On fixed gain recursive estimators with discontinuity in the parameters

In this paper, we estimate the expected tracking error of a fixed gain stochastic approximation scheme. The underlying process is not assumed Markovian, a mixing condition is required instead. Furthermore, the updating function may be discontinuous in the parameter.

[1]  M. Rásonyi.  On the statistical analysis of quantized Gaussian AR(1) processes , 2009 .

[2]  E. Eweda.  Convergence analysis of an adaptive filter equipped with the sign-sign algorithm , 1995, IEEE Trans. Autom. Control..

[3]  László Gerencsér,et al.  AR(infty) estimation and nonparametric stochastic complexity , 1992, IEEE Trans. Inf. Theory.

[4]  Jonathan C. Mattingly,et al.  Yet Another Look at Harris’ Ergodic Theorem for Markov Chains , 2008, 0810.2777.

[5]  László Gerencsér,et al.  A Representation Theorem for the Error of Recursive Estimators , 1992, Proceedings of the 45th IEEE Conference on Decision and Control.

[6]  L. Gerencsér,et al.  New methods for the statistical analysis of Hidden Markov Models , 2002, Proceedings of the 41st IEEE Conference on Decision and Control, 2002..

[7]  L. Gerencsér.  On a class of mixing processes , 1989 .

[8]  M. Rosenbaum,et al.  Volatility is rough , 2014, 1410.3394.

[9]  Ferenc Szidarovszky,et al.  Modeling uncertainty : an examination of stochastic theory, methods, and applications , 2002 .

[10]  Gilles Pagès,et al.  Convergence of the one-dimensional Kohonen algorithm , 1998, Advances in Applied Probability.

[11]  L. Gerencsér.  Strong approximation of the recursive prediction error estimator of the parameters of an ARMA process , 1993 .

[12]  L. Gerencs.  On Fixed Gain Recursive Estimation Processes , 1996 .

[13]  E. Eweda,et al.  Analysis and design of a signed regressor LMS algorithm for stationary and nonstationary adaptive filtering with correlated Gaussian data , 1990 .

[14]  L. Gerencsér.  On Rissanen's predictive stochastic complexity for stationary ARMA processes , 1994 .

[15]  Persi Diaconis,et al.  Iterated Random Functions , 1999, SIAM Rev..

[16]  T. Kohonen.  Analysis of a simple self-organizing process , 1982, Biological Cybernetics.

[17]  S. Ethier,et al.  Markov Processes: Characterization and Convergence , 2005 .

[18]  László Gerencsér,et al.  Stability of Random Iterative Mappings , 2005 .

[19]  F. Comte,et al.  Long memory in continuous‐time stochastic volatility models , 1998 .

[20]  Liudas Giraitis,et al.  Large Sample Inference for Long Memory Processes , 2012 .

[21]  V. Jonker,et al.  TH' , 2019, Dictionary of Upriver Halkomelem.

[22]  R. Bhattacharya,et al.  An Approach to the Existence of Unique Invariant Probabilities for Markov Processes ∗ , 1999 .

[23]  J. Neveu,et al.  Discrete Parameter Martingales , 1975 .

[24]  L. Gerencsér.  Rate of convergence of recursive estimators , 1992 .

[25]  Gilles Pagès,et al.  Stochastic approximation with averaging innovation applied to Finance , 2010, Monte Carlo Methods Appl..

[26]  G. Fort,et al.  Convergence of Markovian Stochastic Approximation with Discontinuous Dynamics , 2014, SIAM J. Control. Optim..

[27]  T. Kawata.  Fourier analysis in probability theory , 1972 .

[28]  M. Manhart,et al.  Markov Processes , 2018, Introduction to Stochastic Processes and Simulation.

[29]  R. Koenker,et al.  Regression Quantiles , 2007 .

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

[31]  O. Kallenberg.  Foundations of Modern Probability , 2021, Probability Theory and Stochastic Modelling.

[32]  S. Geman.  SOME AVERAGING AND STABILITY RESULTS FOR RANDOM DIFFERENTIAL EQUATIONS , 1979 .

[33]  N. G. Parke,et al.  Ordinary Differential Equations. , 1958 .

[34]  M. Rosenbaum,et al.  Volatility is rough , 2018 .