Local convergence theorems for adaptive stochastic approximation schemes
AUTOR(ES)
Lai, T. L.
RESUMO
For the regression model y = M(x) + ε, adaptive stochastic approximation schemes of the form xn+1 = xn — yn/(nbn) for choosing the levels x1,x2,... at which y1,y2,... are observed converge with probability 1 to the unknown root θ of the regression function M(x). Certain local convergence theorems that relate the convergence rate of xn — θ to the limiting behavior of the random variables bn are established.
ACESSO AO ARTIGO
http://www.pubmedcentral.nih.gov/articlerender.fcgi?artid=383763Documentos Relacionados
- Limit theorems for weighted sums and stochastic approximation processes
- LIMIT THEOREMS FOR HOMOGENEOUS STOCHASTIC PROCESSES
- A convergence result for an outer approximation scheme
- APPROXIMATION BY POLYNOMIALS: UNIFORM CONVERGENCE AS IMPLIED BY MEAN CONVERGENCE*
- APPROXIMATION BY POLYNOMIALS: UNIFORM CONVERGENCE AS IMPLIED BY MEAN CONVERGENCE, III*