ABOUT GAUSSIAN SCHEMES IN STOCHASTIC-APPROXIMATION

[摘要] A family of one-dimensional linear stochastic approximation procedures in continuous time where processes of errors are Gaussian martingales is considered. Under some general assumptions the asymptotic behaviour of these procedures is studied concerning strong consistency, rate of convergence and limiting law of involved estimates and costs. At first some asymptotic results for Gaussian martingales, associated quadratic functionals and functions with finite variation are discussed.

[发布日期] 1994-03-01

[关键词] ASYMPTOTIC NORMALITY;ESTIMATE;GAUSSIAN MARTINGALE;RATE OF CONVERGENCE;STOCHASTIC APPROXIMATION;STRONG CONSISTENCY;WIENER PROCESS