On the evaluation complexity of composite function minimization with applications to nonconvex nonlinear programming

Coralia Cartis, Nick Gould, Philippe Toint

Research output: Contribution to journalArticlepeer-review

32 Downloads (Pure)

Abstract

We estimate the worst-case complexity of minimizing an unconstrained, nonconvex composite objective with a structured nonsmooth term by means of some first-order methods. We find that it is unaffected by the nonsmoothness of the objective in that a first-order trust-region or quadratic regularization method applied to it takes at most O(ε-2) function evaluations to reduce the size of a first-order criticality measure below ε. Specializing this result to the case when the composite objective is an exact penalty function allows us to consider the objective- and constraintevaluation worst-case complexity of nonconvex equality-constrained optimization when the solution is computed using a first-order exact penalty method. We obtain that in the reasonable case when the penalty parameters are bounded, the complexity of reaching within ε of a KKT point is at most O(ε-2) problem evaluations, which is the same in order as the function-evaluation complexity of steepest-descent methods applied to unconstrained, nonconvex smooth optimization. © 2011 Society for Industrial and Applied Mathematics.
Original languageEnglish
Pages (from-to)1721-1739
Number of pages19
JournalSIAM Journal on Optimization
Volume21
Issue number4
DOIs
Publication statusPublished - 1 Jan 2011

Keywords

  • nonlinear optimization
  • composite minimization
  • complexity
  • nonconvex problems.

Fingerprint

Dive into the research topics of 'On the evaluation complexity of composite function minimization with applications to nonconvex nonlinear programming'. Together they form a unique fingerprint.

Cite this