GENERALIZED STOCHASTIC GRADIENT LEARNING

George W Evans, Seppo Honkapohja, Noah Williams

    Research output: Contribution to journalArticlepeer-review

    Abstract

    We study the properties of the generalized stochastic gradient (GSG) learning in forward-looking models. GSG algorithms are a natural and convenient way to model learning when agents allow for parameter drift or robustness to parameter uncertainty in their beliefs. The conditions for convergence of GSG learning to a rational expectations equilibrium are distinct from but related to the well-known stability conditions for least squares learning.

    Original languageEnglish
    Pages (from-to)237-262
    Number of pages26
    JournalInternational Economic Review
    Volume51
    Issue number1
    DOIs
    Publication statusPublished - Feb 2010

    Keywords

    • MONETARY-POLICY
    • NASH INFLATION
    • STABILITY
    • EXPECTATIONS
    • CONVERGENCE
    • FRAMEWORK
    • BELIEFS
    • RULES
    • MODEL

    Fingerprint

    Dive into the research topics of 'GENERALIZED STOCHASTIC GRADIENT LEARNING'. Together they form a unique fingerprint.

    Cite this