Computational Optimization and Applications

, Volume 74, Issue 3, pp 779–820 | Cite as

Optimal stochastic extragradient schemes for pseudomonotone stochastic variational inequality problems and their variants

  • Aswin Kannan
  • Uday V. ShanbhagEmail author


We consider the stochastic variational inequality problem in which the map is expectation-valued in a component-wise sense. Much of the available convergence theory and rate statements for stochastic approximation schemes are limited to monotone maps. However, non-monotone stochastic variational inequality problems are not uncommon and are seen to arise from product pricing, fractional optimization problems, and subclasses of economic equilibrium problems. Motivated by the need to address a broader class of maps, we make the following contributions: (1) we present an extragradient-based stochastic approximation scheme and prove that the iterates converge to a solution of the original problem under either pseudomonotonicity requirements or a suitably defined acute angle condition. Such statements are shown to be generalizable to the stochastic mirror-prox framework; (2) under strong pseudomonotonicity, we show that the mean-squared error in the solution iterates produced by the extragradient SA scheme converges at the optimal rate of \({{\mathcal {O}}}\left( \frac{1}{{K}}\right) \), statements that were hitherto unavailable in this regime. Notably, we optimize the initial steplength by obtaining an \(\epsilon \)-infimum of a discontinuous nonconvex function. Similar statements are derived for mirror-prox generalizations and can accommodate monotone SVIs under a weak-sharpness requirement. Finally, both the asymptotics and the empirical rates of the schemes are studied on a set of variational problems where it is seen that the theoretically specified initial steplength leads to significant performance benefits.


Variational inequality problems Stochastic approximation Pseudomonotone 



The authors are grateful to Dr. Farzad Yousefian for his valuable suggestions on a previous version. We particularly appreciate the comments of the referees and the editor, all of which have led to significant improvements in the manuscript.


  1. 1.
    Facchinei, F., Pang, J.-S.: Finite Dimensional Variational Inequalities and Complementarity Problems, vol. 1, 2. Springer, New York (2003)zbMATHGoogle Scholar
  2. 2.
    Konnov, I.V.: Equilibrium Models and Variational Inequalities. Elsevier, Amsterdam (2007)zbMATHGoogle Scholar
  3. 3.
    Brighi, L., John, R.: Characterizations of pseudomonotone maps and economic equilibrium. J. Stat. Manag. Syst. 5(1–3), 253–273 (2002)MathSciNetzbMATHGoogle Scholar
  4. 4.
    Kihlstrom, R., Mas-Colell, A., Sonnenschein, H.: The demand theory of the weak axiom of revealed preference. Econometrica 44(5), 971–978 (1976)MathSciNetzbMATHGoogle Scholar
  5. 5.
    Elizarov, A.M.: Maximizing the lift-drag ratio of wing airfoils with a turbulent boundary layer: exact solutions and approximations. Dokl. Phys. 53(4), 221–227 (2008)zbMATHGoogle Scholar
  6. 6.
    Rousseau, A., Sharer, P., Pagerit, S., Das, S.: Trade-off between fuel economy and cost for advanced vehicle configurations. In: Proceedings of the 20th International Electric Vehicle Symposium, Monaco (2005)Google Scholar
  7. 7.
    Duensing, G.R., Brooker, H.R., Fitzsimmons, J.R.: Maximizing signal-to-noise ratio in the presence of coil coupling. J. Magn. Reson. Ser. B 111(3), 230–235 (1996)Google Scholar
  8. 8.
    Shadwick, W., Keating, C.: A universal performance measure. J. Perform. Meas. 6(3), 59–84 (2002)Google Scholar
  9. 9.
    Hossein, K., Thomas, S., Raj, G.: Omega as a Performance Measure. Preliminary Report, Duke University (2003)Google Scholar
  10. 10.
    Chandra, S.: Strong pseudo-convex programming. Indian J. Pure Appl. Math. 3(2), 278–282 (1972)MathSciNetzbMATHGoogle Scholar
  11. 11.
    Hobbs, B.F.: Mill pricing versus spatial price discrimination under Bertrand and Cournot spatial competition. J. Ind. Econ. 35(2), 173–191 (1986)Google Scholar
  12. 12.
    Choi, S.C., Desarbo, W.S., Harker, P.T.: Product positioning under price competition. Manag. Sci. 36(2), 175–199 (1990)zbMATHGoogle Scholar
  13. 13.
    Garrow, L.A., Koppelman, F.S.: Multinomial and nested logit models of airline passengers’ no-show and standby behaviour. J. Revenue Pricing Manag. 3(3), 237–253 (2004)Google Scholar
  14. 14.
    Newman, J.P.: Normalization of network generalized extreme value models. Transp. Res. Part B Methodol. 42(10), 958–969 (2008)Google Scholar
  15. 15.
    Cliquet, G.: Implementing a subjective MCI model: an application to the furniture market. Eur. J. Oper. Res. 84(2), 279–291 (1995)zbMATHGoogle Scholar
  16. 16.
    Nakanishi, M., Cooper, L.G.: Parameter estimation for a multiplicative competitive interaction model: least squares approach. J. Market. Res. 11(3), 303–311 (1974)Google Scholar
  17. 17.
    Gallego, G., Hu, M.: Dynamic pricing of perishable assets under competition. Manag. Sci. 60(5), 1241–1259 (2014)Google Scholar
  18. 18.
    Ewerhart, C.: Cournot games with biconcave demand. Games Econ. Behav. 85, 37–47 (2014)MathSciNetzbMATHGoogle Scholar
  19. 19.
    Shapiro, A., Dentcheva, D., Ruszczynski, A.: Lectures on Stochastic Programming: Modeling and Theory. The Society for Industrial and Applied Mathematics and the Mathematical Programming Society, Philadelphia (2009)zbMATHGoogle Scholar
  20. 20.
    Xu, H.: Sample average approximation methods for a class of stochastic variational inequality problems. Asia-Pac. J. Oper. Res. 27(1), 103–119 (2010)MathSciNetzbMATHGoogle Scholar
  21. 21.
    Lu, S., Budhiraja, A.: Confidence regions for stochastic variational inequalities. Math. Oper. Res. 38(3), 545–568 (2013)MathSciNetzbMATHGoogle Scholar
  22. 22.
    Lu, S.: Symmetric confidence regions and confidence intervals for normal map formulations of stochastic variational inequalities. SIAM J. Optim. 24(3), 1458–1484 (2014)MathSciNetzbMATHGoogle Scholar
  23. 23.
    Robbins, H., Monro, S.: A stochastic approximation method. Ann. Math. Stat. 22, 400–407 (1951)MathSciNetzbMATHGoogle Scholar
  24. 24.
    Kushner, H.J., Yin, G.G.: Stochastic Approximation and Recursive Algorithms and Applications. Springer, New York (2003)zbMATHGoogle Scholar
  25. 25.
    Borkar, V.S.: Stochastic Approximation: A Dynamical Systems Viewpoint. Cambridge University Press, Cambridge (2008)zbMATHGoogle Scholar
  26. 26.
    Spall, J.C.: Introduction to Stochastic Search and Optimization: Estimation, Simulation, and Control. Wiley Series in Discrete Mathematics and Optimization. Wiley, New York (2005)zbMATHGoogle Scholar
  27. 27.
    Nemirovski, A.S., Judin, D.B.: On Cezari’s convergence of the steepest descent method for approximating saddle point of convex–concave functions. In: Soviet Mathematics-Doklady, vol. 19 (1978)Google Scholar
  28. 28.
    Ruppert, D.: Efficient Estimations from a Slowly Convergent Robbins–Monro Process. Cornell University Technical Report, Operations Research and Industrial Engineering (1988)Google Scholar
  29. 29.
    Polyak, B.T.: New stochastic approximation type procedures. Autom. Telem. 7, 98–107 (1990)Google Scholar
  30. 30.
    Polyak, B.T., Juditsky, A.: Acceleration of stochastic approximation by averaging. SIAM J. Control Optim. 30(4), 838–855 (1992)MathSciNetzbMATHGoogle Scholar
  31. 31.
    Kushner, H.J., Yang, J.: Stochastic approximation with averaging of the iterates: optimal asymptotic rate of convergence for general processes. SIAM J. Control Optim. 31(4), 1045–1062 (1993)MathSciNetzbMATHGoogle Scholar
  32. 32.
    Kushner, H.J., Yang, J.: Analysis of adaptive step-size SA algorithms for parameter tracking. IEEE Trans. Autom. Control 40(8), 1403–1410 (1995)MathSciNetzbMATHGoogle Scholar
  33. 33.
    Nemirovski, A.S., Yudin, D.B.: Problem Complexity and Method Efficiency in Optimization. Wiley-Interscience, New York, Translated by E. R. Dawson (1983)Google Scholar
  34. 34.
    Nemirovski, A., Juditsky, A., Lan, G., Shapiro, A.: Robust stochastic approximation approach to stochastic programming. SIAM J. Optim. 19(4), 1574–1609 (2009)MathSciNetzbMATHGoogle Scholar
  35. 35.
    Ghadimi, S., Lan, G.: Optimal stochastic approximation algorithms for strongly convex stochastic composite optimization, I: a generic algorithmic framework. SIAM J. Optim. 22(4), 1469–1492 (2012)MathSciNetzbMATHGoogle Scholar
  36. 36.
    Ghadimi, S., Lan, G.: Optimal stochastic approximation algorithms for strongly convex stochastic composite optimization, II: shrinking procedures and optimal algorithms. SIAM J. Optim. 23(4), 2061–2089 (2013)MathSciNetzbMATHGoogle Scholar
  37. 37.
    Bertsekas, D., Tsitsiklis, J.: Gradient convergence in gradient methods with errors. SIAM J. Optim. 10(3), 627–642 (2000)MathSciNetzbMATHGoogle Scholar
  38. 38.
    Ghadimi, S., Lan, G.: Stochastic first- and zeroth-order methods for nonconvex stochastic programming. SIAM J. Optim. 23(4), 2341–2368 (2013)MathSciNetzbMATHGoogle Scholar
  39. 39.
    Jiang, H., Xu, H.: Stochastic approximation approaches to the stochastic variational inequality problem. IEEE Trans. Autom. Control 53(6), 1462–1475 (2008)MathSciNetzbMATHGoogle Scholar
  40. 40.
    Koshal, J., Nedić, A., Shanbhag, U.V.: Regularized iterative stochastic approximation methods for stochastic variational inequality problems. IEEE Trans. Autom. Control 58(3), 594–609 (2013)MathSciNetzbMATHGoogle Scholar
  41. 41.
    Yousefian, F., Nedić, A., Shanbhag, U.V.: A regularized smoothing stochastic approximation (RSSA) algorithm for stochastic variational inequality problems. In: Proceedings of the Winter Simulation Conference (WSC), pp. 933–944 (2013)Google Scholar
  42. 42.
    Juditsky, A., Nemirovski, A., Tauvel, C.: Solving variational inequalities with stochastic mirror-prox algorithm. Stoch. Syst. 1(1), 17–58 (2011)MathSciNetzbMATHGoogle Scholar
  43. 43.
    Yousefian, F., Nedić, A., Shanbhag, U.V.: Optimal robust smoothing extragradient algorithms for stochastic variational inequality problems. In 53rd IEEE Conference on Decision and Control, pp. 5831–5836 (2014)Google Scholar
  44. 44.
    Chen, Y., Lan, G., Ouyang, Y.: Accelerated schemes for a class of variational inequalities. Math. Program. 165(1), 113–149 (2017)MathSciNetzbMATHGoogle Scholar
  45. 45.
    Kannan, A., Shanbhag, U.V.: The pseudomonotone stochastic variational inequality problem: analytical statements and stochastic extragradient schemes. In: American Control Conference, ACC 2014, Portland, OR, USA, June 4–6, 2014, pp. 2930–2935. IEEE (2014)Google Scholar
  46. 46.
    Iusem, A.N., Jofré, A., Oliveira, R.I., Thompson, P.: Extragradient method with variance reduction for stochastic variational inequalities. SIAM J. Optim. 27(2), 686–724 (2017)MathSciNetzbMATHGoogle Scholar
  47. 47.
    Yousefian, F., Nedić, A., Shanbhag, U.V.: On stochastic mirror-prox algorithms for stochastic Cartesian variational inequalities: randomized block coordinate and optimal averaging schemes. Set-Valued Var. Anal. 26(4), 789–819 (2018)MathSciNetzbMATHGoogle Scholar
  48. 48.
    Yousefian, F., Nedić, A., Shanbhag, U.V.: Self-tuned stochastic approximation schemes for non-Lipschitzian stochastic multi-user optimization and Nash games. IEEE Trans. Autom. Control 61(7), 1753–1766 (2016)MathSciNetzbMATHGoogle Scholar
  49. 49.
    Iusem, A.N., Jofré, A., Thompson, P.: Incremental constraint projection methods for monotone stochastic variational inequalities. Math. Oper. Res. (2018). CrossRefGoogle Scholar
  50. 50.
    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)MathSciNetzbMATHGoogle Scholar
  51. 51.
    Polyak, B.T.: Introduction to Optimization. Optimization Software Inc., New York (1987)zbMATHGoogle Scholar
  52. 52.
    Nemirovski, A.: Prox-method with rate of convergence \({O}(1/{T})\) for variational inequalities with Lipschitz continuous monotone operators and smooth convex-concave saddle point problems. SIAM J. Optim. 15(1), 229–251 (2005)MathSciNetzbMATHGoogle Scholar
  53. 53.
    Dang, C.D., Lan, G.: On the convergence properties of non-Euclidean extragradient methods for variational inequalities with generalized monotone operators. Comput. Optim. Appl. 60(2), 277–310 (2015)MathSciNetzbMATHGoogle Scholar
  54. 54.
    Dvurechensky, P., Gasnikov, A., Stonyakin, F., Titov, A.: Generalized Mirror Prox: Solving Variational Inequalities with Monotone Operator, Inexact Oracle, and Unknown Hölder Parameters. arxiv:1806.05140.pdf (2018)
  55. 55.
    Nesterov, Y.: Introductory lectures on convex optimization: a basic course. In: Pardalos, P., Hearn, D. (eds.) Applied Optimization. Kluwer, Dordrecht (2004)zbMATHGoogle Scholar
  56. 56.
    Watson, L.T.: Solving the nonlinear complementarity problem by a homotopy method. SIAM J. Control Optim. 17(1), 36–46 (1979)MathSciNetzbMATHGoogle Scholar
  57. 57.
    Kannan, A., Shanbhag, U.V.: Distributed computation of equilibria in monotone Nash games via iterative regularization techniques. SIAM J. Optim. 22(4), 1177–1205 (2012)MathSciNetzbMATHGoogle Scholar
  58. 58.
    Allaz, B., Vila, J.L.: Cournot competition, forward markets and efficiency. J. Econ. Theory 59(1), 1–16 (1993)zbMATHGoogle Scholar
  59. 59.
    Facchinei, F., Kanzow, C.: Generalized Nash equilibrium problems. 4OR 5(3), 173–210 (2007)MathSciNetzbMATHGoogle Scholar

Copyright information

© Springer Science+Business Media, LLC, part of Springer Nature 2019

Authors and Affiliations

  1. 1.India Research Laboratory (IRL), IBM ResearchChennaiIndia
  2. 2.Industrial and Manufacturing EngineeringThe Pennsylvania State UniversityUniversity ParkUSA

Personalised recommendations