Criterion algorithms of stochastic optimization
From MaRDI portal
Criterion optimization problems are considered in which it is important to estimate the optimum value of the performance criterion, whereas the coordinates of the extremum point are not of interest. Algorithms are proposed for solving criterion problems in the presence of random errors of measurement of the gradient; they are optimal in the sense of the criterion rate of convergence.
Recommendations
Cited in
(13)- Optimum parameters and nonasymptotic bounds on the rate of convergence of stochastic algorithms in criterial optimization problems
- Convergence and convergence rate of stochastic gradient search in the case of multiple and non-isolated extrema
- Stochastic comparison algorithm for continuous optimization with estimation
- Stochastic optimization procedure for the index values of software testing
- scientific article; zbMATH DE number 3890235 (Why is no real title available?)
- scientific article; zbMATH DE number 3849116 (Why is no real title available?)
- scientific article; zbMATH DE number 3936951 (Why is no real title available?)
- scientific article; zbMATH DE number 3974776 (Why is no real title available?)
- scientific article; zbMATH DE number 4045480 (Why is no real title available?)
- scientific article; zbMATH DE number 1531974 (Why is no real title available?)
- scientific article; zbMATH DE number 802423 (Why is no real title available?)
- Theoretical and numerical study of the performance of `Pincus' optimisation method
- Matching stochastic algorithms to objective function landscapes
This page was built for publication: Criterion algorithms of stochastic optimization
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q759650)