IDEAS home Printed from https://ideas.repec.org/a/eee/spapps/v156y2023icp312-348.html
   My bibliography  Save this article

Optimal non-asymptotic analysis of the Ruppert–Polyak averaging stochastic algorithm

Author

Listed:
  • Gadat, Sébastien
  • Panloup, Fabien

Abstract

This paper is devoted to the non-asymptotic analysis of the Ruppert–Polyak averaging method introduced in Polyak and Juditsky (1992) and Ruppert (1988)[26] for the minimization of a smooth function f with a stochastic algorithm. We first establish a general non-asymptotic optimal bound: if θˆn is the position of the algorithm at step n, we prove that E|θˆn−argmin(f)|2⩽Tr(Σ⋆)n+Cd,fn−rβ,where Σ⋆ is the limiting covariance matrix of the CLT demonstrated in Polyak and Juditsky (1992) and Cd,fn−rβ is a new state-of-the-art second order term that translates the effect of the dimension. We also identify the optimal gain of the baseline SGD γn=γn−3/4, leading to a second-order term with r3/4=5/4. Second, we show that this result holds under some Kurdyka-Łojiasewicz-type condition (Kurdyka, 1988; Lojasiewicz, 1963) for function f, which is far more general than the standard uniformly strongly convex case. In particular, it makes it possible to handle some pathological examples such as on-line learning for logistic regression and recursive quantile estimation.

Suggested Citation

  • Gadat, Sébastien & Panloup, Fabien, 2023. "Optimal non-asymptotic analysis of the Ruppert–Polyak averaging stochastic algorithm," Stochastic Processes and their Applications, Elsevier, vol. 156(C), pages 312-348.
    • Handle: RePEc:eee:spapps:v:156:y:2023:i:c:p:312-348
    DOI: 10.1016/j.spa.2022.11.012
    as

    Download full text from publisher

    File URL: http://www.sciencedirect.com/science/article/pii/S0304414922002447
    Download Restriction: Full text for ScienceDirect subscribers only
    File URL: https://libkey.io/10.1016/j.spa.2022.11.012?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. Godichon-Baggioni, Antoine, 2016. "Estimating the geometric median in Hilbert spaces with stochastic gradient algorithms: Lp and almost sure rates of convergence," Journal of Multivariate Analysis, Elsevier, vol. 146(C), pages 209-222.
    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. Mokkadem, Abdelkader & Pelletier, Mariane, 2020. "Online estimation of integrated squared density derivatives," Statistics & Probability Letters, Elsevier, vol. 166(C).
    2. Mokkadem, Abdelkader & Pelletier, Mariane, 2021. "A compact law of the iterated logarithm for online estimator of hazard rate under random censoring," Statistics & Probability Letters, Elsevier, vol. 178(C).
    3. Godichon-Baggioni, Antoine & Lu, Wei, 2024. "Online stochastic Newton methods for estimating the geometric median and applications," Journal of Multivariate Analysis, Elsevier, vol. 202(C).
    4. Hervé Cardot & Antoine Godichon-Baggioni, 2017. "Fast estimation of the median covariation matrix with application to online robust principal components analysis," TEST: An Official Journal of the Spanish Society of Statistics and Operations Research, Springer;Sociedad de Estadística e Investigación Operativa, vol. 26(3), pages 461-480, September.
    5. Cheng, Guanghui & Xiong, Qiang & Lin, Ruitao, 2024. "Online bootstrap inference for the geometric median," Computational Statistics & Data Analysis, Elsevier, vol. 197(C).
    6. Vishwajit Hegde & Arvind S. Menon & L. A. Prashanth & Krishna Jagannathan, 2021. "Online Estimation and Optimization of Utility-Based Shortfall Risk," Papers 2111.08805, arXiv.org, revised Nov 2023.

    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:spapps:v:156:y:2023:i:c:p:312-348. 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: Catherine Liu (email available below). General contact details of provider: http://www.elsevier.com/wps/find/journaldescription.cws_home/505572/description#description .

    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.