International economic review (Philadelphia), 2010-02, Vol.51 (1), p.237-262
2010
Details
- Autor(en) / Beteiligte
- Titel
- GENERALIZED STOCHASTIC GRADIENT LEARNING
- Ist Teil von
- International economic review (Philadelphia), 2010-02, Vol.51 (1), p.237-262
- Ort / Verlag
- Malden, USA: Blackwell Publishing Inc
- Erscheinungsjahr
- 2010
- Link zum Volltext
- Quelle
- Business Source Ultimate
- Beschreibungen/Notizen
- 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.
- Sprache
- Englisch
- Identifikatoren
- ISSN: 0020-6598eISSN: 1468-2354DOI: 10.1111/j.1468-2354.2009.00578.xTitel-ID: cdi_proquest_miscellaneous_757167997
- Format
- –
- Schlagworte
- Algorithms, Approximation, Coefficients, Convergence, Data analysis, Economic forecasts, Economic models, Economic stability, Eigenvalues, Estimators, Kalman filters, Learning, Macroeconomics, Mathematical economics, Matrices, Parametric models, Quantitative analysis, Rational expectations, Stochastic models, Studies, Sufficient conditions