Asymptotic Almost Sure Efficiency of Averaged Stochastic Algorithms

DOI10.1137/S0363012998308169zbMath1015.60028MaRDI QIDQ4507444

Mariane Pelletier

Publication date: 18 October 2000

Published in: SIAM Journal on Control and Optimization (Search for Journal in Brave)

zbMATH Keywords

stochastic approximationasymptotic efficiencyzeros of a functionaveraged algorithm

Mathematics Subject Classification ID

Asymptotic properties of parametric estimators (62F12) Strong limit theorems (60F15)

Related Items (22)

L^p and almost sure rates of convergence of averaged stochastic gradient algorithms: locally strongly convex objective ⋮ Estimating the geometric median in Hilbert spaces with stochastic gradient algorithms: \(L^p\) and almost sure rates of convergence ⋮ A framework for adaptive Monte Carlo procedures ⋮ Online statistical inference for parameters estimation with linear-equality constraints ⋮ Convergence rate and averaging of nonlinear two-time-scale stochastic approximation algo\-rithms ⋮ The multivariate Révész's online estimator of a regression function and its averaging ⋮ Trajectory averaging for stochastic approximation MCMC algorithms ⋮ Importance sampling and statistical Romberg method ⋮ Some multivariate risk indicators: Minimization by using a Kiefer–Wolfowitz approach to the mirror stochastic algorithm ⋮ Optimal non-asymptotic analysis of the Ruppert-Polyak averaging stochastic algorithm ⋮ Adaptive importance sampling for multilevel Monte Carlo Euler method ⋮ On the rates of convergence of parallelized averaged stochastic gradient algorithms ⋮ Convergence in quadratic mean of averaged stochastic gradient algorithms without strong convexity nor bounded gradient ⋮ A fast and recursive algorithm for clustering large datasets with \(k\)-medians ⋮ On the asymptotic rate of convergence of stochastic Newton algorithms and their weighted averaged versions ⋮ A companion for the Kiefer-Wolfowitz-Blum stochastic approximation algorithm ⋮ Non asymptotic controls on a recursive superquantile approximation ⋮ Efficient and fast estimation of the geometric median in Hilbert spaces with an averaged stochastic gradient algorithm ⋮ CV<scp>a</scp> R HEDGING USING QUANTIZATION-BASED STOCHASTIC APPROXIMATION ALGORITHM ⋮ Unconstrained recursive importance sampling ⋮ An Efficient Stochastic Newton Algorithm for Parameter Estimation in Logistic Regressions ⋮ Online estimation of the asymptotic variance for averaged stochastic gradient algorithms

This page was built for publication: Asymptotic Almost Sure Efficiency of Averaged Stochastic Algorithms