Abstract
Risk-sensitive identification of AR-processes was first considered in [12]. The purpose of this paper is to extend this original approach to ARMA-processes and even to multi-variable linear stochastic systems. We provide a new definition of a risk-sensitive identification criterion. For this we first consider a recursive identification procedure which is parameterized by a weight-matrix K acting on the stochastic gradient. Using the asymptotic theory of recursive estimation a suitably scaled version of the error process will be approximated by a stationary Gaussian process, see Chapter 4.5, Part II of [1]. The new risk sensitive criterion will be defined in terms of this associated stationary Gaussian process in a familiar manner via an exponential-quadratic cost. The main result of the paper is the minimization of the proposed new criterion with respect to the weight-matrix K over a feasible set EK, see (22), where the cost function is known to be finite, Theorem 6.1. This results will then be extended to the case when minimization over a feasible set E°K is considered, see (26), on the complement of which the cost function is known to be infinite, Theorem 6.1. The starting point of our analysis is an expression of the cost function given in LEQG-theory, in particular a result of [10]. A new expression for the cost function will be also given, using stochastic realization theory, as the mutual information rate between two stochastic processes.
Similar content being viewed by others
References
Benveniste A, Metivier M, Priouret P (1990) Adaptive algorithms and stochastic approximations. Springer, Berlin Heidelberg New York
Bensoussan A, van Schuppen JH (1985) Optimal control of partially observable stochastic systems with an exponential-of-integral performance index. SIAM J Control Optim 23:599–613
Gerencsér L (1992) Rate of convergence of recursive estimators. SIAM J Control Optim 30(5):1200–1227
Gerencsér L (1992) A representation theorem for the error of recursive estimators. In: Proceedings of the 31st IEEE conference on decision and control, Tucson, pp 2251–2256
Jacobson DH (1973) Optimal stochastic linear systems with exponential performance criteria and their relation to deterministic differential games. IEEE Trans Automat Control 18:124–131
Kumar PR (1977) Stochastic optimal control and differential games, Department of System Science and Mathematics, Washington University, St. Louis
Kumar PR, van Schuppen JH (1981) On the optimal control of stochastic systems with an exponential-of-integral performance index. J Math Anal Appl 80:312–332
Ljung L, Söderström T (1983) Theory and practice of recursive identification. MIT, Cambridge
Lütkepohl H (1996) Handbook of matrices. Wiley, New York
Mustafa D, Glover K (1990) Minimum entropy H∞ control. Lecture Notes in Control and Information Sciences, vol 146. Springer, Berlin Heidelberg New York
Söderström T, Stoica P (1989) System identification. Prentice Hall, Englewood Cliffs
Stoorvogel A, van Schuppen JH (1996) System identification with information theoretic criteria. In: Bittanti S, Picci G (eds) From identification to learning: the science of learning models from data. NATO ASI series F: Computer and Systems Sciences, vol 153, pp 289–338
Stoorvogel A, van Schuppen JH (1995) System identification with information theoretic criteria. Report BS-R9513, CWI, Amsterdam
Speyer JL, Deyst J, Jacobson DH (1974) Optimization of stochastic linear systems with additive measurement and process noise using exponential performance criteria. IEEE Trans Automat Control 19:358–366
Whitle P (1981) Risk-sensitive Linear/Quadratic/Gaussian control. Adv Appl Prob 13:764–777
Willems JC (1971) Least squares stationary optimal control and the algebraic Riccati equation. IEEE Trans Automat Control 18(6):621–634
Author information
Authors and Affiliations
Corresponding author
Additional information
This research was supported in part by grants from the Swedish Research Council for Engineering Sciences (TFR), the Göran Gustafsson Foundation, the National Research Foundation of Hungary (OTKA) under Grants T015668, T16665, T020984 and T032932.
Rights and permissions
About this article
Cite this article
Gerencsér, L., Michaletzky, G. & Vágó, Z. Risk sensitive identification of linear stochastic systems. Math. Control Signals Syst. 17, 77–100 (2005). https://doi.org/10.1007/s00498-005-0148-5
Received:
Revised:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00498-005-0148-5