A statistical learning theory approach for uncertain linear and bilinear matrix inequalities. (English) Zbl 1296.93208
Summary: In this paper, we consider the problem of minimizing a linear functional subject to uncertain linear and bilinear matrix inequalities, which depend in a possibly nonlinear way on a vector of uncertain parameters. Motivated by recent results in statistical learning theory, we show that probabilistic guaranteed solutions can be obtained by means of randomized algorithms. In particular, we show that the Vapnik-Chervonenkis dimension (VC-dimension) of the two problems is finite, and we compute upper bounds on it. In turn, these bounds allow us to derive explicitly the sample complexity of these problems. Using these bounds, in the second part of the paper, we derive a sequential scheme, based on a sequence of optimization and validation steps. The algorithm is on the same lines of recent schemes proposed for similar problems, but improves both in terms of complexity and generality. The effectiveness of this approach is shown using a linear model of a robot manipulator subject to uncertain parameters.
MSC:
| 93E35 | Stochastic learning and adaptive control |
| 93C10 | Nonlinear systems in control theory |
| 93C41 | Control/observation systems with incomplete information |
| 93E25 | Computational methods in stochastic control (MSC2010) |
Keywords:
statistical learning theory; Vapnik-Chervonenkis dimension; uncertain linear/bilinear matrix inequality; randomized algorithms; probabilistic designReferences:
| [1] | Alamo, T.; Luque, A.; Ramirez, D.; Tempo, R., Randomized control design through probabilistic validation, (Proc. of the American control conference (2012)), 839-844, see also The sample complexity of randomized methods for analysis and design of uncertain systems, arXiv:1304.0678 [cs.SY] |
| [2] | Alamo, T.; Tempo, R.; Camacho, E., Randomized strategies for probabilistic solutions of uncertain feasibility and optimization problems, IEEE Transactions on Automatic Control, 54, 2545-2559 (2009) · Zbl 1367.90106 |
| [3] | Alamo, T.; Tempo, R.; Ramirez, D.; Camacho, E., A new vertex result for robustness problems with interval matrix uncertainty, Systems Control Letters, 57, 474-481 (2008) · Zbl 1154.93023 |
| [4] | Bernstein, D., Matrix mathematics: theory, facts, and formulas (2009), Princeton University Press · Zbl 1183.15001 |
| [5] | Boyd, S.; El Ghaoui, L.; Feron, E.; Balakrishnan, V., Linear matrix inequalities in system and control theory (1994), SIAM: SIAM Philadelphia · Zbl 0816.93004 |
| [6] | Calafiore, G.; Campi, M., Uncertain convex programs: randomized solutions and confidence levels, Mathematical Programming, 102, 25-46 (2004) · Zbl 1177.90317 |
| [7] | Calafiore, G.; Campi, M., The scenario approach to robust control design, IEEE Transactions on Automatic Control, 51, 742-753 (2006) · Zbl 1366.93457 |
| [8] | Calafiore, G.; Dabbene, F., A reduced vertex set result for interval semidefinite optimization problems, Journal of Optimization Theory and Applications, 139, 17-33 (2008) · Zbl 1189.90114 |
| [9] | Calafiore, G.; Dabbene, F., A probabilistic analytic center cutting plane method for feasibility of uncertain LMIs, Automatica, 43, 2022-2033 (2007) · Zbl 1138.93027 |
| [10] | Calafiore, G.; Dabbene, F.; Tempo, R., Research on probabilistic methods for control system design, Automatica, 47, 1279-1293 (2011) · Zbl 1219.93038 |
| [11] | Calafiore, G.; Polyak, B., Stochastic algorithms for exact and approximate feasibility of robust LMIs, IEEE Transactions on Automatic Control, 46, 1755-1759 (2001) · Zbl 1007.93080 |
| [12] | Campi, M.; Garatti, S., The exact feasibility of randomized solutions of uncertain convex programs, SIAM Journal on Optimization, 19, 1211-1230 (2008) · Zbl 1180.90235 |
| [15] | El Ghaoui, L.; Lebret, H., Robust solutions to uncertain semidefinite programs, SIAM Journal on Optimization, 9, 33-52 (1998) · Zbl 0960.93007 |
| [16] | Fujisaki, Y.; Kozawa, Y., Probabilistic robust controller design: probable near minimax value and randomized algorithms, (Calafiore, G.; Dabbene, F., Probabilistic and randomized methods for design under uncertainty (2006), Springer), 317-329 · Zbl 1274.93282 |
| [17] | Goh, K.; Safonov, M.; Papavassilopoulos, G., Global optimization for the biaffine matrix inequality problem, Journal of Global Optimization, 7, 365-380 (1995) · Zbl 0844.90083 |
| [18] | Kanev, S.; De Schutter, B.; Verhaegen, M., An ellipsoid algorithm for probabilistic robust controller design, Systems Control Letters, 49, 365-375 (2003) · Zbl 1157.93389 |
| [19] | Kanev, S.; Verhaegen, M., Controller reconfiguration for non-linear systems, Control Engineering Practice, 8, 1223-1235 (2000) |
| [20] | Karpinski, M.; Macintyre, A., Polynomial bounds for VC dimension of sigmoidal and general Pfaffian neural networks, Journal of Computer and System Sciences, 54, 169-176 (1995) · Zbl 0869.68088 |
| [21] | Koltchinskii, V.; Abdallah, C.; Ariola, M.; Dorato, P.; Panchenko, D., Improved sample complexity estimates for statistical learning control of uncertain systems, IEEE Transactions on Automatic Control, 45, 2383-2388 (2000) · Zbl 0991.93130 |
| [22] | Kočvara, M.; Stingl, M., PENNON: a code for convex nonlinear and semidefinite programming, Optimization Methods & Software, 18, 317-333 (2003) · Zbl 1037.90003 |
| [23] | Leibfritz, F., COMPleib: COnstrained matrix optimization problem library, (Technical report (2004)) |
| [25] | Oishi, Y., Polynomial-time algorithms for probabilistic solutions of parameter-dependent linear matrix inequalities, Automatica, 43, 3, 538-545 (2007) · Zbl 1137.93425 |
| [26] | Polyak, B.; Tempo, R., Probabilistic robust design with linear quadratic regulators, Systems Control Letters, 43, 343-353 (2001) · Zbl 0974.93070 |
| [27] | Sauer, N., On the density of families of sets, Journal of Combinatorial Theory, Series A, 13, 145-147 (1972) · Zbl 0248.05005 |
| [28] | Kanev, S.; Scherer, C.; Verhaegen, M.; De Schutter, B., Robust output-feedback controller design via local BMI optimization, Automatica, 40, 1115-1127 (2004) · Zbl 1051.93042 |
| [29] | Tempo, R.; Calafiore, G.; Dabbene, F., Randomized algorithms for analysis and control of uncertain systems: with applications (2013), Springer: Springer London · Zbl 1280.93002 |
| [30] | Todd, M., Semidefinite optimization, Acta Numerica, 10, 515-560 (2001) · Zbl 1105.65334 |
| [31] | Tremba, A.; Calafiore, G.; Dabbene, F.; Gryazina, E.; Polyak, B.; Shcherbakov, P., RACT: randomized algorithms control toolbox for MATLAB, (Proc. of the 17th IFAC World Congress, Seoul (2008)), 390-395 |
| [32] | Uryasev, S., Probabilistic constrained optimization: methodology and applications (2000), Kluwer Academic Publishers: Kluwer Academic Publishers New York · Zbl 0959.00019 |
| [33] | VanAntwerp, J. G.; Braatz, R. D., A tutorial on linear and bilinear matrix inequalities, Journal of Process Control, 10, 363-385 (2000) |
| [34] | Vandenberghe, L.; Boyd, S., Semidefinite programming, SIAM Review, 38, 49-95 (1996) · Zbl 0845.65023 |
| [35] | Vapnik, V., Statistical learning theory (1998), Wiley-Interscience · Zbl 0935.62007 |
| [36] | Vapnik, V.; Chervonenkis, A., On the uniform convergence of relative frequencies to their probabilities, Theory of Probability and Its Applications, 16, 264-280 (1971) · Zbl 0247.60005 |
| [37] | Vidyasagar, M., Learning and generalization: with applications to neural networks (2002), Springer |
| [38] | Vidyasagar, M., Randomized algorithms for robust controller synthesis using statistical learning theory, Automatica, 37, 1515-1528 (2001) · Zbl 1055.93512 |
| [39] | Vidyasagar, M.; Blondel, V., Probabilistic solutions to some NP-hard matrix problems, Automatica, 37, 1397-1405 (2001) · Zbl 1031.93165 |
This reference list is based on information provided by the publisher or from digital mathematics libraries. Its items are heuristically matched to zbMATH identifiers and may contain data conversion errors. In some cases that data have been complemented/enhanced by data from zbMATH Open. This attempts to reflect the references listed in the original paper as accurately as possible without claiming completeness or a perfect matching.
