IDEAS home Printed from https://ideas.repec.org/a/spr/joptap/v194y2022i1d10.1007_s10957-021-01994-w.html
   My bibliography  Save this article

A Mixed Finite Differences Scheme for Gradient Approximation

Author

Listed:
  • Marco Boresta

    (Sapienza University of Rome)

  • Tommaso Colombo

    (Sapienza University of Rome)

  • Alberto Santis

    (Sapienza University of Rome)

  • Stefano Lucidi

    (Sapienza University of Rome)

Abstract

In this paper, we focus on the linear functionals defining an approximate version of the gradient of a function. These functionals are often used when dealing with optimization problems where the computation of the gradient of the objective function is costly or the objective function values are affected by some noise. These functionals have been recently considered to estimate the gradient of the objective function by the expected value of the function variations in the space of directions. The expected value is then approximated by a sample average over a proper (random) choice of sample directions in the domain of integration. In this way, the approximation error is characterized by statistical properties of the sample average estimate, typically its variance. Therefore, while useful and attractive bounds for the error variance can be expressed in terms of the number of function evaluations, nothing can be said on the error of a single experiment that could be quite large. This work instead is aimed at deriving an approximation scheme for linear functionals approximating the gradient, whose error of approximation can be characterized by a deterministic point of view in the case of noise-free data. The previously mentioned linear functionals are no longer considered as expected values over the space of directions, but rather as the filtered derivative of the objective function by a Gaussian kernel. By using this new approach, a gradient estimation based on a suitable linear combination of central finite differences at different step sizes is proposed and deterministic bounds that do not depend on the particular sample of points considered are computed. In the noisy setting, on the other end, the variance of the estimation error of the proposed method is showed to be strictly lower than the one of the estimation error of the Central Finite Difference scheme. Numerical experiments on a set of test functions are encouraging, showing good performances compared to those of some methods commonly used in the literature, also in the noisy setting.

Suggested Citation

  • Marco Boresta & Tommaso Colombo & Alberto Santis & Stefano Lucidi, 2022. "A Mixed Finite Differences Scheme for Gradient Approximation," Journal of Optimization Theory and Applications, Springer, vol. 194(1), pages 1-24, July.
    • Handle: RePEc:spr:joptap:v:194:y:2022:i:1:d:10.1007_s10957-021-01994-w
    DOI: 10.1007/s10957-021-01994-w
    as

    Download full text from publisher

    File URL: http://link.springer.com/10.1007/s10957-021-01994-w
    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/s10957-021-01994-w?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 & 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. V. Kungurtsev & F. Rinaldi, 2021. "A zeroth order method for stochastic weakly convex optimization," Computational Optimization and Applications, Springer, vol. 80(3), pages 731-753, December.
    2. Jean-Jacques Forneron, 2023. "Noisy, Non-Smooth, Non-Convex Estimation of Moment Condition Models," Papers 2301.07196, arXiv.org, revised Feb 2023.
    3. Stefan Wager & Kuang Xu, 2021. "Experimenting in Equilibrium," Management Science, INFORMS, vol. 67(11), pages 6694-6715, November.
    4. Geovani Nunes Grapiglia, 2023. "Quadratic regularization methods with finite-difference gradient approximations," Computational Optimization and Applications, Springer, vol. 85(3), pages 683-703, July.
    5. 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.
    6. Nikita Kornilov & Alexander Gasnikov & Pavel Dvurechensky & Darina Dvinskikh, 2023. "Gradient-free methods for non-smooth convex stochastic optimization with heavy-tailed noise on convex compact," Computational Management Science, Springer, vol. 20(1), pages 1-43, December.
    7. 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.
    8. Jun Xie & Chi Cao, 2017. "Non-Convex Economic Dispatch of a Virtual Power Plant via a Distributed Randomized Gradient-Free Algorithm," Energies, MDPI, vol. 10(7), pages 1-12, July.
    9. Michael R. Metel & Akiko Takeda, 2022. "Perturbed Iterate SGD for Lipschitz Continuous Loss Functions," Journal of Optimization Theory and Applications, Springer, vol. 195(2), pages 504-547, November.
    10. Katya Scheinberg, 2022. "Finite Difference Gradient Approximation: To Randomize or Not?," INFORMS Journal on Computing, INFORMS, vol. 34(5), pages 2384-2388, September.
    11. Jingxu Xu & Zeyu Zheng, 2023. "Gradient-Based Simulation Optimization Algorithms via Multi-Resolution System Approximations," INFORMS Journal on Computing, INFORMS, vol. 35(3), pages 633-651, May.
    12. 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.
    13. Jun Xie & Qingyun Yu & Chi Cao, 2018. "A Distributed Randomized Gradient-Free Algorithm for the Non-Convex Economic Dispatch Problem," Energies, MDPI, vol. 11(1), pages 1-15, January.
    14. Yijie Peng & Li Xiao & Bernd Heidergott & L. Jeff Hong & Henry Lam, 2022. "A New Likelihood Ratio Method for Training Artificial Neural Networks," INFORMS Journal on Computing, INFORMS, vol. 34(1), pages 638-655, 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:joptap:v:194:y:2022:i:1:d:10.1007_s10957-021-01994-w. 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.