Answers are grounded in this paper and cite their sources.
Convergence with probability one of a recursive stochastic approximation algorithm is considered. Some extensions of previous results for the Robbins-Monro and the Kiefer-Wolfowitz procedures are given. An inportant feature of the approach taken here is that the convergence analysis can be directly extended to more complex algorithms.
No takes yet. Share an insight, caveat, or question.
Lennart Ljung (1978) studied this question.
Synapse has enriched 10 related papers. Consider them for comparative context: