Abstract
A problem of minimization of integral losses on given horizon is considered for stochastic system in continuous time. The losses occur in jump times of a Poisson process, and represent continuous convex function of control parameter on convex compact finite-dimensional set. At the jump times an oracle provide stochastically perturbed sub-gradient of the loss function, bounded in mean squares; the noise is additive and centered. Control strategy generated by Mirror Descent algorithm is suggested. For the strategy an explicit upper bound for integral loss discrepancy over its minimum is proved. Example of such strategy application to queueing model is examined.
Similar content being viewed by others
References
Nemirovskii, A.S. and Yudin, D.B., Slozhnost’ zadach i effektivnost’ metodov optimizatsii, Moscow: Nauka, 1979. Translated under the title Problem Complexity and Method Efficiency in Optimization, New York: Wiley, 1983.
Ben-Tal, A., Margalit, T., and Nemirovski, A., The Ordered Subsets Mirror Descent Optimization Method with Applications to Tomography, SIAM J. Optim., 2001, vol. 12, no. 1, pp. 79–108.
Juditsky, A.B., Nazin, A.V., Tsybakov, A.B., and Vayatis, N., Recursive Aggregation of Estimators by the Mirror Descent Algorithm with Averaging, Probl. Inf. Transmis., 2005, vol. 41, no. 4, pp. 368–384.
Nazin, A.V. and Polyak, B.T., Randomized Algorithm to Determine the Eigenvector of a Stochastic Matrix with Application to the PageRank Problem, Autom. Remote Control, 2011, vol. 72, no. 2, pp. 342–352.
Nemirovski, A., Juditsky, A., Lan, G., and Shapiro, A., Robust Stochastic Approximation Approach to Stochastic Programming, SIAM J. Optim., 2009, vol. 19, pp. 1574–1609.
Nesterov, Yu., Primal-Dual Subgradient Methods for Convex Problems, Core Discussion Paper 2005/67, Louvain-la-Neuve, Belgium: Center for Operation Research and Econometrics, 2005.
Author information
Authors and Affiliations
Corresponding author
Additional information
Original Russian Text © A.V. Nazin, S.V. Anulova, A.A. Tremba, 2014, published in Avtomatika i Telemekhanika, 2014, No. 6, pp. 30–38.
Rights and permissions
About this article
Cite this article
Nazin, A.V., Anulova, S.V. & Tremba, A.A. A mirror descent algorithm for minimization of mean Poisson flow driven losses. Autom Remote Control 75, 1010–1016 (2014). https://doi.org/10.1134/S0005117914060022
Received:
Published:
Issue Date:
DOI: https://doi.org/10.1134/S0005117914060022