Weighted Means in Stochastic Approximation of Minima
Continuing their own work [Math. Methods Stat. 5, No. 1, 32-60 (1996; Zbl 0858.62070)] the authors derive optimal rates of convergence for various multi-dimensional stochastic approximation procedures of the Kiefer-Wolfowitz type which aim at finding the extremum of a multivariate response function. The procedures considered here are based on the averaging method introduced by Ruppert and Polyak for the Robbins-Monro situation which was one of the major developments in stochastic approximation during the last years. In contrast to the standard Kiefer-Wolfowitz process no prior knowledge is required for the curvature at the extremum. The method allows for a wide flexibility in choosing the estimator of the gradient which covers averaged versions of the \textsl{random direction} and the \textsl{simultaneous perturbation stochastic approximation}. A computation of the resulting asymptotic mean squared errors exhibits a stable behaviour for the present procedures based on the averaging method compared to standard competitors.
- Weighted averaging and stochastic approximation
- Weighted means of processes in stochastic approximation
- Minimax theory of weighted Monte Carlo methods
- Parametric weighted minimax estimates in Monte Carlo methods
- scientific article; zbMATH DE number 766285
- A stochastic fixed point equation for weighted minima and maxima
- scientific article; zbMATH DE number 4145206
- scientific article; zbMATH DE number 272681
- The stochastic approximation method for the estimation of a multivariate probability density
- How does a stochastic optimization/approximation algorithm adapt to a randomly evolving optimum/root with jump Markov sample paths
- Weighted averaging and stochastic approximation
- Accelerated randomized stochastic optimization.
- Online estimation of hazard rate under random censoring
- Variance-constrained actor-critic algorithms for discounted and average reward MDPs
- Weighted means of processes in stochastic approximation
- Online estimation of integrated squared density derivatives
- A compact law of the iterated logarithm for online estimator of hazard rate under random censoring
- Recursive estimators of integrated squared density derivatives
- Online estimation of the asymptotic variance for averaged stochastic gradient algorithms
- An adaptive optimization scheme with satisfactory transient performance
- The multivariate Révész's online estimator of a regression function and its averaging
- The averaged Robbins-Monro method for linear problems in a Banach space
- A companion for the Kiefer-Wolfowitz-Blum stochastic approximation algorithm
- Stochastic approximation method with gradient averaging for unconstrained problems
- scientific article; zbMATH DE number 3965259 (Why is no real title available?)
- Multivariate stochastic approximation using a simultaneous perturbation gradient approximation
- Parallel and bootstrapped stochastic approximation
- Adaptive recursive kernel conditional density estimators under censoring data
- Stochastic approximation algorithms: overview and recent trends.
- Trajectory averaging for stochastic approximation MCMC algorithms
- A simplified Newton stochastic approximation algorithm estimating the hazard function of censored data
- Limit theorems for general recursive regression models involving weakly dependent functional data
- Multivariate compact law of the iterated logarithm for averaged stochastic approximation algorithms
- Weighted average iterated filtering using p-generalized Gaussian smoothing
- A stochastic fixed point equation for weighted minima and maxima
- Convergence rate and averaging of nonlinear two-time-scale stochastic approximation algo\-rithms
This page was built for publication: Weighted Means in Stochastic Approximation of Minima
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q4377400)