A note on continuous-time stochastic approximation in infinite dimensions

被引:0
|
作者
Seidler, Jan [1 ]
Zak, Frantisek [2 ]
机构
[1] Czech Acad Sci, Inst Informat Theory & Automat, Prague 18208, Czech Republic
[2] Imperial Coll London, London, England
关键词
stochastic approximation; stochastic parabolic problems; variational solutions; HILBERT-SPACE;
D O I
10.1214/17-ECP67
中图分类号
O21 [概率论与数理统计]; C8 [统计学];
学科分类号
020208 ; 070103 ; 0714 ;
摘要
We find sufficient conditions for convergence of a continuous-time Robbins-Monro type stochastic approximation procedure in infinite dimensional Hilbert spaces in terms of Lyapunova functions, the variational approach to stochastic partial differential equations being used as the main tool.
引用
收藏
页数:13
相关论文
共 50 条