Sie befinden Sich nicht im Netzwerk der Universität Paderborn. Der Zugriff auf elektronische Ressourcen ist gegebenenfalls nur via VPN oder Shibboleth (DFN-AAI) möglich. mehr Informationen...
Convergence rate of stochastic approximation algorithms in the degenerate case
Ist Teil von
SIAM journal on control and optimization, 1998, Vol.36 (1), p.100-114
Ort / Verlag
Philadelphia, PA: Society for Industrial and Applied Mathematics
Erscheinungsjahr
1998
Quelle
Business Source Ultimate
Beschreibungen/Notizen
Let $f(\cdot)$ be an unknown function whose root $x^0$ is sought by stochastic approximation (SA). Convergence rate and asymptotic normality are usually established for the nondegenerate case $f'(x^0)\neq 0$. This paper demonstrates the convergence rate of SA algorithms for the degenerate case $f'(x^0)=0$. In comparison with the previous work, in this paper no growth rate restriction is imposed on $f(\cdot)$, no statistical property is required for the measurement noise, the general step size is considered, and the result is obtained for the multidimensional case, which is not a straightforward extension of the one-dimensional result. Although the observation noise may be either deterministic or random, the analysis is purely deterministic and elementary.