Stochastic gradient algorithm with random truncations

European Journal of Operational Research

Volumn 101, Issue 2, 1997, Pages 261-284

  Tadić, Vladislav ^a  

^a MIHAJLO PUPIN INSTITUTE   (Serbia)

Author keywords

Gradient methods; Stochastic approximation; Stochastic optimization; Uniform mixing

Indexed keywords

ALGORITHMS; OPTIMIZATION; PROBABILITY; RANDOM PROCESSES;

GRADIENT METHODS; STOCHASTIC APPROXIMATION;

MATHEMATICAL TECHNIQUES;

EID: 0031221985     PISSN: 03772217     EISSN: None     Source Type: Journal    
DOI: 10.1016/S0377-2217(96)00397-9     Document Type: Article

References (21)

1. A. Benveniste, M. Métivier, P. Priouret, Adaptive Algorithms and Stochastic Approximation, Springer-Verlag, Berlin, 1990.
2. H.-F. Chen, Y.-M. Zhu, Stochastic approximation with randomly varying truncations, Scientia Sinica. Series A 29 (9) (1986) 914-926.
3. H.-F. Chen, L. Guo, A.-J. Gao, Convergence and robustness of the Robins-Monro algorithm truncated at randomly varying bounds, Stochastic Processes and their Applications 27 (2) (1988) 217-231.
4. H.-F. Chen, A.-J. Gao, Robustness analysis for stochastic approximation algorithms, Stochastics and Stochastics Reports 26 (1) (1989) 3-20.
5. S.N. Ethier, T.G. Kurtz, Markov Processes: Characterization and Convergence, Wiley, New York, 1986.
6. Yu.M. Ermoliev, Stochastic Programming Methods, Nauka, Moscow, 1976.
7. Yu.M. Ermoliev, A.A. Gaivoronski, Stochastic quasigradient methods for optimization of discrete event systems, Annals of Operations Research 39 (1992) 1-39.
8. A.A. Gaivoronski, On nonstationary stochastic optimization problems, Kibernetika (4) (1978) 89-92.
9. A.A. Gaivoronski, Approximation methods of solution of stochastic programming problems, Kibernetika (2) (1982) 85-90.
10. S.R. Kulkarni, C.S. Horn, Necessary and sufficient conditions for convergence of stochastic approximation algorithms under arbitrary disturbances, in: Proceedings of the 34th Conference on Decision and Control, 1995, 3843-3848.
11. H.J. Kushner, D.S. Clark, Stochastic Approximation Methods for Constrained and Unconstrained Systems, Springer-Verlag, Berlin, 1978.
12. H.J. Kushner, Stochastic approximation with discontinuous dynamics and state dependent noise: w.p.l and weak convergence, Journal of Mathematical Analysis and Applications 82 (1981) 527-542.
13. J.P. LaSalle, The Stability of Dynamical Systems, SIAM, Philadelphia, PA, 1976.
14. L. Ljung, G. Pflug, H. Walk, Stochastic Approximation and Optimization of Random Systems, Birkhäuser Verlag, Basel, 1992.
15. M.B. Nevel'son, R.Z. Has'minskii, Stochastic Approximation and Recursive Estimation, American Mathematical Society, Providence, RI, 1976.
16. G.Ch. Pflug, On-line optimization of simulated Markovian processes, Mathematics of Operations Research 15 (3) (1990) 381-395.
17. M. Rosenblatt, Markov Processes: Structure and Asymptotic Behavior, Springer-Verlag, Berlin, 1971.
18. A.N. Shiryayev, Probability, Springer-Verlag, Berlin, 1984.
19. V. Tadić, Analysis of a class of recursive algorithms of the stochastic approximation type, M.Sc. Thesis, Department of Electrical Engineering, University of Belgrade, 1995.
20. G. Yin, Y.-M. Zhu, Almost sure convergence of stochastic approximation algorithms with non-additive noise, International Journal of Control 49 (4) (1989) 1361-1376.
21. Y.-M. Zhu, Stochastic approximation under a class of measurement errors, Acta Mathematica Scientia 5 (1) (1985) 105-117.