English

Sharp worst-case evaluation complexity bounds for arbitrary-order nonconvex optimization with inexpensive constraints

Optimization and Control 2021-05-31 v1 Artificial Intelligence Computational Complexity Numerical Analysis

Abstract

We provide sharp worst-case evaluation complexity bounds for nonconvex minimization problems with general inexpensive constraints, i.e.\ problems where the cost of evaluating/enforcing of the (possibly nonconvex or even disconnected) constraints, if any, is negligible compared to that of evaluating the objective function. These bounds unify, extend or improve all known upper and lower complexity bounds for unconstrained and convexly-constrained problems. It is shown that, given an accuracy level ϵ\epsilon, a degree of highest available Lipschitz continuous derivatives pp and a desired optimality order qq between one and pp, a conceptual regularization algorithm requires no more than O(ϵp+1pq+1)O(\epsilon^{-\frac{p+1}{p-q+1}}) evaluations of the objective function and its derivatives to compute a suitably approximate qq-th order minimizer. With an appropriate choice of the regularization, a similar result also holds if the pp-th derivative is merely H\"older rather than Lipschitz continuous. We provide an example that shows that the above complexity bound is sharp for unconstrained and a wide class of constrained problems, we also give reasons for the optimality of regularization methods from a worst-case complexity point of view, within a large class of algorithms that use the same derivative information.

Keywords

Cite

@article{arxiv.1811.01220,
  title  = {Sharp worst-case evaluation complexity bounds for arbitrary-order nonconvex optimization with inexpensive constraints},
  author = {Coralia Cartis and Nick I. M. Gould and Philippe L. Toint},
  journal= {arXiv preprint arXiv:1811.01220},
  year   = {2021}
}

Comments

30 pages

R2 v1 2026-06-23T05:03:06.018Z