Abstract
The paper is concerned with stochastic approximation procedures having three main characteristics: truncations with random moving bounds, a matrix-valued random step-size sequence, and a dynamically changing random regression function. We study convergence and rate of convergence. Main results are supplemented with corollaries to establish various sets of sufficient conditions, with the main emphasis on the parametric statistical estimation. The theory is illustrated by examples and special cases.
Article PDF
Similar content being viewed by others
Avoid common mistakes on your manuscript.
References
S. Andradóttir, “A Stochastic Approximation Algorithm with Varying Bounds”, Operations Res. 43 (6), 1037–1048 (1995)
A. Benveniste, M. Métivier, and P. Priouret, Stochastic Approximations and Adaptive Algorithms (Springer-Verlag, 1990).
V. S. Borkar, Stochastic Approximation, in Cambridge Books (Cambridge Univ. Press, Cambridge, 2008).
K. Campbell, “Recursive Computation of M-Estimates for the Parameters of a Finite Autoregressive Process”, Ann. Statist. 442–453 (1982).
H. F. Chen, L. Guo, and A.-J. Gao, “Convergence and Robustness of the Robbins–Monro Algorithm Truncated at Randomly Varying Bounds”, Stoch. Proc. and their Appl. 27, 217–231 (1987).
H. F. Chen and Y. M. Zhu, “Stochastic Approximation Procedures with Randomly Varying Truncations”, Sci. Sinica. Ser. A,Math. Phys. Astronom. & Techn. Sci. 29 (9), 914–926 (1986).
J.-E. Englund, U. Holst, and D. Ruppert, “Recursive Estimators for Stationary, Strong Mixing Processes Representation Theorem and Asymptotic Distributions”, Stoch. Proc. and their Appl. 31 (2), 203–222 (1989).
V. Fabian, “On Asymptotically Efficient Recursive Estimation”, Ann. Statist. 854–866 (1978).
R.A. Horn and C. R. Johnson, Matrix Analysis (Cambridge Univ. Press, Cambridge, 1985).
O. Kallenberg, Foundations of Modern Probability (Springer, 2002).
R. Z. Khas’minskii and M. B. Nevelson, Stochastic Approximation and Recursive Estimation (Nauka, Moscow, 1972) [in Russian].
H. J. Kushner, Stochastic Approximation: A Survey, in Wiley Interdisciplinary Reviews: Computational Statistics (Wiley, 2010), Vol. 2, No. 1, pp. 87–96.
H. J. Kushner and G. Yin, Stochastic Approximation and Recursive Algorithms and Applications (Springer Science & BusinessMedia, 2003), Vol. 35.
T. L. Lai, “Stochastic Approximation”, Ann. Statist. 391–406 (2003).
N. Lazrieva, T. Sharia, and T. Toronjadze, “The Robbins–Monro Type Stochastic Differential Equations. I. Convergence of Solutions”, Stochastics: Intern. J. Probab. and Stoch. Proc. 61 (1–2), 67–87 (1997).
N. Lazrieva, T. Sharia, and T. Toronjadze, “Semimartingale Stochastic Approximation Procedure and Recursive Estimation”, J.Math. Sci. 153 (3), 211–261 (2008).
J. Lelong, “Almost Sure Convergence of Randomly Truncated Stochastic Algorithms under Verifiable Conditions”, Statist. & Probab. Lett. 78 (16), 2632–2636 (2008).
L. Ljung and T. Soderstrom, Theory and Practice of Recursive Identification (The MIT Press, Cambridge, Massachusetts, 1987).
B. T. Poljak and J. Z. Tsypkin, “Robust Identification”, Automatica 16 (1), 53–63 (1980).
H. Robbins and S. Monro, “A Stochastic ApproximationMethod”, Ann. Math. Statist., 400–407 (1951).
H. Robbins and D. Siegmund, “A Convergence Theorem for Nonnegative Almost Supermartingales and Some Applications”, in H. Robbins Selected Papers (Springer, 1985), pp. 111–135.
D. J. Sakrison, “Efficient Recursive Estimation; Application to Estimating the Parameters of a Covariance Function”, Intern. J. Engineer. Sci. 3 (4), 461–483 (1965).
T. Sharia, “Truncated Recursive Estimation Procedures”, Proc. A. Razmadze Math. Inst. 115, 149–159 (1997).
T. Sharia, “On the Recursive Parameter Estimation in the General Discrete Time Statistical Model”, Stoch. Proc. and Their Appl. 73 (2), 151–172 (1998).
T. Sharia, “Rate of Convergence in Recursive Parameter Estimation Procedures”, GeorgianMath. J. 14 (4), 721–736 (2007).
T. Sharia, “Recursive Parameter Estimation: Convergence”, Statist. Infer. for Stoch. Proc. 11 (2), 157–175 (2008).
T. Sharia, “Efficient On-Line Estimation of Autoregressive Parameters”, Math. Methods Statist. 19 (2), 163–186 (2010).
T. Sharia, “Recursive Parameter Estimation: Asymptotic Expansion”, Ann. Instit. Statist. Math. 62 (2), 343–362 (2010).
T. Sharia, “Truncated Stochastic Approximation with Moving Bounds: Convergence”, Statist. Infer. for Stoch. Proc., 1–17 (2014).
V. Tadić, “Stochastic Gradient Algorithm with Random Truncations”, European J. Operat. Res. 101 (2), 261–284 (1997).
V. Tadić, “Stochastic Approximation with Random Truncations, State-Dependent Noise and Discontinuous Dynamics”, Stochastics: Intern. J. Probab. and Stoch. Proc. 64 (3–4), 283–326 (1998).
Author information
Authors and Affiliations
Corresponding author
About this article
Cite this article
Sharia, T., Zhong, L. Rate of convergence of truncated stochastic approximation procedures with moving bounds. Math. Meth. Stat. 25, 262–280 (2016). https://doi.org/10.3103/S1066530716040025
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.3103/S1066530716040025