Advertisement

Stochastic Heavy-Ball Method for Constrained Stochastic Optimization Problems

  • Porntip Promsinchai
  • Ali Farajzadeh
  • Narin PetrotEmail author
Article

Abstract

In this paper, we consider a heavy-ball method for the constrained stochastic optimization problem by focusing to the situation that the constraint set is specified as the intersection of possibly finitely many constraint sets. A variant algorithm of the stochastic heavy-ball method is proposed which will be incrementally processed by both the stochastic heavy-ball method and random constraint projection simultaneously. They converge almost surely to a solution of the suggested method is exhibited. Finally, a numerical experiment is discussed.

Keywords

Constrained stochastic optimization problem Heavy-ball method Random projection method Converge almost surely 

Mathematics Subject Classification (2010)

90C15 90C25 90C06 65K05 

Notes

Funding Information

This study is supported by the Thailand Research Fund through the Royal Golden Jubilee Ph.D. Program (Grant No. PHD/0023/2555).

References

  1. 1.
    Aronszajn, N.: Theory of reproducing kernels. Trans. Am. Math. Soc. 68, 337–404 (1950)MathSciNetCrossRefGoogle Scholar
  2. 2.
    Bauschke, H.H.: Projection algorithms: results and open problems. Inherently Parallel Algorithms in Feasibility and Optimization and Their Applications. Stud. Comput Math, vol. 8, pp. 11–22. North-Holland (2001)Google Scholar
  3. 3.
    Cauchy, A. -L.: Méthode générale pour la résolution des systèmes d’équations simultanées. Comptes Rendus Hebd. Seances Acad. Sci. 25, 536–538 (1847)Google Scholar
  4. 4.
    Deutsch, F., Hundal, H.: The rate of convergence for the cyclic projections algorithm III: egularity of convex sets. J. Approx. Theory 155(2), 155–184 (2008)MathSciNetCrossRefGoogle Scholar
  5. 5.
    Gubin, L.G., Polyak, B.T., Raik, E.V.: The method of projections for finding the common point of convex sets. USSR Comput. Math. Math. Phys. 7(6), 1–24 (1967)CrossRefGoogle Scholar
  6. 6.
    Ghadimi, E., Feyzmahdavian, H.R., Johansson, M.: Global convergence of the heavy-ball method for convex optimization. arXiv:1412.7457.pdf(2014)
  7. 7.
    Hager, W.W., Zhang, H.: A survey of nonlinear conjugate gradient methods. Pac. J. Optim. 2(1), 35–58 (2006)MathSciNetzbMATHGoogle Scholar
  8. 8.
    Johnson, R., Zhang, T.: Accelerating stochastic gradient descent using predictive variance reduction. Adv. NIPS 26, 315–323 (2013)Google Scholar
  9. 9.
    Loizou, N., Richtarik, P.: Linearly convergent stochastic heavy ball method for minimizing generalization error. In: 10th NIPS Workshop on Optimization for Machine Learning (NIPS 2017) (2017)Google Scholar
  10. 10.
    Nedic, A.: Random projection algorithms for convex set intersection problems. In: 49th IEEE Conference on Decision and Control (CDC), pp. 7655–7660 (2010)Google Scholar
  11. 11.
    Nemirovski, A., Juditsky, A., Lan, G., Shapiro, A.: Robust stochastic approximation approach to stochastic programming. SIAM J. Optim. 19(4), 1574–1609 (2008)MathSciNetCrossRefGoogle Scholar
  12. 12.
    Neumann, J.V.: Functional Operators. Princeton University Press, Princeton (1950)zbMATHGoogle Scholar
  13. 13.
    Nguyen, L.M., Nguyen, P.H., Dijk, M.V., Richtárik, P., Scheinberg, K., Takáč, M.: SGD and Hogwild! convergence without the bounded gradients assumption. Proceedings of the 35th International Conference on Machine Learning PMLR 80, 3747–3755 (2018)Google Scholar
  14. 14.
    Polyak, B.T.: Some methods of speeding up the convergence of iteration methods. USSR Comput. Math. Math. Phys. 4(5), 1–17 (1964)CrossRefGoogle Scholar
  15. 15.
    Robbins, H., Monro, S.: A stochastic approximation method. Ann. Math. Statist. 22, 400–407 (1951)MathSciNetCrossRefGoogle Scholar
  16. 16.
    Robbins, H., Siegmund, D.: A convergence theorem for non negative almost supermartingales and some applications. Optim. Methods Statistics, pp 233–257. Academic Press, N. Y. (1971)Google Scholar
  17. 17.
    Roux, N.L., Schmidt, M., Bach, F.: A stochastic gradient method with an exponential convergence rate for finite training sets. Adv. NIPS 4, 2663–2671 (2012)Google Scholar
  18. 18.
    Schmidt, M., Roux, N.L., Bach, F.: Minimizing finite sums with the stochastic average gradient. Technical report (2013)Google Scholar
  19. 19.
    Shanno, D.F., Phua, K.H.: Algorithm 500: Minimization of unconstrained multivariate functions [E4]. ACM Trans. Math. Softw. 2(1), 87–94 (1976)CrossRefGoogle Scholar
  20. 20.
    Shanno, D.F.: On the convergence of a new conjugate gradient algorithm. SIAM J. Numer. Anal. 15(6), 1247–1257 (1978)MathSciNetCrossRefGoogle Scholar
  21. 21.
    Strohmer, T., Vershynin, R.: A randomized Kaczmarz algorithm with exponential convergence. J. Fourier Anal. Appl. 15(2), 262–278 (2009)MathSciNetCrossRefGoogle Scholar
  22. 22.
    Sun, T., Yin, P., Li, D., Huang, C., Guan, L., Jiang, H.: Non-ergodic convergence analysis of heavy-ball algorithms, arXiv:1811.01777(2018)
  23. 23.
    Wang, M., Bertsekas, D.P.: Stochastic first-order methods with random constraint projection. SIAM J. Optim. 26(1), 681–717 (2016)MathSciNetCrossRefGoogle Scholar

Copyright information

© Institute of Mathematics, Vietnam Academy of Science and Technology (VAST) and Springer Nature Singapore Pte Ltd. 2020

Authors and Affiliations

  1. 1.Department of Mathematics, Faculty of ScienceNaresuan UniversityPhitsanulokThailand
  2. 2.Department of Mathematics, Faculty of ScienceRazi UniversityKermanshahIran

Personalised recommendations