Randomized algorithms for robust controller synthesis using statistical learning theory: A tutorial overview

European Journal of Control

Volumn 7, Issue 2-3, 2001, Pages 287-310

  Vidyasagar, M ^a  

^a TATA CONSULTANCY SERVICES   (India)

Author keywords

Computational complexity; Randomized alogorithm; Robust control; Statistical learning theory

Indexed keywords

EID: 1542700719     PISSN: 09473580     EISSN: None     Source Type: Journal    
DOI: 10.3166/ejc.7.287-310     Document Type: Article

References (37)

1. Braatz R, Young P, Doyle J, Morari M. Computational complexity of the μ calculation. IEEE Trans Auto Control 1994; 39: 1000-1002
2. Blondel V, Tsitsiklis JN. NP-hardness of some linear control design problems. SIAM J Control Opt 1997; 35(6): 2118-2127
3. Blondel V, Tsitsiklis JN. A survey of computational complexity results in systems and control. Automatica 2000; 45(9): 1249-1274
4. Coxson GE, DeMarco C. The computational complexity of approximating the minimal perturbation scaling to achieve instability in an interval matrix. Math Control, Signals Systems 1994; 7: 279-291
5. Doyle J. Analysis of feedback systems with structured uncertainties. Proc IEEE 1982; 129: 242-250
6. Fine TL. Feedforward neural network methodology. Springer-Verlag, New York, 1999
7. Gantmacher FR. Matrix theory, vol II. Chelsea, New York, 1959
8. Garey MR, Johnson DS. Computers and intractability: a guide to the theory of NP-completeness. W.H. Freeman, New York, 1979
9. Haussler D. Decision theoretic generalizations of the PAC model for neural net and other learning applications. Information and Computation 1992; 100: 78-150
10. Hoeffding W. Probability inequalities for sums of bounded random variables. J Amer Statist Assoc 1993; 58: 13-30
11. Jury EI. Inners and stability of dynamical systems. John Wiley, New York, 1977
12. Kailath T. Linear systems. Prentice-Hall, Englewood Cliffs, NJ, USA, 1979
13. Karpinski M, Macintyre AJ. Polynomial bounds for VC dimension of sigmoidal neural networks. Proc 27th ACM Symp Thy. Computing 1995, pp 200-208
14. Karpinski M, Macintyre AJ. Polynomial bounds for VC dimension of sigmoidal and general Pfaffian neural networks. J Comp Sys Sci 1997; 54: 169-176
15. Khargonekar PP, Tikku A. Randomized algorithms for robust control analysis have polynomial complexity. Proc Conf Decision Control, 1996
16. Kowalczyk A. Ferra H, Szymanski J. Combining statistical physics with VC-bounds on generalisation in learning systems. Proc Sixth Australian Conf Neural Networks (ACNN'95). Sydney, 1995, pp 41-44
17. Macintyre AJ, Sontag ED. Finiteness results for sigmoidal neural networks. Proc 25th ACM Symp. Thy of Computing 1993, pp 325-334
18. Marrison C, Stengel R. The use of random search and genetic algorithms to optimize stochastic robustness functions. Proc Amer Control Conf Baltimore, MD. 1994, pp 1484-1489
19. Massart P. The tight constant in the Dvoretzky-Kiefer-Wolfowitz inequality. Ann Prob 1990; 18(3): 1269-1283
20. Motwani R, Raghavan P. Randomized algorithms. Cambridge University Press, Cambridge, 1995
21. Nemirovskii A. Several NP-hard problems arising in robust stability analysis. Math Control, Signals, and Systems 1993; 6(2): 99-105
22. Newton GC Jr, Gould LA, Kaiser JF. Analytic design of linear feedback controls. John Wiley, New York, 1967
23. Papadimitrou C. Computational complexity. Addison-Wesley, Reading, MA, USA, 1994
24. Patel VV, Deodhare GS, Viswanath T. Some applications of randomized algorithms for control system design. Submitted to Automatica, 2000
25. Parrondo JM, van den Broeck C. Vapnik-Chervonenkis bounds for generalization. J Phys A 1993; 26: 2211-2223
26. Poljak S, Rohn J. Checking robust nonsingularity is NP-hard. Math Control, Signals, and Systems 1993; 6(1): 1-9
27. Ray LR, Stengel RF. Stochastic robustness of linear time-invariant control systems. IEEE Trans Auto Control 1991; 36: 82-87
28. Steele JM. Empirical discrepancies and subadditive processes. Ann Prob 1978; 6: 118-127
29. Tempo RE, Bai W, Dabbene F. Probabilistic robustness analysis: Explicit bounds for the minimum number of sampling points. Systems & Control Letters 1997; 30: 237-242
30. Vapnik VN. Estimation of dependences based on empirical data. Springer-Verlag, 1982
31. Vapnik VN. Statistical learning theory. John Wiley, New York, 1998
32. Vapnik VN, Chervonenkis AYa. On the uniform convergence of relative frequencies to their probabilities. Theory Prob its Appl 1971; 16(2): 264-280
33. Vapnik VN, Chervonenkis AYa. Necessary and sufficient conditions for the uniform convergence of means to their expectations. Theory Prob its Appl 1981; 26(3): 532-553
34. Vidyasagar M. A theory of learning and generalization: with applications to neural networks and control systems. Springer-Verlag, London 1997
35. Vidyasagar M. Statistical learning theory and its applications to randomized algorithms for robust controller synthesis. Semi-Plenary Lecture, European Control Conference, Brussels, Belgium (G. Basten and M. Gevers, eds.), pp. 161-189, 1997
36. Vidyasagar M. Randomized algorithms for robust controller synthesis using statistical learning theory. Automatica (to appear)
37. Vidyasagar M, Blondel V. Probabilistic solutions to some NP-hard matrix problems. Automatica (to appear)