When a stochastic approximation process satisfies the conditions for convergence there are well-established methods to terminate the iterative process in a manner that allows approximate statistics to be calculated on the final result. Many of these use the asymptotic properties of convergent stochastic approximation. However, such methods converge slowly… (More)

@article{Hutchison2005AMF,
title={A Method for Stopping Nonconvergent Stochastic Approximation Processes},
author={D W Hutchison and J. C. Spall},
journal={Proceedings of the 44th IEEE Conference on Decision and Control},
year={2005},
pages={6620-6625}
}