Asymptotic behaviour of a class of stochastic approximation procedures
Let \({\mathbb{B}}\) be a real Banach space. Considering stochastic approximation procedures of Robbins-Monro and Kiefer-Wolfowitz type, one is led to recursion formulas of the form \[ U_{k+1}=U_ k-k^{- 1}\Gamma_ kU_ k-k^{-\rho}V_ k-k^{-\eta}T_ k \] \(\rho\) and \(\eta\) positive real numbers, \(U_ k\), \(V_ k\), \(T_ k\) \({\mathbb{B}}\)- valued random variables, \(\Gamma_ k\) random linear operators \({\mathbb{B}}\to {\mathbb{B}}\), where - in addition to some further assumptions - \(\Gamma_ k\to \Gamma\) almost surely and \(T_ k\to T\), say, almost surely. Letting \((Y_{k,n})_{k\in \{1,...,n\}}\), \(n\in {\mathbb{N}}\), be an array of \({\mathbb{B}}\)-valued random variables such that the partial sums \(\sum^{m}_{k=1}V_ k\) and \(\sum^{m}_{k=1}Y_{k,n}\) do not differ too much (uniformly in \(m\in \{1,...,n\})\), we shall investigate the distance of \((U_ m)_{m\in \{1,...,n\}}\) and \((U_ m^{(n)})_{m\in \{1,...,n\}}\), where \[ U^{(n)}_{k+1}:=U_ k^{(n)}-k^{-1}\Gamma U_ k^{(n)}-k^{-\rho}Y_{k,n}-k^{- \eta}T,\quad k\in \{1,...,n-1\}. \] The proofs are based on a deterministic argument that enables us to present a unified approach for proving central limit theorems, weak and almost sure invariance principles and variants of the bounded and the functional law of the iterated logarithm for the sequence \((U_ n)\).
- scientific article; zbMATH DE number 4094620
- Rate of convergence of stochastic approximation procedures in a Banach space
- scientific article; zbMATH DE number 721879
- Arithmetic means and invariance principles in stochastic approximation
- On the almost sure convergence of a general stochastic approximation procedure
- A limit theorem for the Robbins-Monro approximation
- A stochastic approximation from dependent observations
- A Stochastic Approximation Procedure in the Case of Weakly Dependent Observations
- Adaptive design and stochastic approximation
- Almost sure approximation of the Robbins-Monro process by sums of independent random variables
- Almost sure approximations to the Robbins-Monro and Kiefer-Wolfowitz processes with dependent noise
- Almost sure invariance principles for partial sums of mixing B-valued random variables
- Almost sure invariance principles for partial sums of weakly dependent random variables
- An almost sure Invariance Principle for Hilbert Space Valued Martingales
- An approximation of partial sums of independent RV'-s, and the sample DF. I
- An approximation of partial sums of independent RV's, and the sample DF. II
- An Extension of the Robbins-Monro Procedure
- An invariance principle for a finite dimensional stochastic approximation method in a Hilbert space
- An invariance principle for the law of the iterated logarithm
- An invariance principle for the Robbins-Monro process in a Hilbert space
- Approximation Methods which Converge with Probability one
- Asymptotic Distribution of Stochastic Approximation Procedures
- Asymptotically efficient stochastic approximation; the RM case
- Distances of Probability Measures and Random Variables
- Functional and random central limit theorems for the Robbins-Munro process
- scientific article; zbMATH DE number 3651458 (Why is no real title available?)
- scientific article; zbMATH DE number 3653234 (Why is no real title available?)
- scientific article; zbMATH DE number 3657011 (Why is no real title available?)
- scientific article; zbMATH DE number 3705593 (Why is no real title available?)
- scientific article; zbMATH DE number 3723610 (Why is no real title available?)
- scientific article; zbMATH DE number 3764993 (Why is no real title available?)
- scientific article; zbMATH DE number 3782249 (Why is no real title available?)
- scientific article; zbMATH DE number 3553601 (Why is no real title available?)
- scientific article; zbMATH DE number 3556932 (Why is no real title available?)
- scientific article; zbMATH DE number 3449064 (Why is no real title available?)
- scientific article; zbMATH DE number 3274494 (Why is no real title available?)
- scientific article; zbMATH DE number 3288917 (Why is no real title available?)
- scientific article; zbMATH DE number 3320019 (Why is no real title available?)
- scientific article; zbMATH DE number 3327878 (Why is no real title available?)
- Invariance principles for dependent variables
- Invariance principles for sums of Banach space valued random elements and empirical processes
- Limit theorems for sums of weakly dependent Banach space valued random variables
- Limit theorems for weighted sums and stochastic approximation processes
- Martingales and the Robbins-Monro procedure in \(D[0,1]\)
- On a Stochastic Approximation Method
- On a unified approach to the law of the iterated logarithm for martingales
- On Asymptotic Normality in Stochastic Approximation
- On asymptotically efficient recursive estimation
- On martingale limit theory and strong convergence results for stochastic approximation procedures
- On the invariance principle for nonstationary mixingales
- On the Law of the Iterated Logarithm in Stochastic Approximation Processes
- On the weak convergence of empirical processes in sup-norm metrics
- Semimartingales: A course on stochastic processes
- Some Multivariate Chebyshev Inequalities with Extensions to Continuous Parameter Processes
- The approximation of partial sums of independent RV's
- The Law of the Iterated Logarithm for Brownian Motion in a Banach Space
- Transformation of observations in stochastic approximation
- Asymptotic behavior of constrained stochastic approximations via the theory of large deviations
- A stochastic Remes algorithm
- The local asymptotic minimax adaptive property of a recursive estimate
- Arithmetic means and invariance principles in stochastic approximation
- Rate of convergence of stochastic approximation procedures in a Banach space
- An almost sure invariance principle for stochastic approximation procedures in linear filtering theory
- Accelerated randomized stochastic optimization.
- On the almost sure asymptotic behaviour of stochastic algorithm
- Optimal scaling and diffusion limits for the Langevin algorithm in high dimensions
- Optimal scaling of the MALA algorithm with irreversible proposals for Gaussian targets
- Diffusion limit for the random walk Metropolis algorithm out of stationarity
- On the stability of sequential Monte Carlo methods in high dimensions
- An asymptotic formula for a class of approximation processes of King’s type
- scientific article; zbMATH DE number 3940520 (Why is no real title available?)
- scientific article; zbMATH DE number 4094620 (Why is no real title available?)
- Stochastic fictitious play with continuous action sets
- Diffusion limits of the random walk Metropolis algorithm in high dimensions
- Parallel and bootstrapped stochastic approximation
- Noisy gradient flow from a random walk in Hilbert space
- scientific article; zbMATH DE number 5025892 (Why is no real title available?)
- A function space HMC algorithm with second order Langevin diffusion limit
- Optimal scaling for the proximal Langevin algorithm in high dimensions
This page was built for publication: Asymptotic behaviour of a class of stochastic approximation procedures
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q1061435)