Stochastic approximation with dependent noise |
| |
Authors: | V Solo |
| |
Institution: | Department of Statistics, Harvard University, Cambridge, MA 02138, U.S.A. |
| |
Abstract: | In this work we derive the usual limit laws (weak and strong convergence, central limit theorem, invariance principle) for stochastic approximation with stationary noise. The idea is to introduce an artificial sequence, related to the SA scheme, but which clearly obeys the desired limit law. This sequence is subtracted from the SA scheme and the remainder, which behaves more or less deterministically, is shown to vanish using simple limit arguments. |
| |
Keywords: | Stochastic approximation invariance principle autocorrelated errors |
本文献已被 ScienceDirect 等数据库收录! |
|