Abstract
A new method of entropy-robust nonparametric estimation of probability density functions (PDFs) of the characteristics of dynamic randomized models with structured nonlinearities given a small amount of data is proposed. Optimal PDFs are shown to belong to the exponential class with Lagrange multipliers being its parameters. In order to determine these parameters, a system of equations with integral components is constructed. An algorithm for solving this problem is developed based on parallel Monte Carlo techniques. The accuracy of the numerical integration for the given class of integral components and the probability of its achievement are estimated. The method is applied to a second-degree nonlinear dynamic system with the given structure of exponential nonlinearity.
This is a preview of subscription content, log in via an institution to check access.
Similar content being viewed by others
References
Yu. S. Popkov, A. Yu. Popkov, and Yu. V. Lysak, “Estimation of characteristics of randomized static models of data (entropy-robust approach),” Autom. Remote Control. 74, 1863–1877 (2013).
Yu. S. Popkov, A. Yu. Popkov, and Yu. V. Lysak, “Estimating the characteristics of randomized dynamic data models (the entropy-robust approach),” Autom. Remote Control. 75, 872–879 (2014).
E. T. Jaynes, “Information theory and statistical mechanics,” Phys. Rev. 106, 620–630 (1957).
A. Golan, “Information and entropy econometrics–a review and synthesis,” Found. Trends Econometr. 2, 1–145 (2008).
Ya. Z. Tsypkin and Yu. S. Popkov, Theory of Nonlinear Pulse Systems (Nauka, Moscow, 1973) [in Russian].
A. M. Rubinov, Abstact Convexity and Global Optimization (Kluwer, Dordrecht, 2000).
A. S. Strekalovskii, Elements of Non-Convex Optimization (Nauka, Novosibirsk, 2003) [in Russian].
R. Batti, M. Brunato, and F. Mascia, Reactive Search and Intelligent Optimazation. Operation Reasearch, Computer Science Interfaces Series, Vol. 45 (Springer, Berlin, 2008).
R. G. Strongin and Yu. D. Sergeyev, Global Optimization with Non-Convex Constraints (Kluwer Academic, Dordrecht, 2000).
Ya. D. Sergeyev, R. G. Strongin, and D. Lera, Introduction to Global Optimization Exploiting Space-Filling Curves (Springer, New York, 2013).
I. M. Sobol, Numerical Monte-Carlo Methods (Nauka, Moscow, 1973) [in Russian].
Z. B. Zabinsky, R. L. Smith, F. McDonald, H. E. Romeijn, and D. E. Kaufman, “Improving hit-and-run for global optimization,” J. Global Optim. 3, 171–192 (1993).
A. Zhigljavsky, Theory of Global Random Search, Ser. Mathematics and Applications (Kluwer Academic, Dordrecht, 1991).
R. E. Caflisch, “Monte Carlo and quasi-Monte Carlo methods,” Acta Numer., p.1–49 (1998).
I. Foster, Designing and Building Parallel Programs: Consepts and Tools for Parallel Software Engineering (Addison Wesley Longman, Boston, MA, 1995).
V. V. Voevodin and Vl. V. Voevodin, Parallel Computing (BKhV-Peterburg, St. Petersburg, 2004) [in Russian].
L. F. Shampine, “MatLab program for quadrature in 2D,” Appl. Math. Comput. 202, 266–274 (2008).
I. M. Gelfand and S. V. Fomin, Calculus of Variations (Prentice-Hall, Englewood Cliffs, NY, 1963).
Author information
Authors and Affiliations
Corresponding author
Additional information
Original Russian Text © Yu.S. Popkov, A.Yu. Popkov, B.S. Darkhovsky, 2015, published in Matematicheskoe Modelirovanie, 2015, Vol. 27, No. 6, pp. 14–32.
Rights and permissions
About this article
Cite this article
Popkov, Y.S., Popkov, A.Y. & Darkhovsky, B.S. Parallel Monte Carlo for entropy robust estimation. Math Models Comput Simul 8, 27–39 (2016). https://doi.org/10.1134/S2070048216010087
Received:
Published:
Issue Date:
DOI: https://doi.org/10.1134/S2070048216010087