Strong diffusion approximations for recursive stochastic algorithms

Lai and Robbins (1978) prove strong diffusion approximations for the Robbins-Monro stochastic approximation algorithm. We show that similar strong approximations hold for stochastic algorithms at the level of generality proposed in the monograph of Benveniste, Metivier and Priouret (1990), wherein algorithms with generally discontinous right-hand sides driven by conditionally Markovian data are considered. The relevance of our result is demonstrated on an estimation algorithm with a discontinuous right-hand side which is used in data communication. The technique of adaptive delta modulation used in digital communication is considered.

[1]  D. Ruppert.  Almost Sure Approximations to the Robbins-Monro and Kiefer-Wolfowitz Processes with Dependent Noise , 1982 .

[2]  M. Métivier,et al.  Théorèmes de convergence presque sure pour une classe d'algorithmes stochastiques à pas décroissant , 1987 .

[3]  T. P. Krasulina,et al.  On the Law of the Iterated Logarithm in Stochastic Approximation Processes , 1975 .

[4]  W. Philipp,et al.  Nearby variables with nearby conditional laws and a strong approximation theorem for Hilbert space valued martingales , 1991 .

[5]  C. Heyde.  Invariance Principles in Statistics, Correspondent Paper , 1981 .

[6]  Pierre Priouret,et al.  Adaptive Algorithms and Stochastic Approximations , 1990, Applications of Mathematics.

[7]  Rabi Bhattacharya,et al.  Stochastic processes with applications , 1990 .

[8]  H. Kushner.  Convergence of recursive adaptive and identification procedures via weak convergence theory , 1977 .

[9]  William A. Sethares,et al.  Weak convergence and local stability properties of fixed step size recursive algorithms , 1993, IEEE Trans. Inf. Theory.

[10]  Functional and random central limit theorems for the Robbins-Munro process , 1976 .

[11]  P. Billingsley,et al.  Convergence of Probability Measures , 1969 .

[12]  A. Skorokhod.  On a Representation of Random Variables , 1977 .

[13]  M. Metivier,et al.  Applications of a Kushner and Clark lemma to general classes of stochastic algorithms , 1984, IEEE Trans. Inf. Theory.

[14]  Richard L. Tweedie,et al.  Markov Chains and Stochastic Stability , 1993, Communications and Control Engineering Series.

[15]  W. Stout.  Almost sure convergence , 1974 .

[16]  A. Benveniste,et al.  Analysis of stochastic approximation schemes with discontinuous and dependent forcing terms with applications to data communication algorithms , 1980 .

[17]  J. Dieudonne.  Foundations of Modern Analysis , 1969 .

[18]  Lennart Ljung,et al.  Analysis of recursive stochastic algorithms , 1977 .

[19]  H Robbins,et al.  Limit theorems for weighted sums and stochastic approximation processes. , 1978, Proceedings of the National Academy of Sciences of the United States of America.

[20]  V. Strassen.  An invariance principle for the law of the iterated logarithm , 1964 .

[21]  K. Jogdeo,et al.  Upper and Lower Functions for Martingales and Mixing Processes , 1975 .