Mirror Descent and Constrained Online Optimization Problems

  • Alexander A. TitovEmail author
  • Fedor S. Stonyakin
  • Alexander V. Gasnikov
  • Mohammad S. Alkousa
Conference paper
Part of the Communications in Computer and Information Science book series (CCIS, volume 974)


We consider the following class of online optimization problems with functional constraints. Assume, that a finite set of convex Lipschitz-continuous non-smooth functionals are given on a closed set of n-dimensional vector space. The problem is to minimize the arithmetic mean of functionals with a convex Lipschitz-continuous non-smooth constraint. In addition, it is allowed to calculate the (sub)gradient of each functional only once. Using some recently proposed adaptive methods of Mirror Descent the method is suggested to solve the mentioned constrained online optimization problem with an optimal estimate of accuracy. For the corresponding non-Euclidean prox-structure, the case of a set of n-dimensional vectors lying on the standard n-dimensional simplex is considered.


Online convex optimization Non-smooth constrained optimization Adaptive mirror descent Non-euclidean prox-structure Unit simplex 


  1. 1.
    Bayandina, A., Gasnikov, A., Gasnikova, E., Matsievsky, S.: Primal-dual mirror descent for the stochastic programming problems with functional constraints. Comput. Math. Math. Phys. (2018, accepted). (in Russian)
  2. 2.
    Bayandina, A., Dvurechensky, P., Gasnikov, A., Stonyakin, F., Titov, A.: Mirror descent and convex optimization problems with non-smooth inequality constraints. In: Large-Scale and Distributed Optimization, pp. 181–213. Springer, Cham (2018)CrossRefGoogle Scholar
  3. 3.
    Beck, A., Ben-Tal, A., Guttmann-Beck, N., Tetruashvili, L.: The comirror algorithm for solving nonsmooth constrained convex problems. Oper. Res. Lett. 38(6), 493–498 (2010)MathSciNetCrossRefGoogle Scholar
  4. 4.
    Beck, A., Teboulle, M.: Mirror descent and nonlinear projected subgradient methods for convex optimization. Oper. Res. Lett. 31(3), 167–175 (2003)MathSciNetCrossRefGoogle Scholar
  5. 5.
    Ben-Tal, A., Nemirovski, A.: Lectures on Modern Convex Optimization. Society for Industrial and Applied Mathematics, Philadelphia (2001)CrossRefGoogle Scholar
  6. 6.
    Ben-Tal, A., Nemirovski, A.: Robust Truss Topology Design via semidefinite programming. SIAM J. Optim. 7(4), 991–1016 (1997)MathSciNetCrossRefGoogle Scholar
  7. 7.
    Boyd, S., Vandenberghe, L.: Convex Optimization. Cambridge University Press, New York (2004)CrossRefGoogle Scholar
  8. 8.
    Bubeck, S., Eldan, R.: Multi-Scale Exploration of Convex Functions and Bandit Convex Optimization. e-print (2015).
  9. 9.
    Bubeck, S., Cesa-Bianchi, N.: Regret analysis of stochastic and nonstochastic multi-armed bandit problems. Found. Trends Mach. Learn. 5(1), 1–122 (2012)CrossRefGoogle Scholar
  10. 10.
    Gasnikov, A.V., Lagunovskaya, A.A., Morozova, L.E.: On the relationship between simulation logit dynamics in the population game theory and a mirror descent method in online optimization using the example of the shortest path problem. Proc. MIPT 7(4), 104–113 (2015). (in Russian)Google Scholar
  11. 11.
    Gasnikov, A.V., Lagunovskaya, A.A., Usmanova, I.N., Fedorenko, F.A., Krymova, E.A.: Stochastic online optimization. Single-point and multi-point non-linear multi-armed bandits. Convex and strongly-convex case. Autom. Remote Control 78(2), 224–234 (2017)MathSciNetCrossRefGoogle Scholar
  12. 12.
    Hazan, E., Kale, S.: Beyond the regret minimization barrier: optimal algorithms for stochastic strongly-convex optimization. JMLR 15, 2489–2512 (2014)MathSciNetzbMATHGoogle Scholar
  13. 13.
    Hazan, E.: Introduction to online convex optimization. Found. Trends Optim. 2(3–4), 157–325 (2015)Google Scholar
  14. 14.
    Jenatton, R., Huang, J., Archambeau, C.: Adaptive Algorithms for Online Convex Optimization with Long-term Constraints (2015).
  15. 15.
    Kalai, A., Vempala, S.: Efficient algorithms for online decision problems. J. Comput. Syst. Sci. 71, 291–307 (2005)MathSciNetCrossRefGoogle Scholar
  16. 16.
    Lugosi, G., Cesa-Bianchi, N.: Prediction, Learning and Games. Cambridge University Press, New York (2006)zbMATHGoogle Scholar
  17. 17.
    Nemirovskii, A.: Efficient methods for large-scale convex optimization problems. Ekonomika i Matematicheskie Metody (1979). (in Russian)Google Scholar
  18. 18.
    Nemirovsky, A., Yudin, D.: Problem Complexity and Method Efficiency in Optimization. Wiley, New York (1983)Google Scholar
  19. 19.
    Nesterov, Y.: Introductory Lectures on Convex Optimization: A Basic Course. Kluwer Academic Publishers, Massachusetts (2004)CrossRefGoogle Scholar
  20. 20.
    Polyak, B.: A general method of solving extremum problems. Sov. Math. Dokl. 8(3), 593–597 (1967). (in Russian)zbMATHGoogle Scholar
  21. 21.
    Shor, N.Z.: Generalized gradient descent with application to block programming. Kibernetika 3(3), 53–55 (1967). (in Russian)MathSciNetGoogle Scholar
  22. 22.
    Stonyakin, F.S., Alkousa, M.S., Stepanov, A.N., Barinov, M.A.: Adaptive mirror descent algorithms in convex programming problems with Lipschitz constraints. Trudy Instituta Matematiki i Mekhaniki URO RAN 24(2), 266–279 (2018)CrossRefGoogle Scholar
  23. 23.
    Shpirko, S., Nesterov, Y.: Primal-dual subgradient methods for huge-scale linear conic problem. SIAM J. Optim. 24(3), 1444–1457 (2014)MathSciNetCrossRefGoogle Scholar
  24. 24.
    Vasilyev, F.: Optimization Methods. Fizmatlit, Moscow (2002). (in Russian)Google Scholar

Copyright information

© Springer Nature Switzerland AG 2019

Authors and Affiliations

  • Alexander A. Titov
    • 1
    Email author
  • Fedor S. Stonyakin
    • 1
    • 2
  • Alexander V. Gasnikov
    • 1
    • 3
  • Mohammad S. Alkousa
    • 1
  1. 1.Moscow Institute of Physics and TechnologiesMoscowRussia
  2. 2.V. I. Vernadsky Crimean Federal UniversitySimferopolRussia
  3. 3.Adyghe State University, Caucasus Mathematical CenterMaykopRussia

Personalised recommendations