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

Authors:
M. Metivier;P. Priouret
Affiliations:
-;-
Venue:
IEEE Transactions on Information Theory
Year:
2006

Citing 0
Cited 4

Adaptive algorithms and networks for optimal feature extraction from Gaussian data

Pattern Recognition Letters
Free energy computations by minimization of Kullback-Leibler divergence: An efficient adaptive biasing potential method for sparse representations

Journal of Computational Physics
Strong points of weak convergence: a study using RPA gradient estimation for automatic learning

Automatica (Journal of IFAC)
Full length article: A compressed sensing receiver for UWB impulse radio in bursty applications like wireless sensor networks

Physical Communication

Quantified Score

Hi-index	754.84

Visualization

Abstract

Two general classes of stochastic algorithms are considered, including algorithms considered by Ljung as well as algorithms of the formtheta_{n+1} = theta_{n} - gamma_{n+1} V_{n+1}(theta_{n}, Z), whereZis 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 method of the associated ordinary differential equation, under the classical boundedness assumptions. In the case of linear algorithms, the boundedness assumptions are dropped.