English

Backtracking linesearch for conditional gradient sliding

Optimization and Control 2020-06-11 v1

Abstract

We present a modification of the conditional gradient sliding (CGS) method that was originally developed in \cite{lan2016conditional}. While the CGS method is a theoretical breakthrough in the theory of projection-free first-order methods since it is the first that reaches the theoretical performance limit, in implementation it requires the knowledge of the Lipschitz constant of the gradient of the objective function LL and the number of total gradient evaluations NN. Such requirements imposes difficulties in the actual implementation, not only because that it can be difficult to choose proper values of LL and NN that satisfies the conditions for convergence, but also since conservative choices of LL and NN can deteriorate the practical numerical performance of the CGS method. Our proposed method, called the conditional gradient sliding method with linesearch (CGS-ls), does not require the knowledge of either LL and NN, and is able to terminate early before the theoretically required number of iterations. While more practical in numerical implementation, the theoretical performance of our proposed CGS-ls method is still as good as that of the CGS method. We present numerical experiments to show the efficiency of our proposed method in practice.

Keywords

Cite

@article{arxiv.2006.05272,
  title  = {Backtracking linesearch for conditional gradient sliding},
  author = {Hamid Nazari and Yuyuan Ouyang},
  journal= {arXiv preprint arXiv:2006.05272},
  year   = {2020}
}