Strong Convergence of a Stochastic Approximation Algorithm
Ljung, Lennart
Ann. Statist., Tome 6 (1978) no. 1, p. 680-696 / Harvested from Project Euclid
Text on Project Euclid
PDF
Alt PDF
Convergence with probability one of a recursive stochastic approximation algorithm is considered. Some extensions of previous results for the Robbins-Monro and the Kiefer-Wolfowitz procedures are given. An inportant feature of the approach taken here is that the convergence analysis can be directly extended to more complex algorithms.
Publié le : 1978-05-14
Classification:  Recursive stochastic algorithms,  stochastic approximation,  62L20,  93E10 
@article{1176344212,
     author = {Ljung, Lennart},
     title = {Strong Convergence of a Stochastic Approximation Algorithm},
     journal = {Ann. Statist.},
     volume = {6},
     number = {1},
     year = {1978},
     pages = { 680-696},
     language = {en},
     url = {http://dml.mathdoc.fr/item/1176344212}
}

Ljung, Lennart. Strong Convergence of a Stochastic Approximation Algorithm. Ann. Statist., Tome 6 (1978) no. 1, pp.  680-696. http://gdmltest.u-ga.fr/item/1176344212/