Robustness analysis for stochastic approximation algorithms
Han-Fu Chen, Aijun Gao · Stochastics and stochastics reports · 1989
This paper gives a robustness analysis of the stochastic approximation algorithms in the situations: when the regression function does not exactly equal zero at the sought-for χo, when the Liapunov function is not zero at χo and when anΣn i=1X;i+1 differs from zero where {aig} are the weighting coefficients of the algorithm and {Xi} are the measurement errors. It is shown that the estimation error is small if the abovementioned differences are small.