Skip to main content
Springer Nature Link
Log in

Improved variance reduction extragradient method with line search for stochastic variational inequalities

  • Published:
Journal of Global Optimization Aims and scope Submit manuscript

Abstract

In this paper, we investigate the numerical methods for solving stochastic variational inequalities. Using line search scheme, we propose an improved variance based stochastic extragradient method with different step sizes in the prediction and correction steps. The range of correction step size which can guarantee the convergence is also given. For the initial line search step size of each iteration, an adaptive method is adopted. Rather than the same scale for each reduction, a proportional reduction related to the problem is used to meet the line search criteria. Under the assumptions of Lipschitz continuous, pseudo-monotone operator and independent identically distributed sampling, the iterative complexity and the oracle complexity are obtained. When estimating the upper bound of the second order moment of the martingale difference sequence, we give a more convenient and comprehensible proof instead of using the Burkholder-Davis-Gundy inequality. The proposed algorithm is applied to fractional programming problems and the \(l_2\) regularized logistic regression problem. The numerical results demonstrate its superiority.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Subscribe and save

Springer+ Basic
$34.99 /Month
  • Get 10 units per month
  • Download Article/Chapter or eBook
  • 1 Unit = 1 Article or 1 Chapter
  • Cancel anytime
Subscribe now

Buy Now

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5

Similar content being viewed by others

References

  1. Agarwal, A.: Information-theoretic lower bounds on the oracle complexity of stochastic convex optimization. IEEE Trans. Inform. Theory 58(5), 3235–3249 (2012)

    Article  MathSciNet  MATH  Google Scholar 

  2. Bach, F., Moulines, E.: Non-asymptotic analysis of stochastic approximation algorithms for machine learning. Neural Information Processing Systems (NIPS), Spain. hal-00608041, (2011)

  3. Bertsekas, D.P.: Nonlinear Programming, 3rd edn. Athena Scientific, Belmont, Massachusetts (2016)

    MATH  Google Scholar 

  4. Bertsekas, D.P., Nedić, A., Ozdaglar, A.E.: Convex Analysis and Optimization. Athena Scientific, Belmont, Massachusetts (2003)

    MATH  Google Scholar 

  5. Bot, R.I., Mertikopoulos, P., Staudigl, M., Vuong, P.T.: Forward-backward-forward methods with variance reduction for stochastic variational inequalities. arXiv preprint arXiv:1902.03355v1 (2019)

  6. Bottou, L., Curtis, F.E., Nocedal, J.: Optimization methods for large-scale machine learning. SIAM Rev. 60(2), 223–311 (2018)

    Article  MathSciNet  MATH  Google Scholar 

  7. Boucheron, S., Lugosi, G., Massart, P.: Concentration Inequalities: A Nonasymptotic Theory of Independence. Clarendon Press, Oxford (2012)

    MATH  Google Scholar 

  8. Cai, X., Gu, G., He, B.: On the O(1/t) convergence rate of the projection and contraction methods for variational inequalities with Lipschitz continuous monotone operators. Comput. Optim. Appl. 57(2), 339–363 (2014)

    Article  MathSciNet  MATH  Google Scholar 

  9. Cai, X., Han, D., Xu, L.: An improved first-order primal-dual algorithm with a new correction step. J. Global Optim. 57(4), 1419–1428 (2013)

    Article  MathSciNet  MATH  Google Scholar 

  10. Chen, Y., Lan, G., Ouyang, Y.: Accelerated schemes for a class of variational inequalities. Math. Program. 165(1), 113–149 (2017)

    Article  MathSciNet  MATH  Google Scholar 

  11. Dong, X., Cai, X., Han, D.: Prediction-correction method with BB step sizes. Front. Math. China 13(6), 1325–1340 (2018)

    Article  MathSciNet  MATH  Google Scholar 

  12. Facchinei, F., Pang, J.-S.: Finite-dimensional Variational Inequalities and Complementarity Problems, vol. I. Springer, New York (2003)

    MATH  Google Scholar 

  13. Gidel, G., Berard, H., Vincent, P., Julien, S.: A variational inequality perspective on generative adversarial nets. arXiv preprint arXiv:1802.10551v3 (2018)

  14. He, B.: My 20 years research on alternating directions method of multipliers. Oper. Res. Trans. 22(1), 1–31 (2018)

    MathSciNet  MATH  Google Scholar 

  15. He, B., Liao, L.: Improvements of some projection methods for monotone nonlinear variational inequalities. J. Optim. Theory Appl. 112(1), 111–128 (2002)

    Article  MathSciNet  MATH  Google Scholar 

  16. He, B., Yang, Z., Yuan, X.: An approximate proximal-extragradient type method for monotone variational inequalities. J. Math. Anal. Appl. 300(2), 362–374 (2004)

    Article  MathSciNet  MATH  Google Scholar 

  17. Iusem, A., Jofré, A., Oliveira, R., Thompson, P.: Extragradient method with variance reduction for stochastic variational inequalities. SIAM J. Optim. 27(2), 686–724 (2017)

    Article  MathSciNet  MATH  Google Scholar 

  18. Iusem, A., Jofré, A., Oliveira, R., Thompson, P.: Variance-based extragradient methods with line search for stochastic variational inequalities. SIAM J. Optim. 29(1), 175–206 (2019)

    Article  MathSciNet  MATH  Google Scholar 

  19. Iusem, A., Jofré, A., Thompson, P.: Incremental constraint projection methods for monotone stochastic variational inequalities. Math. Oper. Res. 44(1), 236–263 (2019)

    MathSciNet  MATH  Google Scholar 

  20. Jiang, H., Xu, H.: Stochastic approximation approaches to the stochastic variational inequality problem. IEEE Trans. Automat. Control 53(6), 1462–1475 (2008)

    Article  MathSciNet  MATH  Google Scholar 

  21. Johnson, R., Zhang, T.: Accelerating stochastic gradient descent using predictive variance reduction. In Advances in Neural Information Processing Systems 26. Vol. 1, 315-323 (2013)

  22. Juditsky, A., Nemirovski, A., Tauvel, C.: Solving variational inequalities with stochastic mirror-proximal algorithm. Stoch. Syst. 1(1), 17–58 (1987)

    Article  MATH  Google Scholar 

  23. Kannan, A., Shanbhag, U.V.: Optimal stochastic extragradient schemes for pseudomonotone stochastic variational inequality problems and their variants. Comput. Optim. Appl. 74(3), 779–820 (2019)

    Article  MathSciNet  MATH  Google Scholar 

  24. Khobotov, E.: Modification of the extra-gradient method for solving variational inequalities and certain optimization problems. USSR Comput. Math. Math. Phys. 27(5), 120–127 (1987)

    Article  MathSciNet  MATH  Google Scholar 

  25. Korpelevič, G.M.: An extragradient method for finding saddle points and for other problems. Matecon 12(4), 747–756 (1976)

    MathSciNet  Google Scholar 

  26. Koshal, J., Nedić, A., Shanbhag, U.V.: Regularized iterative stochastic approximation methods for stochastic variational inequality problems. IEEE Trans. Automat. Control 58(3), 594–609 (2013)

    Article  MathSciNet  MATH  Google Scholar 

  27. Krejic, N., Luzanin, Z., Nikolovski, F., Stojkovska, I.: A nonmonotone line search method for noisy minimization. Optim. Lett. 9(7), 1371–1391 (2015)

    Article  MathSciNet  MATH  Google Scholar 

  28. Krejic, N., Luzanin, Z., Ovcinz, S.: Descent direction method with line search for unconstrained optimization in noisy environment. Optim. Methods Softw. 30(6), 1164–1184 (2015)

    Article  MathSciNet  MATH  Google Scholar 

  29. Liu, J., Hou, Y., Kompella, S., Sherali, H.: Conjugate gradient projection approach for multi-antenna Gaussian broadcast channels. 2007 IEEE International Symposium on Information Theory. 781-785 (2007)

  30. Mahsereci, M., Hennig, P.: Probabilistic line searches for stochastic optimization. J. Mach. Learn. Res. 18(119), 1–59 (2017)

    MathSciNet  MATH  Google Scholar 

  31. Mishchenko, K., Kovalev, D., Shulgin, E., Richtárik, P., Malitsky, Y.: Revisiting stochastic extragradient. arXiv preprint arXiv:1905.11373v2 (2020)

  32. Nemirovski, A., Juditsky, A., Lan, G., Shapiro, A.: Robust stochastic approximation approach to stochastic programming. SIAM J. Optim. 19(4), 1574–1609 (2009)

    Article  MathSciNet  MATH  Google Scholar 

  33. Polyak, B.: New method of stochastic approximation type. Autom. Remote Control. 51(7), 937–1008 (1990)

    MathSciNet  MATH  Google Scholar 

  34. Robbins, H., Monro, S.: A stochastic approximation method. Ann. Math. Statist. 22(3), 400–407 (1951)

    Article  MathSciNet  MATH  Google Scholar 

  35. Shapiro, A., Dentcheva, D., Ruszczyňski, A.: Lectures on Stochastic Programming: Modeling and Theory. SIAM, Philadelphia (2009)

    Book  MATH  Google Scholar 

  36. Shen, K., Yu, W.: Fractional programming for communication systems-part I: power control and beamforming. IEEE Trans. Signal Process. 66(10), 2616–2630 (2018)

    Article  MathSciNet  MATH  Google Scholar 

  37. Telatar, E.: Capacity of multi-antenna Gaussian channels. Eur. Trans. Telecommun. 10(6), 585–595 (1999)

    Article  MathSciNet  Google Scholar 

  38. Wardi, Y.: Stochastic algorithms with armijo stepsizes for minimization of functions. J. Optim. Theory Appl. 64(2), 399–417 (1990)

    Article  MathSciNet  MATH  Google Scholar 

  39. Xu, H.: Sample average approximation methods for a class of stochastic variational inequality problems. Asia-Pac. J. Oper. Res. 27(1), 103–119 (2010)

    Article  MathSciNet  MATH  Google Scholar 

  40. Yousefian, F., Nedić, A., Shanbhag, U.V.: On stochastic gradient and subgradient methods with adaptive steplength sequences. Automatica 48(1), 56–67 (2012)

    Article  MathSciNet  MATH  Google Scholar 

  41. Yousefian, F., Nedić, A., Shanbhag, U.V.: On smoothing, regularization, and averaging in stochastic approximation methods for stochastic variational inequality problems. Math. Program. 165(1), 391–431 (2017)

    Article  MathSciNet  MATH  Google Scholar 

Download references

Acknowledgements

This research is supported by the National Natural Science Foundation of China (Grant Nos. 11871279, 12131004 and 11571178).

Author information

Authors and Affiliations

  1. Jiangsu Key Laboratory for NSLSCS, School of Mathematical Sciences, Nanjing Normal University, Nanjing, 210023, People’s Republic of China

    Ting Li, Xingju Cai, Yongzhong Song & Yumin Ma

Authors
  1. Ting Li
    View author publications

    You can also search for this author inPubMed Google Scholar

  2. Xingju Cai
    View author publications

    You can also search for this author inPubMed Google Scholar

  3. Yongzhong Song
    View author publications

    You can also search for this author inPubMed Google Scholar

  4. Yumin Ma
    View author publications

    You can also search for this author inPubMed Google Scholar

Corresponding author

Correspondence to Yumin Ma.

Additional information

Publisher's Note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Li, T., Cai, X., Song, Y. et al. Improved variance reduction extragradient method with line search for stochastic variational inequalities. J Glob Optim 87, 423–446 (2023). https://doi.org/10.1007/s10898-022-01135-1

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s10898-022-01135-1

Keywords

Mathematics Subject Classification