Optimization Online


Evaluation complexity of adaptive cubic regularization methods for convex unconstrained optimization

Coralia Cartis(Coralia.Cartis***at***ed.ac.uk)
Nicholas I. M. Gould(nick.gould***at***stfc.ac.uk)
Philippe L. Toint(philippe.toint***at***fundp.ac.be)

Abstract: The adaptive cubic regularization algorithms described in Cartis, Gould & Toint (2009, 2010) for unconstrained (nonconvex) optimization are shown to have improved worst-case efficiency in terms of the function- and gradient-evaluation count when applied to convex and strongly convex objectives. In particular, our complexity upper bounds match in order (as a function of the accuracy of approximation), and sometimes even improve, those obtained by Nesterov (2004, 2008) and Nesterov & Polyak (2006) for these same problem classes, without employing the Hessian's Lipschitz constant explicitly in the algorithms or requiring exact or global solution of the subproblem. An additional outcome of our approximate approach is that our complexity results can naturally capture the advantages of both first- and second-order methods.

Keywords: cubic regularization, Newton's method, convex optimization

Category 1: Nonlinear Optimization

Category 2: Convex and Nonsmooth Optimization

Citation: ERGO Technical Report 10-006, 2010, School of Mathematics, University of Edinburgh, United Kingdom

Download: [PDF]

Entry Submitted: 11/05/2010
Entry Accepted: 11/05/2010
Entry Last Modified: 11/05/2010

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 Programming Society