Optimality in problems and optimization algorithms under indeterminacy
Considered is the minimization of a function \(J(x)\) on \({\mathbb{R}}^ r\) assuming that only estimates \(y(n,x)\) of the gradient \(\nabla J(x)\) can be obtained having one of the forms (a) \(y(n,x)=\nabla J(x)+\xi_ 1\) (additive noise) or (b) \(y(n,x)=Diag(\xi_ n)\nabla J(x)\) (multiplicative noise), where \((\xi_ n)\) is a sequence of independent, identically distributed, zero mean random r-vectors. Replacing \(y(n,x)\) by \(\tilde y(n,x)=\phi(y(n,x))\), formulas are given for the transformation \(\phi\) minimizing the asymptotic error covariance matrix of the resulting stochastic gradient procedure with the transformed gradient ỹ(n,x) and having an optimal gain matrix of the type \(\Gamma_ 0(n)=n^{-1}\Gamma_ 0\).
- Problem of improvement of objective function with indeterminate gradient
- How to deal with the unbounded in optimization: Theory and algorithms
- On the problem of possibilistic optimization
- Decision theory meets linear optimization beyond computation
- scientific article; zbMATH DE number 3856971 (Why is no real title available?)
- scientific article; zbMATH DE number 3878685 (Why is no real title available?)
- scientific article; zbMATH DE number 3936951 (Why is no real title available?)
- scientific article; zbMATH DE number 4045480 (Why is no real title available?)
- Informational inequalities in the problem of gradient stochastic optimization and optimal realizable algorithms
This page was built for publication: Optimality in problems and optimization algorithms under indeterminacy
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q1083375)
