Quadratic and Cubic Regularisation Methods with Inexact function and Random Derivatives for Finite-Sum Minimisation

Stefania Bellavia, Gianmarco Gurioli, Benedetta Morini, Philippe L. Toint

    Résultats de recherche: Contribution dans un livre/un catalogue/un rapport/dans les actes d'une conférenceArticle dans les actes d'une conférence/un colloque

    Résumé

    This paper focuses on regularisation methods using models up to the third order to search for up to second-order critical points of a finite-sum minimisation problem. The variant presented belongs to the framework of [1]: it employs random models with accuracy guaranteed with a sufficiently large prefixed probability and deterministic inexact function evaluations within a prescribed level of accuracy. Without assuming unbiased estimators, the expected number of iterations is O( _1^ - 2 ) or O( _1^ - 3/2 ) when searching for a first-order critical point using a second or third order model, respectively, and of O( max [ _1^ - 3/2, _2^ - 3 ] ) when seeking for second-order critical points with a third order model, in which _j,j 1,2, is the j th-order tolerance. These results match the worst-case optimal complexity for the deterministic counterpart of the method. Preliminary numerical tests for first-order optimality in the context of nonconvex binary classification in imaging, with and without Artifical Neural Networks (ANNs), are presented and discussed.

    langue originaleAnglais
    titreProceedings - 2021 21st International Conference on Computational Science and Its Applications, ICCSA 2021
    EditeurInstitute of Electrical and Electronics Engineers Inc.
    Pages258-267
    Nombre de pages10
    ISBN (Electronique)9781665458436
    Les DOIs
    Etat de la publicationPublié - 2021
    Evénement21st International Conference on Computational Science and Its Applications, ICCSA 2021 - Cagliari, Italie
    Durée: 13 sept. 202116 sept. 2021

    Série de publications

    NomProceedings - 2021 21st International Conference on Computational Science and Its Applications, ICCSA 2021

    Une conférence

    Une conférence21st International Conference on Computational Science and Its Applications, ICCSA 2021
    Pays/TerritoireItalie
    La villeCagliari
    période13/09/2116/09/21

    Empreinte digitale

    Examiner les sujets de recherche de « Quadratic and Cubic Regularisation Methods with Inexact function and Random Derivatives for Finite-Sum Minimisation ». Ensemble, ils forment une empreinte digitale unique.

    Contient cette citation