IDEAS home Printed from https://ideas.repec.org/a/spr/comgts/v21y2024i1d10.1007_s10287-023-00489-5.html
   My bibliography  Save this article

Decentralized optimization over slowly time-varying graphs: algorithms and lower bounds

Author

Listed:
  • Dmitry Metelev

    (Moscow Institute of Physics and Technology)

  • Aleksandr Beznosikov

    (Moscow Institute of Physics and Technology
    Skolkovo Institute of Science and Technology
    Mohamed bin Zayed University of Artificial Intelligence)

  • Alexander Rogozin

    (Moscow Institute of Physics and Technology
    Skolkovo Institute of Science and Technology
    HSE University)

  • Alexander Gasnikov

    (Moscow Institute of Physics and Technology
    Skolkovo Institute of Science and Technology
    Institute for Information Transmission Problems)

  • Anton Proskurnikov

    (Politecnico di Torino)

Abstract

We consider a decentralized convex unconstrained optimization problem, where the cost function can be decomposed into a sum of strongly convex and smooth functions, associated with individual agents, interacting over a static or time-varying network. Our main concern is the convergence rate of first-order optimization algorithms as a function of the network’s graph, more specifically, of the condition numbers of gossip matrices. We are interested in the case when the network is time-varying but the rate of changes is restricted. We study two cases: randomly changing network satisfying Markov property and a network changing in a deterministic manner. For the random case, we propose a decentralized optimization algorithm with accelerated consensus. For the deterministic scenario, we show that if the graph is changing in a worst-case way, accelerated consensus is not possible even if only two edges are changed at each iteration. The fact that such a low rate of network changes is sufficient to make accelerated consensus impossible is novel and improves the previous results in the literature.

Suggested Citation

  • Dmitry Metelev & Aleksandr Beznosikov & Alexander Rogozin & Alexander Gasnikov & Anton Proskurnikov, 2024. "Decentralized optimization over slowly time-varying graphs: algorithms and lower bounds," Computational Management Science, Springer, vol. 21(1), pages 1-25, June.
    • Handle: RePEc:spr:comgts:v:21:y:2024:i:1:d:10.1007_s10287-023-00489-5
    DOI: 10.1007/s10287-023-00489-5
    as

    Download full text from publisher

    File URL: http://link.springer.com/10.1007/s10287-023-00489-5
    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/s10287-023-00489-5?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. A. Nedić & A. Ozdaglar, 2009. "Subgradient Methods for Saddle-Point Problems," Journal of Optimization Theory and Applications, Springer, vol. 142(1), pages 205-228, July.
    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. Vinayaka G. Yaji & Shalabh Bhatnagar, 2020. "Stochastic Recursive Inclusions in Two Timescales with Nonadditive Iterate-Dependent Markov Noise," Mathematics of Operations Research, INFORMS, vol. 45(4), pages 1405-1444, November.
    2. Liusheng Hou & Hongjin He & Junfeng Yang, 2016. "A partially parallel splitting method for multiple-block separable convex programming with applications to robust PCA," Computational Optimization and Applications, Springer, vol. 63(1), pages 273-303, January.
    3. Guangming Zhou & Qin Wang & Wenjie Zhao, 2020. "Saddle points of rational functions," Computational Optimization and Applications, Springer, vol. 75(3), pages 817-832, April.
    4. Desmond Cai & Subhonmesh Bose & Adam Wierman, 2019. "On the Role of a Market Maker in Networked Cournot Competition," Mathematics of Operations Research, INFORMS, vol. 44(3), pages 1122-1144, August.
    5. Denizalp Goktas & Amy Greenwald, 2022. "Gradient Descent Ascent in Min-Max Stackelberg Games," Papers 2208.09690, arXiv.org.
    6. Wenjie Zhao & Guangming Zhou, 2022. "Local saddle points for unconstrained polynomial optimization," Computational Optimization and Applications, Springer, vol. 82(1), pages 89-106, May.
    7. Regina S. Burachik & Alfredo N. Iusem & Jefferson G. Melo, 2013. "An Inexact Modified Subgradient Algorithm for Primal-Dual Problems via Augmented Lagrangians," Journal of Optimization Theory and Applications, Springer, vol. 157(1), pages 108-131, April.
    8. Samira Mir Mazhari Anvar & Sohrab Khanmohammadi & Javad Musevi niya, 2016. "Game theoretic power allocation for fading MIMO multiple access channels with imperfect CSIR," Telecommunication Systems: Modelling, Analysis, Design and Management, Springer, vol. 61(4), pages 875-886, April.
    9. Avinash N. Madavan & Subhonmesh Bose, 2021. "A Stochastic Primal-Dual Method for Optimization with Conditional Value at Risk Constraints," Journal of Optimization Theory and Applications, Springer, vol. 190(2), pages 428-460, August.
    10. Guigues, Vincent & Shapiro, Alexander & Cheng, Yi, 2023. "Duality and sensitivity analysis of multistage linear stochastic programs," European Journal of Operational Research, Elsevier, vol. 308(2), pages 752-767.
    11. Andrea Simonetto & Hadi Jamali-Rad, 2016. "Primal Recovery from Consensus-Based Dual Decomposition for Distributed Convex Optimization," Journal of Optimization Theory and Applications, Springer, vol. 168(1), pages 172-197, January.
    12. Bo Wei & William B. Haskell & Sixiang Zhao, 2020. "An inexact primal-dual algorithm for semi-infinite programming," Mathematical Methods of Operations Research, Springer;Gesellschaft für Operations Research (GOR);Nederlands Genootschap voor Besliskunde (NGB), vol. 91(3), pages 501-544, June.
    13. Hu, Mian & Wang, Yan-Wu & Xiao, Jiang-Wen & Lin, Xiangning, 2019. "Multi-energy management with hierarchical distributed multi-scale strategy for pelagic islanded microgrid clusters," Energy, Elsevier, vol. 185(C), pages 910-921.
    14. Yaohua Hu & Jiawen Li & Carisa Kwok Wai Yu, 2020. "Convergence rates of subgradient methods for quasi-convex optimization problems," Computational Optimization and Applications, Springer, vol. 77(1), pages 183-212, September.
    15. A. M. Bagirov & L. Jin & N. Karmitsa & A. Al Nuaimat & N. Sultanova, 2013. "Subgradient Method for Nonconvex Nonsmooth Optimization," Journal of Optimization Theory and Applications, Springer, vol. 157(2), pages 416-435, May.
    16. Giorgio Costa & Roy H. Kwon, 2021. "Data-driven distributionally robust risk parity portfolio optimization," Papers 2110.06464, arXiv.org.
    17. Abdellatif Moudafi, 2024. "About the Subgradient Method for Equilibrium Problems," Mathematics, MDPI, vol. 12(13), pages 1-6, July.
    18. Denizalp Goktas & Jiayi Zhao & Amy Greenwald, 2022. "Robust No-Regret Learning in Min-Max Stackelberg Games," Papers 2203.14126, arXiv.org, revised Apr 2022.
    19. J. Y. Bello Cruz & P. S. M. Santos & S. Scheimberg, 2013. "A Two-Phase Algorithm for a Variational Inequality Formulation of Equilibrium Problems," Journal of Optimization Theory and Applications, Springer, vol. 159(3), pages 562-575, December.
    20. Le Thi Khanh Hien & Renbo Zhao & William B. Haskell, 2024. "An Inexact Primal-Dual Smoothing Framework for Large-Scale Non-Bilinear Saddle Point Problems," Journal of Optimization Theory and Applications, Springer, vol. 200(1), pages 34-67, January.

    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:comgts:v:21:y:2024:i:1:d:10.1007_s10287-023-00489-5. 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.