scientific article; zbMATH DE number 4029264
[For the entire collection see Zbl 0627.00024.] Stochastic approximation methods, e.g. stochastic gradient procedures, can be accelerated considerably by using deterministic (feasible) descent directions or more exact gradient estimations at certain iteration points. A further improvement of the convergence behavior is attained by an adaptive selection of the step sizes. Given a certain optimality criterion, a recursive procedure for the computation of optimal step sizes is derived. Several properties of the optimal step sizes are shown, and the convergence rate of the resulting optimal semi-stochastic approximation algorithm is calculated. Furthermore, the initial behavior of the optimal procedure is examined.
- New method of stochastic approximation type
- Accelerated randomized stochastic optimization.
- scientific article; zbMATH DE number 3876930 (Why is no real title available?)
- scientific article; zbMATH DE number 3891105 (Why is no real title available?)
- scientific article; zbMATH DE number 4203591 (Why is no real title available?)
- Rates of convergence of semi-stochastic approximation procedures for solving stochastic optimization problems
- scientific article; zbMATH DE number 4083367 (Why is no real title available?)
- scientific article; zbMATH DE number 4099037 (Why is no real title available?)
- On sampling controlled stochastic approximation
- scientific article; zbMATH DE number 53162 (Why is no real title available?)
- Globally convergent stochastic optimization with optimal asymptotic distribution
- Stabilization of stochastic approximation by step size adaptation
- Optimal step sizes in semi-stochastic approximation procedures. I
- Optimal step sizes in semi-stochastic approximation procedures. II
- On a Finite Deformation of a Cone
- scientific article; zbMATH DE number 1569106 (Why is no real title available?)
- scientific article; zbMATH DE number 778098 (Why is no real title available?)
- Optimal stochastic approximation algorithms for strongly convex stochastic composite optimization. II: Shrinking procedures and optimal algorithms
- scientific article; zbMATH DE number 3192512 (Why is no real title available?)
This page was built for publication:
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q3770286)