Applications of a Kushner and Clark lemma to general classes of stochastic algorithms

DOI10.1109/TIT.1984.1056894zbMath0546.62056OpenAlexW2007854530WikidataQ124830324 ScholiaQ124830324MaRDI QIDQ3336538

Michel Métivier, Pierre Priouret

Publication date: 1984

Published in: IEEE Transactions on Information Theory (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1109/tit.1984.1056894

zbMATH Keywords

stochastic algorithmsmartingale argumentsstationary ergodic processboundedness assumptionsalgorithm of Ljung typeassociated ordinary differential equationsconditionally MarkovianKushner and Clark lemma

Mathematics Subject Classification ID

Stochastic approximation (62L20)

Related Items (26)

Optimal load sharing in soft real-time systems using likelihood ratios ⋮ Stochastic approximations for finite-state Markov chains ⋮ Weighted averaging and stochastic approximation ⋮ The method of averaged models for discrete-time adaptive systems ⋮ Stochastic recursive inclusions with non-additive iterate-dependent Markov noise ⋮ Abstract stochastic approximations and applications ⋮ Convergence analysis of smoothed stochastic gradient-type algorithm ⋮ Artificial neural networks: an econometric perspective^∗ ⋮ Convergence of stochastic approximation via martingale and converse Lyapunov methods ⋮ Free energy computations by minimization of Kullback-Leibler divergence: An efficient adaptive biasing potential method for sparse representations ⋮ Bridging the gap between constant step size stochastic gradient descent and Markov chains ⋮ On maximum a posteriori estimation with Plug \& Play priors and stochastic gradient descent ⋮ Two-timescale stochastic gradient descent in continuous time with applications to joint online parameter estimation and optimal sensor placement ⋮ An adaptive version for the Metropolis adjusted Langevin algorithm with a truncated drift ⋮ Asymptotic bias of stochastic gradient search ⋮ Maximum Likelihood Estimation of Regularization Parameters in High-Dimensional Inverse Problems: An Empirical Bayesian Approach. Part II: Theoretical Analysis ⋮ Online drift estimation for jump-diffusion processes ⋮ Average Competitive Learning Vector Quantization ⋮ Convergence and convergence rate of stochastic gradient search in the case of multiple and non-isolated extrema ⋮ Two Time-Scale Stochastic Approximation with Controlled Markov Noise and Off-Policy Temporal-Difference Learning ⋮ Stochastic Recursive Inclusions in Two Timescales with Nonadditive Iterate-Dependent Markov Noise ⋮ Convergence of the Robbins-Monro method for linear problems in a Banach space ⋮ Fundamental design principles for reinforcement learning algorithms ⋮ Simulated annealing type algorithms for multivariate optimization ⋮ Sign-error adaptive filtering algorithms involving Markovian parameters ⋮ Théorèmes de convergence presque sure pour une classe d'algorithmes stochastiques à pas decroissant

This page was built for publication: Applications of a Kushner and Clark lemma to general classes of stochastic algorithms