Convergence analysis of dynamic stochastic approximation

✍ Scribed by Han-Fu Chen; Katsuji Uosaki

• Publisher: Elsevier Science
• Year: 1998
• Tongue: English
• Weight: 113 KB
• Volume: 35
• Category: Article
• ISSN: 0167-6911
• DOI: 10.1016/s0167-6911(98)00077-2

✦ Synopsis

Stochastic approximation method concerns the sequential estimation of the root or the extreme of a function observed with noise. The idea is then extended to the moving root case by Dupa c, and it is called as the dynamic stochastic approximation method. Its convergence properties are derived here by using a randomly varying truncation technique under weaker conditions in comparison with the previous work: the growth rate restriction on the function has been removed and the condition on the observation noises has been weakened to the possibly weakest ones.