Title :
General results on the convergence of stochastic algorithms
Author_Institution :
IRISA, Rennes, France
fDate :
9/1/1996 12:00:00 AM
Abstract :
A deterministic approach is proposed for proving the convergence of stochastic algorithms of the most general form under necessary conditions on the input noise and reasonable conditions on the (nonnecessarily continuous) mean field. Emphasis is placed on the case where more than one stationary point exists. We also use this approach to prove the convergence of a stochastic algorithm with Markovian dynamics
Keywords :
convergence; noise; stochastic processes; Markovian dynamics; convergence; input noise; mean field; necessary conditions; stationary point; stochastic algorithms; Convergence; Filtering algorithms; Helium; Heuristic algorithms; Random variables; Recursive estimation; Stochastic processes; Stochastic resonance; Stochastic systems; System identification;
Journal_Title :
Automatic Control, IEEE Transactions on
