Skip to main content
SpringerLink
Log in

Dynamical Behavior of a Stochastic Forward–Backward Algorithm Using Random Monotone Operators

  • Published:
Journal of Optimization Theory and Applications Aims and scope Submit manuscript

Abstract

The purpose of this paper is to study the dynamical behavior of the sequence produced by a Forward–Backward algorithm, involving two random maximal monotone operators and a sequence of decreasing step sizes. Defining a mean monotone operator as an Aumann integral and assuming that the sum of the two mean operators is maximal (sufficient maximality conditions are provided), it is shown that with probability one, the interpolated process obtained from the iterates is an asymptotic pseudotrajectory in the sense of Benaïm and Hirsch of the differential inclusion involving the sum of the mean operators. The convergence of the empirical means of the iterates toward a zero of the sum of the mean operators is shown, as well as the convergence of the sequence itself to such a zero under a demipositivity assumption. These results find applications in a wide range of optimization problems or variational inequalities in random environments.

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

Access this article

Log in via an institution

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

Instant access to the full article PDF.

Institutional subscriptions

Similar content being viewed by others

Notes

  1. The result is stated in [8] when v is a so-called weak APT. It turns out that any almost sure APT is a weak APT by Lévy’s conditional form of Borel–Cantelli’s lemma.

  2. By [14, 23], the mapping \(A{:}\,\varXi \rightarrow {{\mathcal {M}}}\), defined as \(A(\xi ,\cdot ) = \partial g(\xi , \cdot )\), is measurable in the sense of Sect. 2.3.

References

  1. Mercier, B.: Lectures on topics in finite element solution of elliptic problems, Tata Institute of Fundamental Research Lectures on Mathematics and Physics, vol. 63. Tata Institute of Fundamental Research, Bombay (1979). With notes by G. Vijayasundaram

  2. Lions, P.L., Mercier, B.: Splitting algorithms for the sum of two nonlinear operators. SIAM J. Numer. Anal. 16(6), 964–979 (1979)

    Article  MathSciNet  MATH  Google Scholar 

  3. Benaïm, M., Hirsch, M.W.: Asymptotic pseudotrajectories and chain recurrent flows, with applications. J. Dyn. Differ. Equ. 8(1), 141–176 (1996)

    Article  MathSciNet  MATH  Google Scholar 

  4. Benaïm, M., Hofbauer, J., Sorin, S.: Stochastic approximations and differential inclusions. SIAM J. Control Optim. 44(1), 328–348 (2005). (electronic)

    Article  MathSciNet  MATH  Google Scholar 

  5. Aumann, R.J.: Integrals of set-valued functions. J. Math. Anal. Appl. 12, 1–12 (1965)

    Article  MathSciNet  MATH  Google Scholar 

  6. Aubin, J.P., Frankowska, H.: Set-Valued Analysis. Modern Birkhäuser Classics. Birkhäuser Boston Inc, Boston (2009). (Reprint of the 1990 edition)

    Book  Google Scholar 

  7. Bianchi, P.: Ergodic Convergence of a stochastic proximal point algorithm. arXiv:1504.05400 (2015)

  8. Benaïm, M., Schreiber, S.J.: Ergodic properties of weak asymptotic pseudotrajectories for semiflows. J. Dyn. Differ. Equ. 12(3), 579–598 (2000)

    Article  MathSciNet  MATH  Google Scholar 

  9. Bruck Jr., R.E.: Asymptotic convergence of nonlinear contraction semigroups in Hilbert space. J. Funct. Anal. 18, 15–26 (1975)

    Article  MathSciNet  MATH  Google Scholar 

  10. Brézis, H.: Opérateurs maximaux monotones et semi-groupes de contractions dans les espaces de Hilbert. North-Holland mathematics studies. Elsevier Science, Burlington (1973)

    MATH  Google Scholar 

  11. Bauschke, H.H., Combettes, P.L.: Convex Analysis and Monotone Operator Theory in Hilbert Spaces. CMS Books in Mathematics/Ouvrages de Mathématiques de la SMC. Springer, New York (2011)

    Google Scholar 

  12. Castaing, C., Valadier, M.: Convex Analysis and Measurable Multifunctions, vol. 580. Springer, Berlin (1977)

    MATH  Google Scholar 

  13. Hiai, F., Umegaki, H.: Integrals, conditional expectations, and martingales of multivalued functions. J. Multivar. Anal. 7(1), 149–182 (1977)

    Article  MathSciNet  MATH  Google Scholar 

  14. Attouch, H.: Familles d’opérateurs maximaux monotones et mesurabilité. Annali di Matematica Pura ed Appl. 120(1), 35–111 (1979). doi:10.1007/BF02411939

    Article  MathSciNet  MATH  Google Scholar 

  15. Hiriart-Urruty, J.B.: Contributions à la programmation mathématique: cas déterministe et stochastique. Université de Clermont-Ferrand II, Clermont-Ferrand (1977). Thèse présentée à l’Université de Clermont-Ferrand II pour obtenir le grade de Docteur ès Sciences Mathématiques. Série E, No. 247

  16. Aubin, J.P., Cellina, A.: Differential Inclusions, Grundlehren der Mathematischen Wissenschaften [Fundamental Principles of Mathematical Sciences], vol. 264. Springer, Berlin (1984). (Set-valued maps and viability theory)

    Google Scholar 

  17. Benaïm, M.: Dynamics of stochastic approximation algorithms. In: Séminaire de Probabilités, XXXIII, Lecture Notes in Math., vol. 1709, pp. 1–68. Springer, Berlin (1999)

  18. Delyon, B.: Stochastic Approximation with Decreasing Gain: Convergence and Asymptotic Theory. Unpublished Lecture Notes, http://perso.univ-rennes1.fr/bernard.delyon/as_cours.ps (2000)

  19. Bauschke, H.H., Borwein, J.M., Li, W.: Strong conical hull intersection property, bounded linear regularity, jamesons property (g), and error bounds in convex optimization. Math. Program. 86(1), 135–160 (1999)

    Article  MathSciNet  MATH  Google Scholar 

  20. Peypouquet, J., Sorin, S.: Evolution equations for maximal monotone operators: asymptotic analysis in continuous and discrete time. J. Convex Anal. 17(3–4), 1113–1163 (2010)

    MathSciNet  MATH  Google Scholar 

  21. Pazy, A.: On the asymptotic behavior of semigroups of nonlinear contractions in Hilbert space. J. Funct. Anal. 27(3), 292–307 (1978)

    Article  MathSciNet  MATH  Google Scholar 

  22. Rockafellar, R.T.: Measurable dependence of convex sets and functions on parameters. J. Math. Anal. Appl. 28, 4–25 (1969)

    Article  MathSciNet  MATH  Google Scholar 

  23. Rockafellar, R.T., Wets, R.J.B.: Variational Analysis, Grundlehren der Mathematischen Wissenschaften [Fundamental Principles of Mathematical Sciences], vol. 317. Springer, Berlin (1998)

    Google Scholar 

  24. Walkup, D.W., Wets, R.J.B.: Stochastic programs with recourse. II: on the continuity of the objective. SIAM J. Appl. Math. 17, 98–103 (1969)

    Article  MathSciNet  MATH  Google Scholar 

  25. Kushner, H.J., Yin, G.G.: Stochastic Approximation and Recursive Algorithms and Applications, Applications of Mathematics (New York), vol. 35, 2nd edn. Springer, New York (2003). (Stochastic Modelling and Applied Probability)

    MATH  Google Scholar 

  26. Nedić, A.: Random algorithms for convex minimization problems. Math. Program. 129(2, Ser. B), 225–253 (2011)

    Article  MathSciNet  MATH  Google Scholar 

  27. Lee, S., Nedic, A.: Distributed random projection algorithm for convex optimization. IEEE J. Sel. Top. Signal Process. 7(2), 221–229 (2013). doi:10.1109/JSTSP.2013.2247023

    Article  Google Scholar 

  28. Bertsekas, D.P.: Incremental proximal methods for large scale convex optimization. Math. Program. 129(2, Ser. B), 163–195 (2011)

    Article  MathSciNet  MATH  Google Scholar 

  29. Wang, M., Bertsekas, D.P.: Incremental constraint projection-proximal methods for nonsmooth convex optimization. Tech. rep, Massachusetts Institute of Technology (2013)

  30. Wang, M., Bertsekas, D.P.: Incremental constraint projection methods for variational inequalities. Math. Program. 150(2, Ser. A), 321–363 (2015)

    Article  MathSciNet  MATH  Google Scholar 

  31. Kinderlehrer, D., Stampacchia, G.: An introduction to variational inequalities and their applications, Classics in Applied Mathematics, vol. 31. Society for Industrial and Applied Mathematics (SIAM), Philadelphia, PA (2000). (Reprint of the 1980 original)

  32. Passty, G.B.: Ergodic convergence to a zero of the sum of monotone operators in Hilbert space. J. Math. Anal. Appl. 72(2), 383–390 (1979)

    Article  MathSciNet  MATH  Google Scholar 

  33. Combettes, P., Pesquet, J.C.: Stochastic Approximations and Perturbations in Forward–backward Splitting for Monotone Operators. Pure and Applied Functional Analysis (2016). To appear

  34. Atchade, Y.F., Fort, G., Moulines, E.: On perturbed proximal gradient algorithms. arXiv:1402.2365 (2014)

  35. Rosasco, L., Villa, S., Vũ, B.C.: Convergence of stochastic proximal gradient algorithm. arXiv preprint arXiv:1403.5074 (2014)

  36. Rosasco, L., Villa, S., Vũ, B.C.: A stochastic inertial forward–backward splitting algorithm for multivariate monotone inclusions. arXiv preprint arXiv:1507.00848 (2015)

  37. Toulis, P., Tran, D., Airoldi, E.M.: Towards stability and optimality in stochastic gradient descent. arXiv:1505.02417 (2015)

  38. Alvarez, F., Peypouquet, J.: Asymptotic equivalence and Kobayashi-type estimates for nonautonomous monotone operators in Banach spaces. Discrete Contin. Dyn. Syst. 25(4), 1109–1128 (2009)

    Article  MathSciNet  MATH  Google Scholar 

  39. Alvarez, F., Peypouquet, J.: Asymptotic almost-equivalence of Lipschitz evolution systems in Banach spaces. Nonlinear Anal. Theory Methods Appl. 73(9), 3018–3033 (2010)

    Article  MathSciNet  MATH  Google Scholar 

  40. Álvarez, F., Peypouquet, J.: A unified approach to the asymptotic almost-equivalence of evolution systems without Lipschitz conditions. Nonlinear Anal. 74(11), 3440–3444 (2011)

    Article  MathSciNet  MATH  Google Scholar 

  41. Robbins, H., Siegmund, D.: A convergence theorem for non negative almost supermartingales and some applications. In: Optimizing Methods in Statistics, pp. 233–257. Academic Press, New York (1971)

  42. Baillon, J.B., Brézis, H.: Une remarque sur le comportement asymptotique des semigroupes non linéaires. Houston J. Math. 2(1), 5–7 (1976)

    MathSciNet  MATH  Google Scholar 

  43. Rockafellar, R.T., Wets, R.J.B.: On the interchange of subdifferentiation and conditional expectations for convex functionals. Stochastics 7(3), 173–182 (1982)

    Article  MathSciNet  MATH  Google Scholar 

Download references

Acknowledgments

This work was partially funded by phi-TAB, the Orange–Telecom ParisTech think tank, and by the ASTRID program of the French Agence Nationale de la Recherche (ODISSEE Project ANR-13-ASTR-0030).

Author information

Authors and Affiliations

  1. LTCI, CNRS, Télécom ParisTech, Université Paris-Saclay, 75013, Paris, France

    Pascal Bianchi & Walid Hachem

Authors
  1. Pascal Bianchi
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Walid Hachem
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Walid Hachem.

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Bianchi, P., Hachem, W. Dynamical Behavior of a Stochastic Forward–Backward Algorithm Using Random Monotone Operators. J Optim Theory Appl 171, 90–120 (2016). https://doi.org/10.1007/s10957-016-0978-y

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s10957-016-0978-y

Keywords

Mathematics Subject Classification

Search

Navigation