Thông tin tài liệu

Thông tin siêu dữ liệu biểu ghi
Trường DC Giá trịNgôn ngữ
dc.contributor.authorNikita, Doikov-
dc.contributor.authorYurii, Nesterov-
dc.date.accessioned2023-04-05T03:12:47Z-
dc.date.available2023-04-05T03:12:47Z-
dc.date.issued2023-
dc.identifier.urihttps://link.springer.com/article/10.1007/s10107-023-01943-7-
dc.identifier.urihttps://dlib.phenikaa-uni.edu.vn/handle/PNK/7538-
dc.descriptionCC BYvi
dc.description.abstractIn this paper, we propose a first second-order scheme based on arbitrary non-Euclidean norms, incorporated by Bregman distances. They are introduced directly in the Newton iterate with regularization parameter proportional to the square root of the norm of the current gradient. For the basic scheme, as applied to the composite convex optimization problem, we establish the global convergence rate of the order O(k−2) both in terms of the functional residual and in the norm of subgradients. Our main assumption on the smooth part of the objective is Lipschitz continuity of its Hessian.vi
dc.language.isoenvi
dc.publisherSpringervi
dc.subjectorder O(k−2) bothvi
dc.subjectLipschitz continuity of its Hessianvi
dc.titleGradient regularization of Newton method with Bregman distancesvi
dc.typeBookvi
Bộ sưu tập
OER - Khoa học Tự nhiên

Danh sách tệp tin đính kèm:

Ảnh bìa
  • Gradient regularization of Newton method with Bregman distances-2023.pdf
      Restricted Access
    • Dung lượng : 742,44 kB

    • Định dạng : Adobe PDF