An incremental quasi-Newton method with a local superlinear convergence rate

Aryan Mokhtari, Mark Eisen, Alejandro Ribeiro

Abstract

We present an incremental Broyden-Fletcher-Goldfarb-Shanno (BFGS) method as a quasi-Newton algorithm with a cyclically iterative update scheme for solving large-scale optimization problems. The proposed incremental quasi-Newton (IQN) algorithm reduces computational cost relative to traditional quasi-Newton methods by restricting the update to a single function per iteration and relative to incremental second-order methods by removing the need to compute the inverse of the Hessian. A local superlinear convergence rate is established and a strong improvement is shown over first order methods numerically for a set of common large-scale optimization problems.
BibTeX
@inproceedings{mokhtari2017incremental,
  author = {Aryan Mokhtari and Mark Eisen and Alejandro Ribeiro},
  title = {{An incremental quasi-Newton method with a local superlinear convergence rate}},
  booktitle = {IEEE International Conference on Acoustics, Speech and Signal Processing},
  year = {2017},
  doi = {10.1109/icassp.2017.7952915},
}
Figure