I am looking for a result/paper (if there is any) on the large deviations rate of convergence of the Robbins-Monro (RM) algorithm. Specifically, given $X_k \rightarrow X$ a.s. in the RM algorithm, I would like a result of the form $\lim_{k \rightarrow \infty} \frac{1}{k} | X_k - X | = c$. Thanks!