location: Current position: Home >> Scientific Research >> Paper Publications

On the Convergence of Smoothed Functional Stochastic Optimization Algorithms

Hits:

Indexed by:期刊论文

Date of Publication:2015-01-01

Journal:IFAC-PapersOnLine

Included Journals:EI、Scopus

Volume:48

Issue:28

Page Number:229-233

ISSN No.:24058963

Abstract:Smoothed functional gradient algorithm with perturbations distributed according to the Gaussian distribution is considered for stochastic optimization problem with additive noise. A stochastic approximation algorithm with expanding truncations that uses either one-sided or two-sided gradient estimate is given. At each iteration of the algorithm only two observations are required. The algorithm is shown to be convergent under only some mild conditions ? 2015

Pre One:Recursive Nonparametric Regression with Errors in Variables

Next One:On the convergence of smoothed functional stochastic optimization algorithms