Multidimensional Stochastic Approximation Methods
Blum, Julius R.
Ann. Math. Statist., Tome 25 (1954) no. 4, p. 737-744 / Harvested from Project Euclid
Text on Project Euclid
PDF
Alt PDF
Multidimensional stochastic approximation schemes are presented, and conditions are given for these schemes to converge a.s. (almost surely) to the solutions of $k$ stochastic equations in $k$ unknowns and to the point where a regression function in $k$ variables achieves its maximum.
Publié le : 1954-12-14
Classification:  
@article{1177728659,
     author = {Blum, Julius R.},
     title = {Multidimensional Stochastic Approximation Methods},
     journal = {Ann. Math. Statist.},
     volume = {25},
     number = {4},
     year = {1954},
     pages = { 737-744},
     language = {en},
     url = {http://dml.mathdoc.fr/item/1177728659}
}

Blum, Julius R. Multidimensional Stochastic Approximation Methods. Ann. Math. Statist., Tome 25 (1954) no. 4, pp.  737-744. http://gdmltest.u-ga.fr/item/1177728659/