Advertisement

Testing and Non-linear Preconditioning of the Proximal Point Method

  • Tuomo Valkonen
Article
  • 19 Downloads

Abstract

Employing the ideas of non-linear preconditioning and testing of the classical proximal point method, we formalise common arguments in convergence rate and convergence proofs of optimisation methods to the verification of a simple iteration-wise inequality. When applied to fixed point operators, the latter can be seen as a generalisation of firm non-expansivity or the \(\alpha \)-averaged property. The main purpose of this work is to provide the abstract background theory for our companion paper “Block-proximal methods with spatially adapted acceleration”. In the present account we demonstrate the effectiveness of the general approach on several classical algorithms, as well as their stochastic variants. Besides, of course, the proximal point method, these method include the gradient descent, forward–backward splitting, Douglas–Rachford splitting, Newton’s method, as well as several methods for saddle-point problems, such as the Alternating Directions Method of Multipliers, and the Chambolle–Pock method.

Mathematics Subject Classification

49M29 65K10 65K15 90C30 90C47 

References

  1. 1.
    Martinet, B.: Brève communication. Régularisation d’inéquations variationnelles par approximations successives. ESAIM 4(R3), 154–158 (1970)zbMATHGoogle Scholar
  2. 2.
    Rockafellar, R.T.: Monotone operators and the proximal point algorithm. SIAM J. Optim. 14(5), 877–898 (1976).  https://doi.org/10.1137/0314056 MathSciNetCrossRefzbMATHGoogle Scholar
  3. 3.
    Beck, A., Teboulle, M.: A fast iterative shrinkage-thresholding algorithm for linear inverse problems. SIAM J. Imaging Sci. 2(1), 183–202 (2009).  https://doi.org/10.1137/080716542 MathSciNetCrossRefzbMATHGoogle Scholar
  4. 4.
    Loris, I., Verhoeven, C.: On a generalization of the iterative soft-thresholding algorithm for the case of non-separable penalty. Inverse Probl. 27(12), 125,007 (2011).  https://doi.org/10.1088/0266-5611/27/12/125007 MathSciNetCrossRefzbMATHGoogle Scholar
  5. 5.
    Gabay, D.: Applications of the method of multipliers to variational inequalities. In: M. Fortin, R. Glowinski (eds.) Augmented Lagrangian Methods: Applications to the Numerical Solution of Boundary-Value Problems, vol. 15, pp. 299–331. North-Holland (1983)Google Scholar
  6. 6.
    Chambolle, A., Pock, T.: A first-order primal-dual algorithm for convex problems with applications to imaging. J. Math. Imaging Vis. 40, 120–145 (2011).  https://doi.org/10.1007/s10851-010-0251-1 MathSciNetCrossRefzbMATHGoogle Scholar
  7. 7.
    He, B., Yuan, X.: Convergence analysis of primal-dual algorithms for a saddle-point problem: from contraction perspective. SIAM J. Imaging Sci. 5(1), 119–149 (2012).  https://doi.org/10.1137/100814494 MathSciNetCrossRefzbMATHGoogle Scholar
  8. 8.
    Valkonen, T., Pock, T.: Acceleration of the PDHGM on partially strongly convex functions. J. Math. Imaging Vis. 59, 394–414 (2017).  https://doi.org/10.1007/s10851-016-0692-2 MathSciNetCrossRefzbMATHGoogle Scholar
  9. 9.
    Valkonen, T.: Block-proximal methods with spatially adapted acceleration (2017). http://tuomov.iki.fi/m/blockcp.pdf (Submitted)
  10. 10.
    Browder, F.E.: Nonexpansive nonlinear operators in a banach space. Proc. Natl. Acad. Sci. USA 54(4), 1041 (1965)MathSciNetCrossRefGoogle Scholar
  11. 11.
    Wright, S.: Coordinate descent algorithms. Math. Progr. 151(1), 3–34 (2015).  https://doi.org/10.1007/s10107-015-0892-3 MathSciNetCrossRefzbMATHGoogle Scholar
  12. 12.
    Censor, Y., Zenios, S.A.: Proximal minimization algorithm withd-functions. J. Optim. Theory Appl. 73(3), 451–464 (1992).  https://doi.org/10.1007/BF00940051 MathSciNetCrossRefzbMATHGoogle Scholar
  13. 13.
    Chen, G., Teboulle, M.: Convergence analysis of a proximal-like minimization algorithm using bregman functions. SIAM J. Optim. 3(3), 538–543 (1993).  https://doi.org/10.1137/0803026 MathSciNetCrossRefzbMATHGoogle Scholar
  14. 14.
    Lorenz, D., Pock, T.: An inertial forward-backward algorithm for monotone inclusions. J. Math. Imaging Vis. 51(2), 311–325 (2015).  https://doi.org/10.1007/s10851-014-0523-2 MathSciNetCrossRefzbMATHGoogle Scholar
  15. 15.
    Hohage, T., Homann, C.: A generalization of the Chambolle-Pock algorithm to Banach spaces with applications to inverse problems (2014) (Preprint)Google Scholar
  16. 16.
    Hua, X., Yamashita, N.: Block coordinate proximal gradient methods with variable bregman functions for nonsmooth separable optimization. Math. Program. 160(1), 1–32 (2016).  https://doi.org/10.1007/s10107-015-0969-z MathSciNetCrossRefzbMATHGoogle Scholar
  17. 17.
    Brezis, H., Crandall, M.G., Pazy, A.: Perturbations of nonlinear maximal monotone sets in banach space. Commun. Pure Appl. Math. 23(1), 123–144 (1970).  https://doi.org/10.1002/cpa.3160230107 MathSciNetCrossRefzbMATHGoogle Scholar
  18. 18.
    Opial, Z.: Weak convergence of the sequence of successive approximations for nonexpansive mappings. Bull. Am. Math. Soc. 73(4), 591–597 (1967).  https://doi.org/10.1090/S0002-9904-1967-11761-0 MathSciNetCrossRefzbMATHGoogle Scholar
  19. 19.
    Browder, F.E.: Convergence theorems for sequences of nonlinear operators in banach spaces. Math. Z. 100(3), 201–225 (1967).  https://doi.org/10.1007/BF01109805 MathSciNetCrossRefzbMATHGoogle Scholar
  20. 20.
    Daubechies, I., Defrise, M., De Mol, C.: An iterative thresholding algorithm for linear inverse problems with a sparsity constraint. Commun. Pure Appl. Math. 57(11), 1413–1457 (2004).  https://doi.org/10.1002/cpa.20042 MathSciNetCrossRefzbMATHGoogle Scholar
  21. 21.
    Douglas Jim, J., Rachford, H.H.J.: On the numerical solution of heat conduction problems in two and three space variables. Trans. Am. Math. Soc. 82(2), 421–439 (1956).  https://doi.org/10.2307/1993056 MathSciNetCrossRefzbMATHGoogle Scholar
  22. 22.
    Bauschke, H.H., Combettes, P.L.: Convex Analysis and Monotone Operator Theory in Hilbert Spaces, 2 edn. CMS Books in Mathematics/Ouvrages de Mathématiques de la SMC. Springer, New York (2017).  https://doi.org/10.1007/978-3-319-48311-5 CrossRefGoogle Scholar
  23. 23.
    Lee, J.D., Sun, Y., Saunders, M.A.: Proximal Newton-type methods for minimizing composite functions. SIAM J. Optim. 24(3), 1420–1443 (2014).  https://doi.org/10.1137/130921428 MathSciNetCrossRefzbMATHGoogle Scholar
  24. 24.
    Mann, W.R.: Mean value methods in iteration. Proc. Am. Math. Soc. 4(3), 506–510 (1953)MathSciNetCrossRefGoogle Scholar
  25. 25.
    Schaefer, H.: Über die methode sukzessiver approximationen. Jahresbericht der Deutschen Mathematiker-Vereinigung 59, 131–140 (1957)MathSciNetzbMATHGoogle Scholar
  26. 26.
    Petryshyn, W.: Construction of fixed points of demicompact mappings in Hilbert space. J. Math. Anal. Appl. 14(2), 276–284 (1966)MathSciNetCrossRefGoogle Scholar
  27. 27.
    Krasnoselski, M.A.: Two remarks about the method of successive approximations. Uspekhi Mat. Nauk. 19, 123–127 (1955)Google Scholar
  28. 28.
    Shiriyaev, A.N.: Probability. Graduate Texts in Mathematics. Springer, New York (1996)Google Scholar
  29. 29.
    Qu, Z., Richtárik, P., Takáč, M., Fercoq, O.: SDNA: stochastic dual Newton ascent for empirical risk minimization (2015)Google Scholar
  30. 30.
    Pilanci, M., Wainwright, M.J.: Iterative Hessian sketch: fast and accurate solution approximation for constrained least-squares. J. Mach. Learn. Res. 17(53), 1–38 (2016)MathSciNetzbMATHGoogle Scholar
  31. 31.
    Condat, L.: A primal-dual splitting method for convex optimization involving lipschitzian, proximable and linear composite terms. J. Optim. Theory Appl. 158(2), 460–479 (2013).  https://doi.org/10.1007/s10957-012-0245-9 MathSciNetCrossRefzbMATHGoogle Scholar
  32. 32.
    Vũ, B.C.: A splitting algorithm for dual monotone inclusions involving cocoercive operators. Adv. Comput. Math. 38(3), 667–681 (2013).  https://doi.org/10.1007/s10444-011-9254-8 MathSciNetCrossRefzbMATHGoogle Scholar
  33. 33.
    Chambolle, A., Pock, T.: On the ergodic convergence rates of a first-order primal–dual algorithm. Math. Progr. (2015).  https://doi.org/10.1007/s10107-015-0957-3 MathSciNetCrossRefGoogle Scholar
  34. 34.
    Richtárik, P., Takáč, M.: Parallel coordinate descent methods for big data optimization. Math. Progr. (2015).  https://doi.org/10.1007/s10107-015-0901-6 MathSciNetCrossRefGoogle Scholar

Copyright information

© Springer Science+Business Media, LLC, part of Springer Nature 2018

Authors and Affiliations

  1. 1.ModeMat, Escuela Politécnica NacionalQuitoEcuador
  2. 2.Department of Mathematical SciencesUniversity of LiverpoolLiverpoolUK

Personalised recommendations