Doukhan, Paul; Brandière, Odile Dependent noise for stochastic algorithms. (English) Zbl 1067.62085 Probab. Math. Stat. 24, No. 2, 381-399 (2004). Summary: We introduce different ways of being dependent for the input noise of stochastic algorithms. We are aimed to prove that such innovations allow to use the ODE (ordinary differential equation) method. Illustrations to the linear regression frame and to the law of large numbers for triangular arrays of weighted dependent random variables are also given. Cited in 1 Document MSC: 62L20 Stochastic approximation 62J05 Linear regression; mixed models PDFBibTeX XMLCite \textit{P. Doukhan} and \textit{O. Brandière}, Probab. Math. Stat. 24, No. 2, 381--399 (2004; Zbl 1067.62085)