Hilbert-valued perturbed subgradient algorithms

Mathematics of Operations Research

Volumn 32, Issue 3, 2007, Pages 551-562

  Barty, Kengy ^a   Roy, Jean Sébastien ^a   Strugarek, Cyrille ^b  

^a EDF R AND D   (France)

^b UNIVERSITÉ PARIS EST   (France)

Author keywords

Infinite dimensional problems; Nonsmooth optimization; Perturbed subgradient; Stochastic quasigradient

Indexed keywords

ALGORITHMS; ASYMPTOTIC ANALYSIS; CLOSED LOOP CONTROL SYSTEMS; CONVERGENCE OF NUMERICAL METHODS; DECISION TREES; HILBERT SPACES; OPTIMIZATION; UNCERTAINTY ANALYSIS;

INFINITE DIMENSIONAL PROBLEMS; NONSMOOTH OPTIMIZATION; PERTURBED SUBGRADIENTS; STOCHASTIC QUASIGRADIENT;

PERTURBATION TECHNIQUES;

EID: 38549116701     PISSN: 0364765X     EISSN: 15265471     Source Type: Journal    
DOI: 10.1287/moor.1070.0253     Document Type: Article

References (30)

1. Alber, Y., A. Iusem, M. Solodov. 1998. On the projected subgradient method for nonsmooth convex optimization in a Hilbert space. Math. Programming 81 23-35.
2. Barty, K., J.-S. Roy, C. Strugarek. 2005. A stochastic gradient type algorithm for closed loop problems. Stochastic Programming E-print Series, No. 16. http://www.speps.org.
3. Benvéniste, A., M. Métivier, P. Priouret. 1990. Adaptive Algorithms and Stochastic Approximation. Springer Verlag, New York.
4. Berliocchi, H., J.-M. Lasry. 1972. Nouvelles applications des mesures paramétrées. C. R. Acad. Sci. Paris 274 1623-1626.
5. Bertsekas, D. P., J. N. Tsitsiklis. 2000. Gradient convergence in gradient methods. SIAM J. Optim. 10(3) 627-642.
6. Chen, X., H. White. 1998. Laws of large numbers for Hilbert space-valued mixingales with applications. Econometric Theory 12 284-304.
7. Chen, X., H. White. 2002. Asymptotic properties of some projection-based Robbins-Monro procedures in a Hilbert space. Stud. Nonlinear Dynam. Econom. 6 1-53.
8. Clark, D. S., H. J. Kushner. 1978. Stochastic Approximation for Constrained and Unconstrained Systems. Springer Verlag, New York.
9. Cohen, G. 1984. Décomposition et coordination en optimisation déterministe différentiable et non-différentiable. Thèse de doctorat d'État, Université de Paris IX Dauphine, Paris, France.
10. Cohen, G., J.-C. Culioli. 1990. Decomposition coordination algorithms for stochastic optimization. SIAM J. Control Optim. 28(6) 1372-1403.
11. Delyon, B. 1996. General results on the convergence of stochastic algorithms. IEEE Trans. Autom. Control 41(9) 1245-1255.
12. Derevitskii, D., A. Fradkov. 1974. Two models for analyzing the dynamics of adaptation algorithms. Autom. Remote Control 35 59-67.
13. Duflo, M. 1997. Random Iterative Models. Springer Verlag, Berlin, Germany.
14. Ermoliev, Y. 1966. Methods of solution of nonlinear extremal problems. Cybernetics 2(4) 1-17.
15. Ermoliev, Y. 1969. On the method of generalized stochastic gradients and quasi-Féjer sequences. Cybernetics 5(2) 73-84.
16. Ermoliev, Y. 1976. Methods of Stochastic Programming. Nauka, Moscow, Russia [in Russian].
17. Goldstein, L. 1988. Minimizing noisy functionals in Hilbert spaces: An extension of the Kiefer-Wolfowitz procedure. J. Theoret. Probab. 1 189-204.
18. Hiriart-Urruty, J.-B. 1975. Algorithmes de résolution d'équations et d'inéquations variationnelles. Z. Wahrscheinlichkeitstheorie verwandte Gebiete 33 167-186 [in French].
19. Horn, C., S. R. Kulkarni. 1996. An alternative proof for convergence of stochastic approximation algorithms. IEEE Trans. Autom. Control 41(3) 419-424.
20. Kiefer, J., J. Wolfowitz. 1952. Stochastic estimation of the maximum of a regression function. Ann. Math. Statist. 23 462-466.
21. Lai, T. L. 2003. Stochastic approximation. Ann. Statist. 31(2) 391-406.
22. Métivier, M. 1982. Semimartingales. De Gruyter, Berlin, Germany.
23. Nevel'son, M. B., R. Z. Has'minskii. 1973. Stochastic Approximation and Recursive Estimation. American Mathematical Society, Providence, RI.
24. Polyak, B. T., Y. Z. Tsypkin. 1973. Pseudogradient adaptation and training algorithms. Automation Remote Control 12 83-94.
25. Révész, P. 1973. Robbins-Monro procedure in a Hilbert space and its application in the theory of learning processes. I. Studia Scientiarum Mathematicarum Hungarica 8 391-398.
26. Révész, P. 1973. Robbins-Monro procedure in a Hilbert space. II. Studia Scientiarum Mathematicarum Hungarica 8 469-472.
27. Robbins, H., S. Monro. 1951. A stochastic approximation method. Ann. Math. Statist. 22 400-407.
28. Robbins, H., D. Siegmund. 1971. A convergence theorem for nonnegative almost supermartingales and some applications. J. S. Rustagi, ed. Optimizing Methods in Statistics. Academic Press, New York, 233-257.
29. Salov, G. 1980. On a stochastic approximation theorem in a Hilbert space and its applications. Theory Probab. Appl. 24 413-419.
30. Yin, G., Y. M. Zhu. 1990. On H-valued Robbins-Monro processes. J. Multivariate Anal. 34 116-140.