Convergence and robustness of the Robbins-Monro algorithm truncated at randomly varying bounds
From MaRDI portal
Publication:1095544
DOI10.1016/0304-4149(87)90039-1zbMath0632.62082OpenAlexW1975193898MaRDI QIDQ1095544
Lei Guo, Ai-Jun Gao, Chen, Hanfu
Publication date: 1988
Published in: Stochastic Processes and their Applications (Search for Journal in Brave)
Full work available at URL: https://doi.org/10.1016/0304-4149(87)90039-1
robustnessmeasurement errornecessary and sufficient conditionestimation errorRobbins-Monro algorithmrandomly varying truncation
Related Items (40)
Convergence of perturbation analysis based optimization algorithm with fixed number of customers period ⋮ An adaptive multiple-try Metropolis algorithm ⋮ Algorithms for Kullback--Leibler Approximation of Probability Measures in Infinite Dimensions ⋮ Quantile estimation with adaptive importance sampling ⋮ On the ergodicity properties of some adaptive MCMC algorithms ⋮ Weighted averaging and stochastic approximation ⋮ Coupling importance sampling and multilevel Monte Carlo using sample average approximation ⋮ Adaptative Monte Carlo Method, A Variance Reduction Technique ⋮ On robustness of the Robbins-Monro method for parallel processing ⋮ Limit theorems for some adaptive MCMC algorithms with subgeometric kernels ⋮ Trajectory averaging for stochastic approximation MCMC algorithms ⋮ Asymptotic behavior of truncated stochastic approximation procedures ⋮ Importance sampling and statistical Romberg method ⋮ Truncated stochastic approximation with moving bounds: convergence ⋮ Asymptotic bias of stochastic gradient search ⋮ On H-valued Robbins-Monro processes ⋮ A Robbins-Monro procedure for estimation in semiparametric regression models ⋮ Markovian stochastic approximation with expanding projections ⋮ Continuous-time stochastic approximation: Convergence and asymptotic efficiency ⋮ Convergence of the Monte Carlo expectation maximization for curved exponential families. ⋮ Almost sure convergence of randomly truncated stochastic algorithms under verifiable condi\-tions ⋮ Rate of convergence of truncated stochastic approximation procedures with moving bounds ⋮ Online EM algorithm for mixture with application to Internet traffic modeling ⋮ Improved results on the robustness of stochastic approximation algorithms ⋮ Coupling a stochastic approximation version of EM with an MCMC procedure ⋮ Robust adaptive importance sampling for normal random vectors ⋮ Central limit theorems for stochastic approximation with controlled Markov chain dynamics ⋮ Unconstrained recursive importance sampling ⋮ On Recursive Estimation in Incomplete Data Models ⋮ Algorithms of robust stochastic optimization based on mirror descent method ⋮ On the convergence of stochastic approximations under a subgeometric ergodic Markov dynamic ⋮ Forward-reverse expectation-maximization algorithm for Markov chains: convergence and numerical analysis ⋮ Convergence of a stochastic approximation version of the EM algorithm ⋮ On the almost sure asymptotic behaviour of stochastic algorithm ⋮ An almost sure central limit theorem for stochastic approximation algorithms ⋮ Stochastic Recursive Inclusions in Two Timescales with Nonadditive Iterate-Dependent Markov Noise ⋮ Stochastic gradient algorithm with random truncations ⋮ Maximum Entropy Methods for Texture Synthesis: Theory and Practice ⋮ Weak convergence rates for stochastic approximation with application to multiple targets and simulated annealing ⋮ Convergence of the Wang-Landau algorithm
Cites Work
- Necessary and sufficient conditions for the Robbins-Monro method
- A combined algorithm for identification and approximation
- Stochastic approximation with dependent noise
- Stochastic approximation methods for constrained and unconstrained systems
- Strong convergence of a stochastic approximation algorithm
- Analysis of recursive stochastic algorithms
- A Stochastic Approximation Method
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Unnamed Item
This page was built for publication: Convergence and robustness of the Robbins-Monro algorithm truncated at randomly varying bounds
