Abstract
For the nonantagonistic two-person game which is equivalent to the problem of minimizing the quantile function, a modification of the stochastic quasigradient algorithm to seek the Nash point was proposed. The Nash point defines both the optimal strategy minimizing the quantile function and the minimum value of this function. Convergence of the algorithm with the probability 1 was proved. The question of choosing the starting point was discussed.
Similar content being viewed by others
REFERENCES
Kibzun, A.I. and Kan, Yu.S., Stochastic Programming Problems with Probability and Quantile Functions, Chichester: Wiley, 1996.
Kibzun, A.I. and Kuznetsov, E.A., Optimal Control of the Portfolio, Avtom. Telemekh., 2001, no. 9, pp. 101-113.
Kan, Yu.S., Application of the Quantile Optimization to Bond Portfolio Selection, in Stochastic Optimization Techniques. Numerical Methods and Technical Applications. Lect. Notes Econom. Math. Syst., Marti, K., Ed., Berlin: Springer, 2002.
Kibzun, A.I. and Kurbakovskii, V.Yu., Numerical Algorithms of Quantile Optimization and Their Application to Problems with Probabilistic Constraints, Izv. Ross. Akad. Nauk, Tekh. Kibern., 1991, no. 1, pp. 75-81.
Kibzun, A.I. and Kurbakovskiy, V.Yu., Guaranteeing Approach to Solving Quantile Optimization Problems, Ann. Oper. Res., 1991, vol. 30, pp. 81-93.
Kan, Yu.S., Quasigradient Algorithm of Quantile Function Minimization, Izv. Ross. Akad. Nauk, Teor. Sist. Upravlen., 1996, no. 2, pp. 81-86.
Uryas'ev, S.P., Adaptivnye algoritmy stokhasticheskoi optimizatsii i teorii igr (Adaptive Algorithms of Stochastic Optimization and Game Theory), Moscow: Nauka, 1990.
Lepp, R., Minimization of Smooth Function for Probabilistic Constraints, Izv. Eston. Akad. Nauk, Phys. Math., 1980, vol. 29, no.2, pp. 140-144.
Ermol'ev, Yu.M., Metody stokhasticheskogo programmirovaniya (Methods of Stochastic Programming), Moscow: Nauka, 1976.
Polyak, B.T. and Tsypkin, Ya.Z., Pseudogradient Algorithm of Adaptation and Learning, Avtom. Telemekh., 1973, no. 3, pp. 45-68.
Kibzun, A.I. and Tret'yakov, G.L., Differentiability of the Probability Function, Dokl. Ross. Akad. Nauk, 1997, vol. 354, no.2, pp. 159-161.
Kibzun, A.I. and Tret'yakov, G.L., On Smoothness of the Criteria Function in the Problem of Quantile Optimization, Avtom. Telemekh., 1997, no. 9, pp. 69-80.
Kibzun, A. and Uryasev, S., Differentiability of Probability Function, Stoc. Anal. Appl., 1998, vol. 16, no.6, pp. 1101-1128.
Kan, Yu.S. and Kibzun, A.I., Properties of Convexity of the Probability and Quantile Functions in Optimization Problems, Avtom. Telemekh., 1996, no. 3, pp. 82-102.
Malyshev, V.V. and Kibzun, A.I., Analiz i sintez vysokotochnogo upravleniya letatel'nymi apparatami (High-precision Control of Flight Vehicles: Analysis and Design), Moscow: Mashinostroenie, 1987.
Raik, E., On Problems of Stochastic Programming with Functionals of Probability and Quantile, Izv. Eston. Akad. Nauk, Phys. Math., 1972, vol. 21, no.2, pp. 142-148.
Robbins, H. and Monro, S., A Stochastic Approximation Method, Ann. Math. Statist., 1951, no. 22, pp. 400-407.
Gladyshev, E.G., On Stochastic Approximation, Teor. Veroyatn. Primen., 1965, vol. 10, no.2, pp. 297-300.
Prékopa, A., On Logarithmic Concave Measures and Functions, Acta Sci. Math., 1973, vol. 34, pp. 325-343.
Polyak, B.T., Convergence and Rate of Convergence of Iterative Stochastic Algorithms. I, Avtom. Telemekh., 1976, no. 12, pp. 83-94.
Siegmund, D. and Robbins, H., A Convergence Theorem for Nonnegative Almost Supermartingales and Some Applications, in Optimiz. Methods Statist., Rustaji, J.S., Ed., New York: Academic, 1971.
Nazin, A.V., Metod stokhasticheskoi approksimatsii s usredneniem (Method of Stochastic Approximation with Averaging), Moscow: Mosk. Aviats. Inst., 2001.
Prékopa, A., Logarithmic Concave Measures and Related Topics, in Stochastic Programming, Dempster, M.A.H., Ed., London: Academic, 1980.
Fedorov, V.V., Chislennye metody maksimina (Numerical Maximin Methods), Moscow: Nauka, 1979.
Author information
Authors and Affiliations
Rights and permissions
About this article
Cite this article
Kan, Y.S. On Convergence of a Stochastic Quasigradient Algorithm of Quantile Optimization. Automation and Remote Control 64, 263–278 (2003). https://doi.org/10.1023/A:1022215131373
Issue Date:
DOI: https://doi.org/10.1023/A:1022215131373