Abstract
The semimartingale stochastic approximation procedure, precisely, the Robbins-Monro type SDE, is introduced, which naturally includes both generalized stochastic approximation algorithms with martingale noises and recursive parameter estimation procedures for statistical models associated with semimartingales. General results concerning the asymptotic behavior of the solution are presented. In particular, the conditions ensuring the convergence, the rate of convergence, and the asymptotic expansion are established. The results concerning the Polyak weighted averaging procedure are also presented.
Article PDF
Similar content being viewed by others
Avoid common mistakes on your manuscript.
References
A. E. Albert and L. A. Gardner, Jr., “Stochastic approximations and nonlinear regression,” M.I.T. Press Research Monograph, 42, The M.I.T. Press, Cambridge, (1967).
A. Le Breton, “About the averaging approach in Gaussian schemes for stochastic approximation,” Math. Methods Statist., 2, No. 4, 295–315 (1993).
A. Le Breton, “About Gaussian schemes in stochastic approximation,” Stochastic Process. Appl., 50, No. 1, 101–115 (1994).
A. Le Breton and A. A. Novikov, “Averaging for estimating covariances in stochastic approximation,” Math. Methods Statist., 3, No. 3, 244–266 (1994).
H. F. Chen, “Asymptotically efficient stochastic approximation,” Stochastics Stochastics Rep., 45, Nos. 1–2, 1–16 (1993).
B. Delyon and A. Juditsky, “Stochastic optimization with averaging of trajectories,” Stochastics Stochastics Rep., 39, Nos. 2–3, 107–118 (1992).
V. Fabian, “On asymptotically efficient recursive estimation,” Ann. Statist., 6, No. 4, 854–866 (1978).
L. I. Gal’chuk, “On the existence and uniqueness of solutions of stochastic equations with respect to semimartingales,” Teor. Veroyatn. Primen., 23, No. 4, 782–795 (1978).
I. I. Gikhman and A. V. Skorokhod, Stochastic Differential Equations and Their Applications [in Russian], Naukova Dumka, Kiev (1982).
A. A. Gushchin, “Asymptotic optimality of parameter estimators under the LAQ condition,” Teor. Veroyatn. Primen., 40, No. 2, 286–300 (1995). (1996).
P. Hall and C. C. Heyde, “Martingale limit theory and its application,” in: Probability and Mathematical Statistics, Academic Press, New York-London (1980).
J. Jacod, “Calcul stochastique et problèmes de martingales,” Lect. Notes Math., 714 (1979).
J. Jacod and J. Mémin, “Weak and strong solutions of stochastic differential equations: existence and stability,” Lect. Notes Math., 851 (1981).
J. Jacod and A. N. Shiryaev, “Limit theorems for stochastic processes,” Grundlehren Math. Wiss., 288 (1987).
J. Jacod, “Regularity, partial regularity, partial information process for a filtered statistical model,” Probab. Theory Related Fields, 86, No. 3, 305–335 (1990).
Yu. M. Kabanov, R. Sh. Litscer, and A. N. Shiryaev, “Absolute continuity and singularity of locally absolutely continuous probability distributions, I,” Mat. Sb., 107, No. 3, 364–415 (1978).
H. J. Kushner and G. G. Yin, “Stochastic approximation algorithms and applications,” Appl. Math., 35 (1997).
N. L. Lazrieva and T. A. Toronjadze, “Ito-Ventzel’s formula for semimartingales, asymptotic properties of MLE and recursive estimation,” Lect. Notes Control Inf. Sci., 96 (1987), pp. 346–355.
N. Lazrieva, T. Sharia, and T. Toronjadze, “The Robbins-Monro type stochastic differential equations, I. Convergence of solutions,” Stochastics Stochastics Rep., 61, Nos. 1–2, 67–87 (1997).
N. Lazrieva, T. Sharia, and T. Toronjadze, “The Robbins-Monro type stochastic differential equations, II. Asymptotic behavior of solutions,” Stochastics Stochastics Rep., 75, No. 3, 153–180 (2003).
N. Lazrieva and T. Toronjadze, “The Polyak weighted averaging procedure for Robbins-Monro type SDE,” Proc. Razmadze Math. Inst., 124, 115–130 (2000).
E. Lenglart, “Sur la convergence presque sure des martingales locales,” C. R. Acad. Sci. Paris Sér. A–B, 284, No. 17, A1085–A1088 (1977).
D. Levanony, A. Shwartz, and O. Zeitouni, “Recursive identification in continuous-time stochastic processes,” Stochastic Process. Appl., 49, No. 2, 245–275 (1994).
R. Sh. Liptser, “A strong law of large numbers for local martingales,” Stochastics, 3, No. 3, 217–228 (1980).
R. Sh. Liptser and A. N. Shiryaev, Martingale Theory [in Russian], Nauka, Moscow (1986).
L. Ljung, G. Pflug, and H. Walk, “Stochastic approximation and optimization of random systems,” in: DMV Seminar, 17, Birkhäuser (1992).
L. Ljung, “Recursive least-squares and accelerated convergence in stochastic approximation schemes,” Int. J. Adapt. Control Signal Process., 15, No. 2, 169–178 (2001).
A. V. Melnikov, “Stochastic approximation procedures for semimartingales,” in: Statistics and Control of Random Processes [in Russian], Nauka, Moscow (1989), pp. 147–156.
A. V. Melnikov and A. E. Rodkina, “Martingale approach to the procedures of stochastic approximation,” in: Proc. Third Finnish-Soviet Symp. on Probability Theory and Mathematical Statistics, Turku, Finland, August 13–16, 1991, VSP. Front. Pure Appl. Probab., 1, Utrecht (1993), pp. 165–182.
A. V. Melnikov, A. E. Rodkina, and E. Valkeila, “On a general class of stochastic approximation algorithms,” in: Proc. Third Finnish-Soviet Symp. on Probability Theory and Mathematical Statistics, Turku, Finland, August 13–16, 1991, VSP. Front. Pure Appl. Probab., 1, Utrecht (1993), pp. 183–196.
A. V. Melnikov and E. Valkeila, “Martingale models of stochastic approximation and their convergence,” Teor. Veroyatn. Primen., 44, No. 2, 278–311 (1999).
M. B. Nevelson and R. Z. Khas’minski, “Stochastic approximation and recurrent estimation,” in: Monogr. Probability Theory and Mathematical Statistics [in Russian], Nauka, Moscow (1972).
B. T. Polyak, “A new method of stochastic approximation type,” Avtomat. Telemekh., 7, 98–107 (1990).
B. T. Polyak and A. B. Juditsky, “Acceleration of stochastic approximation by averaging,” SIAM J. Control Optim., 30, No. 4, 838–855 (1992).
B. L. S. Prakasa Rao, “Semimartingales and their statistical inference,” in: Monogr. on Statistics and Applied Probability, 83 (1999).
H. Robbins and S. Monro, “A stochastic approximation method,” Ann. Math. Statistics, 22, 400–407 (1951).
H. Robbins and D. Siegmund, “A convergence theorem for nonnegative almost supermartingales and some applications,” in: Optimizing Methods in Statistics. Proc. Sympos., Ohio State Univ., Columbus, Ohio, 1971, Academic Press, New York (1971), pp. 233–257.
D. Ruppert, “Efficient estimations from a slowly convergent Robbins-Monro process,” Tech. Rep. 781, School of Oper. Res. and Indust. Eng., Cornell Univ. (1988).
T. Sharia, “On the recursive parameter estimation in the general discrete time statistical model,” Stochastic Process. Appl., 73, No. 2, 151–172 (1998).
P. Spreij, “Recursive approximate maximum likelihood estimation for a class of counting process models,” J. Multivariate Anal., 39, No. 2, 236–245 (1991).
G. Yin and I. Gupta, “On a continuous time stochastic approximation problem. Stochastic optimization,” Acta Appl. Math., 33, No. 1, 3–20 (1993).
G. Yin, “Stochastic approximation: theory and applications,” in: Handbook of Stochastic Analysis and Applications. Statist. Textbooks Monogr., 163, Dekker, New York (2002), pp. 577–624.
Author information
Authors and Affiliations
Corresponding author
Additional information
__________
Translated from Sovremennaya Matematika i Ee Prilozheniya (Contemporary Mathematics and Its Applications), Vol. 45, Martingale Theory and Its Application, 2007.
Rights and permissions
About this article
Cite this article
Lazrieva, N., Sharia, T. & Toronjadze, T. Semimartingale stochastic approximation procedure and recursive estimation. J Math Sci 153, 211–261 (2008). https://doi.org/10.1007/s10958-008-9127-y
Published:
Issue Date:
DOI: https://doi.org/10.1007/s10958-008-9127-y