English

Rate of Convergence of the Bundle Method

Optimization and Control 2016-09-06 v1

Abstract

We prove that the bundle method for nonsmooth optimization achieves solution accuracy ε\varepsilon in at most O(ln(1/ε)/ε)\mathcal{O}\big(\ln(1/\varepsilon)/\varepsilon\big) iterations, if the function is strongly convex. The result is true for the versions of the method with multiple cuts and with cut aggregation.

Keywords

Cite

@article{arxiv.1609.00842,
  title  = {Rate of Convergence of the Bundle Method},
  author = {Yu Du and Andrzej Ruszczynski},
  journal= {arXiv preprint arXiv:1609.00842},
  year   = {2016}
}

Comments

arXiv admin note: text overlap with arXiv:1511.01716