IDEAS home Printed from https://ideas.repec.org/a/eee/chsofr/v189y2024ip1s0960077924012062.html
   My bibliography  Save this article

New aspects of black box conditional gradient: Variance reduction and one point feedback

Author

Listed:
  • Veprikov, Andrey
  • Bogdanov, Alexander
  • Minashkin, Vladislav
  • Beznosikov, Aleksandr

Abstract

This paper deals with the black-box optimization problem. In this setup, we do not have access to the gradient of the objective function, therefore, we need to estimate it somehow. We propose a new type of approximation JAGUAR, that memorizes information from previous iterations and requires O(1) oracle calls. We implement this approximation in the Frank–Wolfe and Gradient Descent algorithms and prove the convergence of these methods with different types of zero-order oracle. Our theoretical analysis covers scenarios of non-convex, convex and PL-condition cases. Also in this paper, we consider the stochastic minimization problem on the set Q with noise in the zero-order oracle; this setup is quite unpopular in the literature, but we prove that the JAGUAR approximation is robust not only in deterministic minimization problems, but also in the stochastic case. We perform experiments to compare our gradient estimator with those already known in the literature and confirm the dominance of our methods.

Suggested Citation

  • Veprikov, Andrey & Bogdanov, Alexander & Minashkin, Vladislav & Beznosikov, Aleksandr, 2024. "New aspects of black box conditional gradient: Variance reduction and one point feedback," Chaos, Solitons & Fractals, Elsevier, vol. 189(P1).
    • Handle: RePEc:eee:chsofr:v:189:y:2024:i:p1:s0960077924012062
    DOI: 10.1016/j.chaos.2024.115654
    as

    Download full text from publisher

    File URL: http://www.sciencedirect.com/science/article/pii/S0960077924012062
    Download Restriction: Full text for ScienceDirect subscribers only
    File URL: https://libkey.io/10.1016/j.chaos.2024.115654?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. Yurii NESTEROV & Sebastian U. STICH, 2017. "Efficiency of the accelerated coordinate descent method on structured optimization problems," LIDAM Reprints CORE 2845, Université catholique de Louvain, Center for Operations Research and Econometrics (CORE).
    2. Aleksandr Lobanov & Andrew Veprikov & Georgiy Konin & Aleksandr Beznosikov & Alexander Gasnikov & Dmitry Kovalev, 2023. "Non-smooth setting of stochastic decentralized convex optimization problem over time-varying Graphs," Computational Management Science, Springer, vol. 20(1), pages 1-55, December.
    3. Marguerite Frank & Philip Wolfe, 1956. "An algorithm for quadratic programming," Naval Research Logistics Quarterly, John Wiley & Sons, vol. 3(1‐2), pages 95-110, March.
    4. NESTEROV, Yurii, 2012. "Efficiency of coordinate descent methods on huge-scale optimization problems," LIDAM Reprints CORE 2511, Université catholique de Louvain, Center for Operations Research and Econometrics (CORE).
    5. Dvurechensky, Pavel & Gorbunov, Eduard & Gasnikov, Alexander, 2021. "An accelerated directional derivative method for smooth stochastic convex optimization," European Journal of Operational Research, Elsevier, vol. 290(2), pages 601-621.
    6. Larry J. LeBlanc & Richard V. Helgason & David E. Boyce, 1985. "Improved Efficiency of the Frank-Wolfe Algorithm for Convex Network Programs," Transportation Science, INFORMS, vol. 19(4), pages 445-462, November.
    7. Statkevich, Ekaterina & Bondar, Sofiya & Dvinskikh, Darina & Gasnikov, Alexander & Lobanov, Aleksandr, 2024. "Gradient-free algorithm for saddle point problems under overparametrization," Chaos, Solitons & Fractals, Elsevier, vol. 185(C).
    8. Yurii NESTEROV & Vladimir SPOKOINY, 2017. "Random gradient-free minimization of convex functions," LIDAM Reprints CORE 2851, Université catholique de Louvain, Center for Operations Research and Econometrics (CORE).
    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. Anastasiya Ivanova & Pavel Dvurechensky & Evgeniya Vorontsova & Dmitry Pasechnyuk & Alexander Gasnikov & Darina Dvinskikh & Alexander Tyurin, 2022. "Oracle Complexity Separation in Convex Optimization," Journal of Optimization Theory and Applications, Springer, vol. 193(1), pages 462-490, June.
    2. Flavia Chorobura & Ion Necoara, 2024. "Coordinate descent methods beyond smoothness and separability," Computational Optimization and Applications, Springer, vol. 88(1), pages 107-149, May.
    3. Dvurechensky, Pavel & Gorbunov, Eduard & Gasnikov, Alexander, 2021. "An accelerated directional derivative method for smooth stochastic convex optimization," European Journal of Operational Research, Elsevier, vol. 290(2), pages 601-621.
    4. Meruza Kubentayeva & Demyan Yarmoshik & Mikhail Persiianov & Alexey Kroshnin & Ekaterina Kotliarova & Nazarii Tupitsa & Dmitry Pasechnyuk & Alexander Gasnikov & Vladimir Shvetsov & Leonid Baryshev & A, 2024. "Primal-dual gradient methods for searching network equilibria in combined models with nested choice structure and capacity constraints," Computational Management Science, Springer, vol. 21(1), pages 1-33, June.
    5. David Kozak & Stephen Becker & Alireza Doostan & Luis Tenorio, 2021. "A stochastic subspace approach to gradient-free optimization in high dimensions," Computational Optimization and Applications, Springer, vol. 79(2), pages 339-368, June.
    6. A. Karakitsiou & A. Migdalas, 2016. "Convex optimization problems in supply chain planning and their solution by a column generation method based on the Frank Wolfe method," Operational Research, Springer, vol. 16(3), pages 401-421, October.
    7. Meruza Kubentayeva & Alexander Gasnikov, 2021. "Finding Equilibria in the Traffic Assignment Problem with Primal-Dual Gradient Methods for Stable Dynamics Model and Beckmann Model," Mathematics, MDPI, vol. 9(11), pages 1-17, May.
    8. Sarah Perrin & Thierry Roncalli, 2019. "Machine Learning Optimization Algorithms & Portfolio Allocation," Papers 1909.10233, arXiv.org.
    9. Chi Xie & Xing Wu & Stephen Boyles, 2019. "Traffic equilibrium with a continuously distributed bound on travel weights: the rise of range anxiety and mental account," Annals of Operations Research, Springer, vol. 273(1), pages 279-310, February.
    10. Valentina Morandi, 2024. "Bridging the user equilibrium and the system optimum in static traffic assignment: a review," 4OR, Springer, vol. 22(1), pages 89-119, March.
    11. Guillaume Sagnol & Edouard Pauwels, 2019. "An unexpected connection between Bayes A-optimal designs and the group lasso," Statistical Papers, Springer, vol. 60(2), pages 565-584, April.
    12. Abdelfettah Laouzai & Rachid Ouafi, 2022. "A prediction model for atmospheric pollution reduction from urban traffic," Environment and Planning B, , vol. 49(2), pages 566-584, February.
    13. Ghadimi, Saeed & Powell, Warren B., 2024. "Stochastic search for a parametric cost function approximation: Energy storage with rolling forecasts," European Journal of Operational Research, Elsevier, vol. 312(2), pages 641-652.
    14. Chou, Chang-Chi & Chiang, Wen-Chu & Chen, Albert Y., 2022. "Emergency medical response in mass casualty incidents considering the traffic congestions in proximity on-site and hospital delays," Transportation Research Part E: Logistics and Transportation Review, Elsevier, vol. 158(C).
    15. Francesco Rinaldi & Damiano Zeffiro, 2023. "Avoiding bad steps in Frank-Wolfe variants," Computational Optimization and Applications, Springer, vol. 84(1), pages 225-264, January.
    16. Beck, Yasmine & Ljubić, Ivana & Schmidt, Martin, 2023. "A survey on bilevel optimization under uncertainty," European Journal of Operational Research, Elsevier, vol. 311(2), pages 401-426.
    17. Tiến-Sơn Phạm, 2019. "Optimality Conditions for Minimizers at Infinity in Polynomial Programming," Management Science, INFORMS, vol. 44(4), pages 1381-1395, November.
    18. Filippozzi, Rafaela & Gonçalves, Douglas S. & Santos, Luiz-Rafael, 2023. "First-order methods for the convex hull membership problem," European Journal of Operational Research, Elsevier, vol. 306(1), pages 17-33.
    19. Xuefei Lu & Alessandro Rudi & Emanuele Borgonovo & Lorenzo Rosasco, 2020. "Faster Kriging: Facing High-Dimensional Simulators," Operations Research, INFORMS, vol. 68(1), pages 233-249, January.
    20. Abulimiti Wubuli & Fangfang Li & Shanwei Cao & Lingling Zhang, 2025. "Timing of Preventive Highway Maintenance: A Study from the Whole Life Cycle Perspective," Sustainability, MDPI, vol. 17(3), pages 1-21, 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:eee:chsofr:v:189:y:2024:i:p1:s0960077924012062. 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: Thayer, Thomas R. (email available below). General contact details of provider: https://www.journals.elsevier.com/chaos-solitons-and-fractals .

    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.