
      pubtype: Academic Journal
      doctype: Article
      src: R
    language: English
    refInfo:
    copyright:
      @attributes:
        flag: Y
      dt:
        @attributes:
          year: 2022
    holdings:
      @attributes:
        islocal: N