IDEAS home Printed from https://ideas.repec.org/a/spr/joptap/v195y2022i3d10.1007_s10957-022-02122-y.html
   My bibliography  Save this article

SABRINA: A Stochastic Subspace Majorization-Minimization Algorithm

Author

Listed:
  • Emilie Chouzenoux

    (Université Paris-Saclay)

  • Jean-Baptiste Fest

    (Université Paris-Saclay)

Abstract

A wide class of problems involves the minimization of a coercive and differentiable function F on $${\mathbb {R}}^N$$ R N whose gradient cannot be evaluated in an exact manner. In such context, many existing convergence results from standard gradient-based optimization literature cannot be directly applied and robustness to errors in the gradient is not necessarily guaranteed. This work is dedicated to investigating the convergence of Majorization-Minimization (MM) schemes when stochastic errors affect the gradient terms. We introduce a general stochastic optimization framework, called StochAstic suBspace majoRIzation-miNimization Algorithm SABRINA that encompasses MM quadratic schemes possibly enhanced with a subspace acceleration strategy. New asymptotical results are built for the stochastic process generated by SABRINA. Two sets of numerical experiments in the field of machine learning and image processing are presented to support our theoretical results and illustrate the good performance of SABRINA with respect to state-of-the-art gradient-based stochastic optimization methods.

Suggested Citation

  • 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.
    • Handle: RePEc:spr:joptap:v:195:y:2022:i:3:d:10.1007_s10957-022-02122-y
    DOI: 10.1007/s10957-022-02122-y
    as

    Download full text from publisher

    File URL: http://link.springer.com/10.1007/s10957-022-02122-y
    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/s10957-022-02122-y?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. Nicolas Loizou & Peter Richtárik, 2020. "Momentum and stochastic momentum for stochastic gradient, Newton, proximal point and subspace descent methods," Computational Optimization and Applications, Springer, vol. 77(3), pages 653-710, December.
    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. Gadat, Sébastien & Gavra, Ioana, 2021. "Asymptotic study of stochastic adaptive algorithm in non-convex landscape," TSE Working Papers 21-1175, Toulouse School of Economics (TSE).
    4. Jérôme Bolte & Edouard Pauwels, 2016. "Majorization-Minimization Procedures and Convergence of SQP Methods for Semi-Algebraic and Tame Programs," Mathematics of Operations Research, INFORMS, vol. 41(2), pages 442-465, 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. Peter Ochs, 2018. "Local Convergence of the Heavy-Ball Method and iPiano for Non-convex Optimization," Journal of Optimization Theory and Applications, Springer, vol. 177(1), pages 153-180, April.
    2. 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).
    3. Marc C. Robini & Lihui Wang & Yuemin Zhu, 2024. "The appeals of quadratic majorization–minimization," Journal of Global Optimization, Springer, vol. 89(3), pages 509-558, July.
    4. Shuqin Sun & Ting Kei Pong, 2023. "Doubly iteratively reweighted algorithm for constrained compressed sensing models," Computational Optimization and Applications, Springer, vol. 85(2), pages 583-619, June.
    5. 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.
    6. 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).
    7. 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).
    8. Zhuoxuan Jiang & Xinyuan Zhao & Chao Ding, 2021. "A proximal DC approach for quadratic assignment problem," Computational Optimization and Applications, Springer, vol. 78(3), pages 825-851, April.
    9. Francisco Facchinei & Vyacheslav Kungurtsev & Lorenzo Lampariello & Gesualdo Scutari, 2021. "Ghost Penalties in Nonconvex Constrained Optimization: Diminishing Stepsizes and Iteration Complexity," Mathematics of Operations Research, INFORMS, vol. 46(2), pages 595-627, May.
    10. Bolte, Jérôme & Pauwels, Edouard, 2021. "A mathematical model for automatic differentiation in machine learning," TSE Working Papers 21-1184, Toulouse School of Economics (TSE).
    11. Jérôme Bolte & Shoham Sabach & Marc Teboulle, 2018. "Nonconvex Lagrangian-Based Optimization: Monitoring Schemes and Global Convergence," Mathematics of Operations Research, INFORMS, vol. 43(4), pages 1210-1232, November.
    12. 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.

    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:195:y:2022:i:3:d:10.1007_s10957-022-02122-y. 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.