A learning theory approach to system identification and stochastic adaptive control

Journal of Process Control

Volumn 18, Issue 3-4, 2008, Pages 421-430

  Vidyasagar, M ^a   Karandikar, Rajeeva L ^b  

^a Cranes Software International Limited ^*  (India)

^b Cranes Software International Limited   (India)

Author keywords

Statistical learning theory; Stochastic adaptive control; System identification

Indexed keywords

COMPUTATIONAL COMPLEXITY; IDENTIFICATION (CONTROL SYSTEMS); PROBLEM SOLVING; ROBUST CONTROL; STATISTICAL METHODS;

LEARNING THEORY; STATISTICAL LEARNING THEORY; STOCHASTIC ADAPTIVE CONTROL;

STOCHASTIC CONTROL SYSTEMS;

EID: 40849089395     PISSN: 09591524     EISSN: None     Source Type: Journal    
DOI: 10.1016/j.jprocont.2007.10.009     Document Type: Article

References (20)

1. E. Weyer, R.C. Williamson, I. Mareels, Sample complexity of least squares identification of FIR models, in: Proceedings of the 13th World Congress of IFAC, San Francisco, CA, July 1996, pp. 239-244.
2. Weyer E., Williamson R.C., and Mareels I. Finite sample properties of linear model identification. IEEE Trans. Automat. Contr. 44 7 (1999) 1370-1383
3. Weyer E. Finite sample properties of system identification of ARX models under mixing conditions. Automatica 36 9 (2000) 1291-1299
4. Ljung L. Convergence analysis of parametric identification methods. IEEE Trans. Automat. Contr. AC-23 5 (1978) 770-783
5. Caines P.E. Prediction error identification methods for stationary stochastic processes. IEEE Trans. Automat. Contr. AC-21 4 (1976) 500-505
6. Caines P.E. Stationary linear and nonlinear system identification and predictor set completeness. IEEE Trans. Automat. Contr. AC-23 4 (1978) 583-594
7. G. Zames, A.K. El-Sakkary, Unstable systems and feedback: The gap metric, in: Proceedings of the Allerton Conference, 1980, pp. 380-385.
8. Georgiou T.T., and Smith M.C. Optimal robustness in the gap metric. IEEE Trans. Automat. Contr. AC-35 6 (1992) 673-686
9. Vidyasagar M. The graph metric for unstable plants and robustness estimates for feedback stability. IEEE Trans. Automat. Contr. AC-29 5 (1984) 403-418
10. Weyer E., and Campi M.C. Non-asymptotic confidence ellipsoids for the least squares error estimate. Automatica 38 (2002) 1529-1547
11. Campi M.C., and Weyer E. Finite sample properties of system identification methods. IEEE Trans. Automat. Contr. 47 (2002) 1329-1334
12. Karandikar R.L., and Vidyasagar M. Rates of uniform convergence of empirical means with mixing processes. Stat. Probabil. Lett. 58 (2002) 297-307
13. Vapnik V.N., and Chervonenkis A.Ya. Necessary and sufficient conditions for the uniform convergence of means to their expectations. Theory Probab. Appl. 26 3 (1981) 532-553
14. Vapnik V.N., and Chervonenkis A.Ya. On the uniform convergence of relative frequencies to their probabilities. Theory Probab. Appl. 16 2 (1971) 264-280
15. Vidyasagar M. A Theory of Learning and Generalization (1997), Springer-Verlag, London
16. Dasgupta B., and Sontag E.D. Sample complexity for learning recurrent perceptron mappings. IEEE Trans. Inform. Theory 42 (1996) 1479-1487
17. M. Karpinski, A.J. Macintyre, Polynomial bounds for VC dimension of sigmoidal neural networks, in: Proc. 27th ACM Symp. Theory Comput., 1995, pp. 200-208.
18. Karpinski M., and Macintyre A.J. Polynomial bounds for VC dimension of sigmoidal and general Pfaffian neural networks. J. Comput. Syst. Sci. 54 (1997) 169-176
19. A.J. Macintyre, E.D. Sontag, Finiteness results for sigmoidal neural networks, in: Proc. 25th ACM Symp. Theory of Comput., 1993, pp. 325-334.
20. Meyn S.P., and Tweedie R.L. Markov Chains and Stochastic Stability (1993), Springer-Verlag, London