Finite sample properties of linear model identification

IEEE Transactions on Automatic Control

Volumn 44, Issue 7, 1999, Pages 1370-1383

  Weyer, Erik ^b   Williamson, Robert C ^c   Mareels, Iven M Y ^a,b  

^a IEEE

^b UNIVERSITY OF MELBOURNE   (Australia)

^c AUSTRALIAN NATIONAL UNIVERSITY   (Australia)

Author keywords

ARX models; Finite sample properties; FIR models; Least squares system identification; Risk minimization theory

Indexed keywords

RISK MINIMIZATION THEORY;

LEAST SQUARES APPROXIMATIONS; MATHEMATICAL MODELS; PROBABILITY;

LINEAR CONTROL SYSTEMS;

EID: 0032689410     PISSN: 00189286     EISSN: None     Source Type: Journal    
DOI: 10.1109/9.774109     Document Type: Article

References (23)

1. M. A. Dahleh, T. V. Theodosopoulos, and J. N. Tsitsiklis, "The sample complexity of worst-case identification of FIR linear systems," Syst. Contr. Lett., vol. 20, pp. 157-166, 1993.
2. B. Dasgupta and E. D. Sontag, "Sample complexity for learning recurrent perceptron mappings," IEEE Trans. Inform. Theory, vol. 42, pp. 1479-1437.
3. L. Gerencsèr, "On a class of mixing processes," Stochastics, vol. 26, pp. 165-191, 1989.
4. M. Gevers, "Toward a joint design of identification and control?" in Essays on Control: Perspectives in the Theory and its Applications, H. L. Trentelman and J. C. Willems, Eds. Boston, MA: Birkhäuser, 1993, pp. 111-151.
5. L. Giarre, B. Kacewicz, and M. Milanese, "Model quality evaluation in set membership identification," Automatica, vol. 33, pp. 1133-1140, 1997.
6. G. C. Goodwin and R. L. Payne, Dynamic System Identification: Experiment Design and Data Analysis. New York: Academic, 1977.
7. D. Haussler, "Decision theoretic generalizations of the PAC model for neural net and other learning applications," Inform. Computation, vol. 100, pp. 78-150, 1992.
8. H. Hjalmarson, "Aspects on incomplete modeling in system identification," Ph.D. dissertation, Department of Electrical Engineering, Linköping Univ., Sweden, 1993.
9. A. Hole, "Vapnik-Chervonenkis generalization bounds for real valued neural networks," Neural Computation, vol. 8, no. 6, pp. 1277-1299, 1996.
10. P. J. Huber, Robust Statistics. New York: Wiley, 1981.
11. 1 system identification," in Proc. 31st IEEE Conf. Decision and Control, Tucson, AZ, 1992, pp. 56-61.
12. L. Ljung, "Convergence analysis of parametric identification methods," IEEE Trans. Automat. Contr., vol. 23, pp. 770-783, 1978.
13. _, System Identification - Theory for the User. Englewood Cliffs, NJ: Prentice-Hall, 1987.
14. _, "Perspectives on the process of identification," Preprints 12th IFAC World Congr., Sydney, Australia, 1993, vol. 5, pp. 197-205.
15. K. Poolla and A. Tikku, "On the time complexity of worst-case system identification," IEEE Trans. Automat. Contr., vol. 39, pp. 944-950, May 1994.
16. J. C. Spall, "Uncertainty bounds for parameter identification with small sample sizes," in Proc. 34th IEEE Conf. Decision and Control, New Orleans, LA, 1994, pp. 3504-3515.
17. T. Söderström and P. Stoica, System Identification. Englewood Cliffs, NJ: Prentice-Hall, 1988.
18. P. M. J. Van den Hof and R. J. P. Schrama, "Identification and control-closed loop issues," in Preprints 10th IFAC Symp. System Identification, Copenhagen, Denmark, 1994, vol. 2, pp. 1-13.
19. A. W. Van der Vaart and J. A. Wellner, Weak Convergence and Empirical Processes. New York: Springer Verlag, 1996.
20. V. N. Vapnik, Estimation of Dependences Based on Empirical Data. New York: Springer Verlag, 1982.
21. _, The Nature of Statistical Learning Theory. New York: Springer Verlag, 1995.
22. E. Weyer, "System identification in the behavioral framework," Ph.D. dissertation, The Norwegian Inst. Technol., Trondheim, Norway, 1992.
23. G. Zames, L. Lin, and L. Y. Wang, "Fast identification n-widths and uncertainty principles for LTI and slowly varying systems," IEEE Trans. Automat. Contr., vol. 39, pp. 1827-1838, Sept. 1994.