Statistical Learning Theory and Randomized Algorithms for Control

IEEE Control Systems

Volumn 18, Issue 6, 1998, Pages 69-85

  Vidyasagar, M ^a  

^a and Virtual Reality Groups   (India)

Author keywords

[No Author keywords available]

Indexed keywords

RANDOMIZED ALGORITHMS; STATISTICAL LEARNING THEORY;

COMPUTATIONAL COMPLEXITY; CONTROL SYSTEM SYNTHESIS; LEARNING ALGORITHMS; RANDOM PROCESSES; STATISTICAL METHODS;

CONTROL SYSTEM ANALYSIS;

EID: 0032290586     PISSN: 1066033X     EISSN: None     Source Type: Journal    
DOI: 10.1109/37.736014     Document Type: Article

References (37)

1. A.V. Aho, J.E. Hopcroft, and J.D. Ullman, The Design and Analysis of Coniputer Algorithms, Addison-Wesley, New York, 1974.
2. B.D.O. Anderson, N.K. Bose, and E.I. Jury, “Output feedback stabilization and related problems-Solution via decisionmethods,” IEEE Trans.Automat. Contr., vol. AC-20, pp. 53-66, Feb. 1975.
3. R. Braatz, P. Young,J. Doyle and M. Morari, “Computationalcomplexity of the p calculation,” IEEE Trans.Automat. Contr., vol. 39, pp. 1000-1002, 1994.
4. V. Blondel and J.N. Tsitsiklis, “NP-hardness of some linear control design problems,” SIAM J, Contr.and Opt.,vol. 35, no. 6,pp. 2118-2127,Nov. 1997.
5. H. Chernoff,” A measure of asymptotic efficiency for tests of a hypothesis based on the sum of observations,” Ann. Math. Stat., vol. 23, pp. 493-507, 1952.
6. S.A. Cook, “The complexity of theorem-proving procedures,” Proc. 3rd ACM Symp. Theory of computing, pp. 151-158, 1971.
7. G.E. Coxson and C. DeMarco, “The computational complexity of approximating the minimal perturbalion scaling to achieve instability in an interval matrix,” Math. Control, Signals,Systenis, vol. 7, 279-291, 1994.
8. ∞ Approach,” AIAA Guidance Navigation and Control Conf., Boston, Aug. 10-12, 1998.
9. J. Doyle, “Analysis of feedback systems with structured uncertainties,” Proc. IEEE, vol. 129,pp. 242-250, 1982.
10. E.R. Gantmacher,Matrix Theory, Vol. 11, Chelsea, New York, 1959.
11. M.R. Garey and D.S. Johnson,Computers and Intractabi1ity:A Guide to the Theoi-y of NP-Completeness, W.H. Freeman, New York, 1979.
12. D. Haussler, “Decision theoretic generalizations of the PAC model for neural net and other learning applications,” Inform. and Computation, vol. 100,pp. 78-150, 1992.
13. W. Hoeffding, Probability inequalities for sums of bounded random variables. J. Amer. Statist. Assoc. vol. 58, pp. 13-30, 1963.
14. E.I. Jury, Inners and Stability of Dynamical Systems, John Wiley, New York, 1977.
15. T. Kailath, Linear Systems, Prentice-Hall, Englewood Cliffs, NJ, U.S.A. 1979.
16. M. Karpinski and A.J. Macintyre, “Polynomial bounds for VC dimension of sigmoidal neural networks,” Proc. 27th ACM Synip. Theory of Computing, pp. 200-208, 1995.
17. M. Karpinski and A.J. Macintyre, “Polynomial bounds for VC dimension of sigmoidal and general Pfaffian neural networks,” I. Conf. Sys. Sci., vol. 54, pp. 169-176, 1997.
18. P.P. Khargonekar and A. Tikku, “Randomized algorithms for robust control analysis have polynomial complexity,” Proc. Conf. Decision and Contr, pp. 3470-3475, 1996.
19. A. Kowalczyk, H. Ferra and J. Szymanski, “Combiningstatistical physics with VC-bounds on generalisation in learning systems,” Proc.6th Australian Conf. Neural Networks (ACNN 95), pp. 41-44, Sydney, 1995.
20. A.J. Macintyre and E.D. Sontag,” Finiteness results for sigmoidal neural networks,” Proc. 25th ACM Symp. Theory of Computing, pp. 325-334, 1993.
21. C. Marrison and R. Stengel, “The use of random search and genetic algorithms to optimize stochastic robustness functions,” Proc. Amer. Contr Conf., Baltimore, MD, pp. 1484-1489, 1994.
22. R. Motwani and P. Raghavan, Randoniizcd Algoritlznzs, Cambridge U. Press, Cambridge, 1995.
23. A. Nemirovskii, “Several NP-hard problems arising in robust stability analysis,” Math.of Contr, Signals, and Systems, 6(2), pp. 99-105, 1993.
24. C. Papademitrou, Computational Complexity, Addison-Wesley, Reading, MA, USA, 1994.
25. V.V. Patel and G.S. Deodhare, “Some applications of randomized algorithms for control system design,” submitted for publication.
26. S. Poljak and J. Rohn, “Checking robust nonsingularity is NP-hard,” Math. Contr., Signals, and Systems, vol. 6,no. 1, pp. 1-9, 1993.
27. L.R. Ray and R.F. Stengel, “Stochastic robustness of linear timeinvariant control systems,” IEEE Trans.Autonut. Conti:, vol. 36, pp. 82-87, 1991.
28. M.G. Safanov, “Stability margins of diagonally perturbed multivariable feedback systems,” IEE Proc., Part D, vol. 129, pp. 251-256, 1983.
29. J.M. Steele,” Empirical discrepancies and subadditive processes,” Ann. Prob., vol. 6, pp. 118-127, 1978.
30. R. Tempo,E.W. Bai and E Dabbene, “Probabilisticrobustness analysis: Explicit bounds for the minimum number of sampling points,” Systems & Contr: Letters, vol. 30, pp. 237-242, 1997.
31. J.E. Tierno and J.C. Doyle, “Control problems and the polynomial time hierarchy,” Proc. Conf:Decision and Contn, pp. 2927-2931, 1995.
32. V.N. Vapnik, Estimation uf Dependences Based on Empirical Data, Springer-Verlag, 1982.
33. V.N. Vapnik and A. Ya. Chervonenk relative frequencies to their probabilities, 16, no. 2, pp. 264-280, 1971.
34. V.N. Vapnik and A. Ya. Chervonenkis, “Necessary and and sufficient conditions for the uniform convergence of means to their expectations,” Theory of Proc. and its Appl., vol. 26, no. 3, pp. 532-553, 1981.
35. M. Vidyasagar, A Tlzcwry of Learning and Generalization: With Applications to Neural Networks and Contt.ol Systenzs, Springer-Verlag, London, 1997.
36. M. Vidyasagar, “Statistical lcarning theory and its applications to randomized algorithms for robust controller synthesis,” (Semi-Plenary Talk), European Contr. Conf., Brussels, Belgium, 1997.
37. M. Vidyasagar and V. Blondel, “Randomized algorithms for some NP-hard matrix problems,” to be presented at thc 1998 Conf. Decision and Contr.