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

DOI10.1109/TIT.1984.1056894zbMath0546.62056WikidataQ124830324 ScholiaQ124830324MaRDI QIDQ3336538

Michel Métivier, Pierre Priouret

Publication date: 1984

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

zbMATH Keywords

stochastic algorithms; martingale arguments; stationary ergodic process; boundedness assumptions; algorithm of Ljung type; associated ordinary differential equations; conditionally Markovian; Kushner and Clark lemma

Mathematics Subject Classification ID

62L20: Stochastic approximation

Related Items

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