Applications of a Kushner and Clark lemma to general classes of stochastic algorithms

@article{Metivier1984ApplicationsOA,
  title={Applications of a Kushner and Clark lemma to general classes of stochastic algorithms},
  author={M. Metivier and P. Priouret},
  journal={IEEE Trans. Information Theory},
  year={1984},
  volume={30},
  pages={140-150}
}
Two general classes of stochastic algorithms are considered, including algorithms considered by Ljung as well as algorithms of the form \theta_{n+1} = \theta_{n} - \gamma_{n+1} V_{n+1}(\theta_{n}, Z) , where Z is a stationary ergodic process. It is shown how one can apply a lemma of Kushner and Clark to obtain properties of these algorithms. This is done by using in particular Martingale arguments in the generalized Ljung case. In these various situations the convergence is obtained by the… CONTINUE READING

Topics from this paper.

Citations

Publications citing this paper.
SHOWING 1-10 OF 49 CITATIONS

Adaptive stochastic approximation by the simultaneous perturbation method

  • IEEE Trans. Automat. Contr.
  • 2000
VIEW 4 EXCERPTS
CITES METHODS
HIGHLY INFLUENCED

Almost sure and Lq-convergence of the re-initialized BMP scheme

  • 2007 46th IEEE Conference on Decision and Control
  • 2007
VIEW 4 EXCERPTS
CITES BACKGROUND & METHODS
HIGHLY INFLUENCED