Learnability of e-stable equilibria

Atanas Christev, Sergey Slobodyan

Research output: Contribution to journalArticle

4 Citations (Scopus)

Abstract

If private sector agents update their beliefs with a learning algorithm other than recursive least squares, expectational stability or learnability of rational expectations equilibria (REE) is not guaranteed. Monetary policy under commitment, with a determinate and E-stable REE, may not imply robust learning stability of such equilibria if the recursuve least-squares speed
of convergence is slow. The authors propose a refinement of E-stability conditions that select equilibria more robust to specification of the learning algorithm within the RLS/SG/GSG class. E-stable equilibria characterized by faster speed of convergence under RLS learning are learnable with SG or generalized SG algorithms as well.
Original languageEnglish
Pages (from-to)959-984
Number of pages26
JournalMacroeconomic Dynamics
Volume18
Issue number5
Early online date3 Apr 2013
DOIs
Publication statusPublished - Jul 2014

Keywords

  • Adaptive Learning
  • Expectational Stability
  • Speed of Convergence
  • Stochastic Gradient

ASJC Scopus subject areas

  • Economics and Econometrics

Fingerprint Dive into the research topics of 'Learnability of e-stable equilibria'. Together they form a unique fingerprint.

Cite this