English

BFGS convergence to nonsmooth minimizers of convex functions

Optimization and Control 2017-03-21 v1

Abstract

The popular BFGS quasi-Newton minimization algorithm under reasonable conditions converges globally on smooth convex functions. This result was proved by Powell in 1976: we consider its implications for functions that are not smooth. In particular, an analogous convergence result holds for functions, like the Euclidean norm, that are nonsmooth at the minimizer.

Keywords

Cite

@article{arxiv.1703.06690,
  title  = {BFGS convergence to nonsmooth minimizers of convex functions},
  author = {Jiayi Guo and Adrian Lewis},
  journal= {arXiv preprint arXiv:1703.06690},
  year   = {2017}
}