A method of stochastic subgradients with complete feedback stepsize rule for convex stochastic approximation problems (Q1093531)
From MaRDI portal
scientific article
| Language | Label | Description | Also known as |
|---|---|---|---|
| English | A method of stochastic subgradients with complete feedback stepsize rule for convex stochastic approximation problems |
scientific article |
Statements
A method of stochastic subgradients with complete feedback stepsize rule for convex stochastic approximation problems (English)
0 references
1988
0 references
A stochastic subgradient algorithm for solving convex stochastic approximation problems is considered. In the algorithm, the stepsize coefficients are controlled online on the basis of information gathered in the course of computations according to a new, complete feedback rule derived from the concept of regularized improvement function. Convergence with probability 1 of the method is established.
0 references
stochastic subgradient algorithm
0 references
convex stochastic approximation
0 references
feedback rule
0 references
0 references
0 references
0 references
