Optimization Online


On Inexact Solution of Auxiliary Problems in Tensor Methods for Convex Optimization

Geovani Grapiglia (grapiglia***at***ufpr.br)
Yurii Nesterov (yurii.nesterov***at***uclouvain.be)

Abstract: In this paper we study the auxiliary problems that appear in p-order tensor methods for unconstrained minimization of convex functions with \nu-Holder continuous pth derivatives. This type of auxiliary problems corresponds to the minimization of a (p+\nu)-order regularization of the pth order Taylor approximation of the objective. For the case p=3, we consider the use of a Gradient Methods with Bregman distance. When the regularization parameter is sufficiently large, we prove that the referred methods take at most O(log(eps^{-1})) iterations to find either a suitable approximate stationary point of the tensor model or an eps-approximate stationary point of the original objective function.

Keywords: unconstrained minimization, high-order methods, tensor methods, Holder condition, worst-case global complexity bounds

Category 1: Convex and Nonsmooth Optimization

Citation: Optimization Methods and Software 36, 145-170 (2021)

Download: [PDF]

Entry Submitted: 07/30/2019
Entry Accepted: 07/30/2019
Entry Last Modified: 05/21/2021

Modify/Update this entry

  Visitors Authors More about us Links
  Subscribe, Unsubscribe
Digest Archive
Search, Browse the Repository


Coordinator's Board
Classification Scheme
Give us feedback
Optimization Journals, Sites, Societies
Mathematical Optimization Society