IDEAS home Printed from https://ideas.repec.org/a/spr/joptap/v195y2022i1d10.1007_s10957-022-02061-8.html
   My bibliography  Save this article

Dualize, Split, Randomize: Toward Fast Nonsmooth Optimization Algorithms

Author

Listed:
  • Adil Salim

    (King Abdullah University of Science and Technology (KAUST))

  • Laurent Condat

    (King Abdullah University of Science and Technology (KAUST))

  • Konstantin Mishchenko

    (King Abdullah University of Science and Technology (KAUST))

  • Peter Richtárik

    (King Abdullah University of Science and Technology (KAUST))

Abstract

We consider minimizing the sum of three convex functions, where the first one F is smooth, the second one is nonsmooth and proximable and the third one is the composition of a nonsmooth proximable function with a linear operator L. This template problem has many applications, for instance, in image processing and machine learning. First, we propose a new primal–dual algorithm, which we call PDDY, for this problem. It is constructed by applying Davis–Yin splitting to a monotone inclusion in a primal–dual product space, where the operators are monotone under a specific metric depending on L. We show that three existing algorithms (the two forms of the Condat–Vũ algorithm and the PD3O algorithm) have the same structure, so that PDDY is the fourth missing link in this self-consistent class of primal–dual algorithms. This representation eases the convergence analysis: it allows us to derive sublinear convergence rates in general, and linear convergence results in presence of strong convexity. Moreover, within our broad and flexible analysis framework, we propose new stochastic generalizations of the algorithms, in which a variance-reduced random estimate of the gradient of F is used, instead of the true gradient. Furthermore, we obtain, as a special case of PDDY, a linearly converging algorithm for the minimization of a strongly convex function F under a linear constraint; we discuss its important application to decentralized optimization.

Suggested Citation

  • Adil Salim & Laurent Condat & Konstantin Mishchenko & Peter Richtárik, 2022. "Dualize, Split, Randomize: Toward Fast Nonsmooth Optimization Algorithms," Journal of Optimization Theory and Applications, Springer, vol. 195(1), pages 102-130, October.
  • Handle: RePEc:spr:joptap:v:195:y:2022:i:1:d:10.1007_s10957-022-02061-8
    DOI: 10.1007/s10957-022-02061-8
    as

    Download full text from publisher

    File URL: http://link.springer.com/10.1007/s10957-022-02061-8
    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/s10957-022-02061-8?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. Laurent Condat, 2013. "A Primal–Dual Splitting Method for Convex Optimization Involving Lipschitzian, Proximable and Linear Composite Terms," Journal of Optimization Theory and Applications, Springer, vol. 158(2), pages 460-479, August.
    2. Patrick R. Johnstone & Jonathan Eckstein, 2021. "Single-forward-step projective splitting: exploiting cocoercivity," Computational Optimization and Applications, Springer, vol. 78(1), pages 125-166, January.
    Full references (including those not matched with items on IDEAS)

    Citations

    Citations are extracted by the CitEc Project, subscribe to its RSS feed for this item.
    as


    Cited by:

    1. Xin Jiang & Lieven Vandenberghe, 2023. "Bregman Three-Operator Splitting Methods," Journal of Optimization Theory and Applications, Springer, vol. 196(3), pages 936-972, March.

    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. Dong, Yunda, 2023. "A new splitting method for systems of monotone inclusions in Hilbert spaces," Mathematics and Computers in Simulation (MATCOM), Elsevier, vol. 203(C), pages 518-537.
    2. Puya Latafat & Panagiotis Patrinos, 2017. "Asymmetric forward–backward–adjoint splitting for solving monotone inclusions involving three operators," Computational Optimization and Applications, Springer, vol. 68(1), pages 57-93, September.
    3. Xin Jiang & Lieven Vandenberghe, 2022. "Bregman primal–dual first-order method and application to sparse semidefinite programming," Computational Optimization and Applications, Springer, vol. 81(1), pages 127-159, January.
    4. Sun, Shilin & Wang, Tianyang & Yang, Hongxing & Chu, Fulei, 2022. "Damage identification of wind turbine blades using an adaptive method for compressive beamforming based on the generalized minimax-concave penalty function," Renewable Energy, Elsevier, vol. 181(C), pages 59-70.
    5. David Degras, 2021. "Sparse group fused lasso for model segmentation: a hybrid approach," Advances in Data Analysis and Classification, Springer;German Classification Society - Gesellschaft für Klassifikation (GfKl);Japanese Classification Society (JCS);Classification and Data Analysis Group of the Italian Statistical Society (CLADAG);International Federation of Classification Societies (IFCS), vol. 15(3), pages 625-671, September.
    6. Xiaoliang Wang & Liping Pang & Qi Wu & Mingkun Zhang, 2021. "An Adaptive Proximal Bundle Method with Inexact Oracles for a Class of Nonconvex and Nonsmooth Composite Optimization," Mathematics, MDPI, vol. 9(8), pages 1-27, April.
    7. Walaa M. Moursi & Lieven Vandenberghe, 2019. "Douglas–Rachford Splitting for the Sum of a Lipschitz Continuous and a Strongly Monotone Operator," Journal of Optimization Theory and Applications, Springer, vol. 183(1), pages 179-198, October.
    8. Luis M. Briceño-Arias & Fernando Roldán, 2022. "Four-Operator Splitting via a Forward–Backward–Half-Forward Algorithm with Line Search," Journal of Optimization Theory and Applications, Springer, vol. 195(1), pages 205-225, October.
    9. Luis Briceño-Arias & Fernando Roldán, 2023. "Primal-dual splittings as fixed point iterations in the range of linear operators," Journal of Global Optimization, Springer, vol. 85(4), pages 847-866, April.
    10. Eisuke Yamagata & Shunsuke Ono, 2023. "Sparse Index Tracking: Simultaneous Asset Selection and Capital Allocation via $\ell_0$-Constrained Portfolio," Papers 2309.10152, arXiv.org, revised Mar 2024.
    11. Ying Gao & Wenxing Zhang, 2023. "An alternative extrapolation scheme of PDHGM for saddle point problem with nonlinear function," Computational Optimization and Applications, Springer, vol. 85(1), pages 263-291, May.
    12. S. Bonettini & M. Prato & S. Rebegoldi, 2023. "A nested primal–dual FISTA-like scheme for composite convex optimization problems," Computational Optimization and Applications, Springer, vol. 84(1), pages 85-123, January.
    13. Wenli Huang & Yuchao Tang & Meng Wen & Haiyang Li, 2022. "Relaxed Variable Metric Primal-Dual Fixed-Point Algorithm with Applications," Mathematics, MDPI, vol. 10(22), pages 1-16, November.
    14. Luis Briceño-Arias & Julio Deride & Cristian Vega, 2022. "Random Activations in Primal-Dual Splittings for Monotone Inclusions with a Priori Information," Journal of Optimization Theory and Applications, Springer, vol. 192(1), pages 56-81, January.
    15. Xin Jiang & Lieven Vandenberghe, 2023. "Bregman Three-Operator Splitting Methods," Journal of Optimization Theory and Applications, Springer, vol. 196(3), pages 936-972, March.
    16. Yunda Dong, 2021. "Weak convergence of an extended splitting method for monotone inclusions," Journal of Global Optimization, Springer, vol. 79(1), pages 257-277, January.
    17. Radu Ioan Bot & Dang-Khoa Nguyen, 2020. "The Proximal Alternating Direction Method of Multipliers in the Nonconvex Setting: Convergence Analysis and Rates," Mathematics of Operations Research, INFORMS, vol. 45(2), pages 682-712, May.
    18. Julian Rasch & Antonin Chambolle, 2020. "Inexact first-order primal–dual algorithms," Computational Optimization and Applications, Springer, vol. 76(2), pages 381-430, June.
    19. Fu, Penghui & Tan, Zhiqiang, 2024. "Block-wise primal-dual algorithms for large-scale doubly penalized ANOVA modeling," Computational Statistics & Data Analysis, Elsevier, vol. 194(C).
    20. Yawei Shi & Liang Ran & Jialong Tang & Xiangzhao Wu, 2022. "Distributed Optimization Algorithm for Composite Optimization Problems with Non-Smooth Function," Mathematics, MDPI, vol. 10(17), pages 1-17, September.

    More about this item

    Statistics

    Access and download statistics

    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:1:d:10.1007_s10957-022-02061-8. 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.