On the almost sure asymptotic behaviour of stochastic algorithm
From MaRDI portal
The author considers a stochastic algorithm of the form: \( Z_{n+1}=Z_n +\gamma_n(h(Z_n)+r_n)+ \sigma_n \epsilon_{n+1},\) where \(h :R^d \to R^d,\) \(\{r_n\}\) and \(\{\epsilon_n\}\) are disturbances and \(\{\gamma_n\}\) , \(\{\sigma_n\}\) are nonrandom strictly positive sequences with \(\sum_n\gamma_n<\infty\), \(\sum_n\sigma_n<\infty \). She studies almost sure behavior of the algorithm. A law of iterated logarithm and a quadratic strong law of large numbers are established.
Recommendations
- Almost sure convergence of a class of stochastic algorithms
- Une version presque sûre du théorème de la limite centrale pour les algorithmes stochastiques
- scientific article; zbMATH DE number 952465
- Asymptotic Almost Sure Efficiency of Averaged Stochastic Algorithms
- An almost sure central limit theorem for stochastic approximation algorithms
- scientific article; zbMATH DE number 1946759
- scientific article; zbMATH DE number 721880
Cites work
- About the averaging approach in Gaussian schemes for stochastic approximation
- Adaptive prediction by least squares predictors in stochastic regression models with applications to time series
- Almost sure approximations to the Robbins-Monro and Kiefer-Wolfowitz processes with dependent noise
- Arithmetic means and invariance principles in stochastic approximation
- Asymptotic behaviour of a class of stochastic approximation procedures
- Asymptotic properties of least-squares estimates in stochastic regression models
- Averaging for estimating covariances in stochastic approximation
- Convergence and robustness of the Robbins-Monro algorithm truncated at randomly varying bounds
- scientific article; zbMATH DE number 3818787 (Why is no real title available?)
- scientific article; zbMATH DE number 3764993 (Why is no real title available?)
- scientific article; zbMATH DE number 48727 (Why is no real title available?)
- scientific article; zbMATH DE number 48067 (Why is no real title available?)
- scientific article; zbMATH DE number 53271 (Why is no real title available?)
- scientific article; zbMATH DE number 952465 (Why is no real title available?)
- scientific article; zbMATH DE number 3249395 (Why is no real title available?)
- scientific article; zbMATH DE number 3333814 (Why is no real title available?)
- Limit theorems for weighted sums and stochastic approximation processes
- On the Law of the Iterated Logarithm in Stochastic Approximation Processes
- Rates of Convergence for an Adaptive Filtering Algorithm Driven by Stationary Dependent Data
- Regularly varying functions
- Some results about averaging in stochastic approximation
- Stochastic algorithms
- Stochastic approximation methods for constrained and unconstrained systems
- Sur la loi des grands nombres pour les martingales vectorielles et l'estimateur des moindres carrés d'un modèle de régression. (On the law of large numbers for vectorial martingales and least square estimators of a regression model)
- Weak convergence rates for stochastic approximation with application to multiple targets and simulated annealing
Cited in
(40)- Théorèmes de convergence presque sure pour une classe d'algorithmes stochastiques à pas decroissant
- General multilevel adaptations for stochastic approximation algorithms of Robbins-Monro and Polyak-Ruppert type
- An almost sure central limit theorem for stochastic approximation algorithms
- Asymptotic distribution and convergence rates of stochastic algorithms for entropic optimal transportation between probability measures
- Stochastic approximation algorithms for superquantiles estimation
- On the asymptotic behaviour of the Aragón Artacho-Campoy algorithm
- Online estimation of the asymptotic variance for averaged stochastic gradient algorithms
- An adaptive version for the Metropolis adjusted Langevin algorithm with a truncated drift
- A companion for the Kiefer-Wolfowitz-Blum stochastic approximation algorithm
- Estimation of the shift parameter in regression models with unknown distribution of the observations
- A law of the iterated logarithm for stochastic approximation procedures in d-dimensional Euclidean space.
- On the asymptotic rate of convergence of stochastic Newton algorithms and their weighted averaged versions
- Limit theorems with weights for vector-valued martingales
- On Optimal Algorithms in an Asymptotic Model with Gaussian Measure
- Recursive estimation in a class of models of deformation
- scientific article; zbMATH DE number 718744 (Why is no real title available?)
- Une version presque sûre du théorème de la limite centrale pour les algorithmes stochastiques
- scientific article; zbMATH DE number 1946759 (Why is no real title available?)
- A Law of Large Numbers for Rescaled Random Difference Equations
- A Robbins-Monro procedure for estimation in semiparametric regression models
- Asymptotic Almost Sure Efficiency of Averaged Stochastic Algorithms
- Law of the Iterated Logarithm for a Constant-Gain Linear Stochastic Gradient Algorithm
- The Compact Law of the Iterated Logarithm for Multivariate Stochastic Approximation Algorithms
- scientific article; zbMATH DE number 947091 (Why is no real title available?)
- scientific article; zbMATH DE number 952465 (Why is no real title available?)
- On the rates of convergence of parallelized averaged stochastic gradient algorithms
- Lp and almost sure rates of convergence of averaged stochastic gradient algorithms: locally strongly convex objective
- Stochastic approximation algorithms: overview and recent trends.
- Convergence in quadratic mean of averaged stochastic gradient algorithms without strong convexity nor bounded gradient
- On the inversion-free Newton's method and its applications
- An efficient averaged stochastic Gauss-Newton algorithm for estimating parameters of nonlinear regressions models
- Stochastic approximation and reinforcement learning: the interface and a little beyond
- Natural Gradient Variational Bayes Without Fisher Matrix Analytic Calculation and Its Inversion
- On adaptive stochastic optimization for streaming data: a Newton's method with \( \mathcal{O}(dN)\) operations
- Multivariate compact law of the iterated logarithm for averaged stochastic approximation algorithms
- Optimization based on a team of automata with binary outputs
- Online and offline robust multivariate linear regression
- Complexity reduction in online stochastic Newton methods with potential \(\mathcal{O}(Nd)\) total cost
- On adaptive and non-adaptive stochastic and deterministic algorithms
- Convergence rate and averaging of nonlinear two-time-scale stochastic approximation algo\-rithms
This page was built for publication: On the almost sure asymptotic behaviour of stochastic algorithm
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q1807280)
