Higher order representations of the Robbins–Monro process |
| |
Authors: | Jürgen Dippon |
| |
Institution: | Fachbereich Mathematik, Universität Stuttgart, 70550, Stuttgart, Germany |
| |
Abstract: | For quasi-linear regression functions, the Robbins–Monro process Xn is decomposed in a sum of a linear form and a quadratic form both defined in the observation errors. Under regularity conditions, the remainder term is of order O(n−3/2) with respect to the Lp-norm. If a cubic form is added, the remainder term can be improved up to an order of O(n−2). As a corollary the expectation of Xn is expanded up to an error of order O(n−2). This is used to correct the bias of Xn up to an error of order O(n−3/2 log n). |
| |
Keywords: | Stochastic approximation Robbins– Monro procedure Non-recursive representation Asymptotic expansion Bias correction |
本文献已被 ScienceDirect 等数据库收录! |
|