Applications of a Kushner and Clark lemma to general classes of stochastic algorithms
作者： Michel Metivier , Pierre Priouret
关键词:
摘要: … of stochastic algorithms are considered, including algorithms considered by Ljung as well as algorithms of the … and Clark to obtain properties of these algorithms. This is done by using in …
acm.org 
sci-hub.se 参考文章(7)
L�szl� Gy�rfi, Stochastic approximation from ergodic sample for linear regression Probability Theory and Related Fields. ,vol. 54, pp. 47- 55 ,(1980) , 10.1007/BF00535352
E. Eweda, O. Macchi, Convergence of an adaptive linear estimation algorithm IEEE Transactions on Automatic Control. ,vol. 29, pp. 119- 127 ,(1984) , 10.1109/TAC.1984.1103463
Harold J Kushner, Stochastic approximation with discontinuous dynamics and state dependent noise: w.p. 1 and weak convergence☆ Journal of Mathematical Analysis and Applications. ,vol. 82, pp. 524- 542 ,(1981) , 10.1016/0022-247X(81)90214-6
E. G. Gladyshev, On Stochastic Approximation Theory of Probability and Its Applications. ,vol. 10, pp. 275- 278 ,(1965) , 10.1137/1110031
L. Ljung, Analysis of recursive stochastic algorithms IEEE Transactions on Automatic Control. ,vol. 22, pp. 551- 575 ,(1977) , 10.1109/TAC.1977.1101561
Harold J. Kushner, Adam Shwartz, Convergence of stochastic approximations with state dependent noise under weak conditions conference on decision and control. ,vol. 21, pp. 517- 521 ,(1982) , 10.1109/CDC.1982.268195
O. Macchi, E. Eweda, Quadratic mean and almost-sure convergence of unbounded stochastic approximation algorithms with correlated observations Annales De L Institut Henri Poincare-probabilites Et Statistiques. ,vol. 19, pp. 235- 255 ,(1983)