IDEAS home Printed from https://ideas.repec.org/a/spr/joptap/v198y2023i1d10.1007_s10957-023-02228-x.html
   My bibliography  Save this article

Convergence of Inertial Dynamics Driven by Sums of Potential and Nonpotential Operators with Implicit Newton-Like Damping

Author

Listed:
  • Samir Adly

    (Université de Limoges)

  • Hedy Attouch

    (Université Montpellier)

  • Van Nam Vo

    (Université de Limoges)

Abstract

We analyze the convergence properties when the time t tends to infinity of the trajectories generated by damped inertial dynamics which are driven by the sum of potential and nonpotential operators. Precisely, we seek to reach asymptotically the zeros of a maximally monotone operator which is the sum of a potential operator (the gradient of a continuously differentiable convex function) and of a monotone and cocoercive nonpotential operator. As an original feature, in addition to the viscous friction, the dynamic involves implicit Newton-type damping. This contrasts with the authors’ previous study where explicit Newton-type damping was considered, which, for the potential term corresponds to Hessian-driven damping. We show the weak convergence, as time tends to infinity, of the generated trajectories toward the zeros of the sum of the potential and nonpotential operators. Our results are based on Lyapunov analysis and appropriate setting of the damping parameters. The introduction of geometric dampings allows to control and attenuate the oscillations known for the viscous damping of inertial methods. Rewriting the second-order evolution equation as a system involving only first-order derivative in time and space allows us to extend the convergence analysis to nonsmooth convex potentials. The main part of our study concerns the autonomous case with positive fixed parameters. We complete it with some first results concerning the nonautonomous case, and which are based on a recent acceleration method using time scaling and averaging. These results open the door to the design of new first-order accelerated algorithms in optimization taking into account the specific properties of potential and nonpotential terms. The proofs and techniques are original due to the presence of the nonpotential term.

Suggested Citation

  • Samir Adly & Hedy Attouch & Van Nam Vo, 2023. "Convergence of Inertial Dynamics Driven by Sums of Potential and Nonpotential Operators with Implicit Newton-Like Damping," Journal of Optimization Theory and Applications, Springer, vol. 198(1), pages 290-331, July.
  • Handle: RePEc:spr:joptap:v:198:y:2023:i:1:d:10.1007_s10957-023-02228-x
    DOI: 10.1007/s10957-023-02228-x
    as

    Download full text from publisher

    File URL: http://link.springer.com/10.1007/s10957-023-02228-x
    File Function: Abstract
    Download Restriction: Access to the full text of the articles in this series is restricted.

    File URL: https://libkey.io/10.1007/s10957-023-02228-x?utm_source=ideas
    LibKey link: if access is restricted and if your library uses this service, LibKey will redirect you to where you can use your library subscription to access this item
    ---><---

    As the access to this document is restricted, you may want to search for a different version of it.

    References listed on IDEAS

    as
    1. Hedy Attouch & Zaki Chbani & Jalal Fadili & Hassan Riahi, 2022. "Fast Convergence of Dynamical ADMM via Time Scaling of Damped Inertial Dynamics," Journal of Optimization Theory and Applications, Springer, vol. 193(1), pages 704-736, June.
    2. Bolte, Jérôme & Castera, Camille & Pauwels, Edouard & Févotte, Cédric, 2019. "An Inertial Newton Algorithm for Deep Learning," TSE Working Papers 19-1043, Toulouse School of Economics (TSE).
    3. H. Attouch & P. Redont & B. F. Svaiter, 2013. "Global Convergence of a Closed-Loop Regularized Newton Method for Solving Monotone Inclusions in Hilbert Spaces," Journal of Optimization Theory and Applications, Springer, vol. 157(3), pages 624-650, June.
    4. B. Abbas & H. Attouch & Benar F. Svaiter, 2014. "Newton-Like Dynamics and Forward-Backward Methods for Structured Monotone Inclusions in Hilbert Spaces," Journal of Optimization Theory and Applications, Springer, vol. 161(2), pages 331-360, May.
    Full references (including those not matched with items on IDEAS)

    Most related items

    These are the items that most often cite the same works as this one and are cited by the same works as this one.
    1. Bolte, Jérôme & Le, Tam & Pauwels, Edouard & Silveti-Falls, Antonio, 2022. "Nonsmooth Implicit Differentiation for Machine Learning and Optimization," TSE Working Papers 22-1314, Toulouse School of Economics (TSE).
    2. Boţ, R.I. & Csetnek, E.R. & Vuong, P.T., 2020. "The forward–backward–forward method from continuous and discrete perspective for pseudo-monotone variational inequalities in Hilbert spaces," European Journal of Operational Research, Elsevier, vol. 287(1), pages 49-60.
    3. B. Abbas & H. Attouch & Benar F. Svaiter, 2014. "Newton-Like Dynamics and Forward-Backward Methods for Structured Monotone Inclusions in Hilbert Spaces," Journal of Optimization Theory and Applications, Springer, vol. 161(2), pages 331-360, May.
    4. Boţ, Radu Ioan & Kanzler, Laura, 2021. "A forward-backward dynamical approach for nonsmooth problems with block structure coupled by a smooth function," Applied Mathematics and Computation, Elsevier, vol. 394(C).
    5. Emilie Chouzenoux & Jean-Baptiste Fest, 2022. "SABRINA: A Stochastic Subspace Majorization-Minimization Algorithm," Journal of Optimization Theory and Applications, Springer, vol. 195(3), pages 919-952, December.
    6. Pankaj Gautam & Daya Ram Sahu & Avinash Dixit & Tanmoy Som, 2021. "Forward–Backward–Half Forward Dynamical Systems for Monotone Inclusion Problems with Application to v-GNE," Journal of Optimization Theory and Applications, Springer, vol. 190(2), pages 491-523, August.
    7. Bolte, Jérôme & Pauwels, Edouard, 2019. "Conservative set valued fields, automatic differentiation, stochastic gradient methods and deep learning," TSE Working Papers 19-1044, Toulouse School of Economics (TSE).
    8. Bolte, Jérôme & Glaudin, Lilian & Pauwels, Edouard & Serrurier, Matthieu, 2021. "A Hölderian backtracking method for min-max and min-min problems," TSE Working Papers 21-1243, Toulouse School of Economics (TSE).
    9. Bolte, Jérôme & Pauwels, Edouard, 2021. "A mathematical model for automatic differentiation in machine learning," TSE Working Papers 21-1184, Toulouse School of Economics (TSE).
    10. Claire Boyer & Antoine Godichon-Baggioni, 2023. "On the asymptotic rate of convergence of Stochastic Newton algorithms and their Weighted Averaged versions," Computational Optimization and Applications, Springer, vol. 84(3), pages 921-972, April.
    11. Rieger, Janosch & Tam, Matthew K., 2020. "Backward-Forward-Reflected-Backward Splitting for Three Operator Monotone Inclusions," Applied Mathematics and Computation, Elsevier, vol. 381(C).

    Corrections

    All material on this site has been provided by the respective publishers and authors. You can help correct errors and omissions. When requesting a correction, please mention this item's handle: RePEc:spr:joptap:v:198:y:2023:i:1:d:10.1007_s10957-023-02228-x. See general information about how to correct material in RePEc.

    If you have authored this item and are not yet registered with RePEc, we encourage you to do it here. This allows to link your profile to this item. It also allows you to accept potential citations to this item that we are uncertain about.

    If CitEc recognized a bibliographic reference but did not link an item in RePEc to it, you can help with this form .

    If you know of missing items citing this one, you can help us creating those links by adding the relevant references in the same way as above, for each refering item. If you are a registered author of this item, you may also want to check the "citations" tab in your RePEc Author Service profile, as there may be some citations waiting for confirmation.

    For technical questions regarding this item, or to correct its authors, title, abstract, bibliographic or download information, contact: Sonal Shukla or Springer Nature Abstracting and Indexing (email available below). General contact details of provider: http://www.springer.com .

    Please note that corrections may take a couple of weeks to filter through the various RePEc services.

    IDEAS is a RePEc service. RePEc uses bibliographic data supplied by the respective publishers.