：随机逼近与随机梯度下降02-2：Robbins-Monro（RM）算法【wₖ₊₁=wₖ-αₖĝ(wₖ,ηₖ)】【SA领域的开创性工作】)
2、Robbins-Monro（RM）算法Robbins-Monro(RM)算法：wk+1 = wk − ak g~(wk,ηk ),k = 1,2,3,... \begin{aligned}w_{k+1}\:=\:w_k\:-\:a_k\:\tilde{g}(w_k,\eta_k\:),k\:=\:1,2,3,...\end{aligned}wk+1=wk−akg~(wk,ηk),k=1,2,3,...其中wkw_kwk是root的第kkk次估计；g~(wk,ηk)=g(wk)+ηk\tilde{g}\left(w_k,\eta_k\right)=g(w_k)+\eta_kg~(wk,ηk)=g(wk)+ηk是第kkk次带有噪声的观测；
 的用法、联动删除机制与恢复原理)
