English

On the Convergence of Primal-Dual Proximal Incremental Aggregated Gradient Algorithms

Optimization and Control 2019-11-14 v1

Abstract

In this paper, we adapt proximal incremental aggregated gradient methods to saddle point problems, which is motivated by decoupling linear transformations in regularized empirical risk minimization models. First, the Primal-Dual Proximal Incremental Aggregated (PD-PIAG) methods with extrapolations were proposed. We proved that the primal-dual gap of the averaged iteration sequence sublinearly converges to 0, and the iteration sequence converges to some saddle point. Under the strong convexity of ff and hh^\ast, we proved that the iteration sequence linearly converges to the saddle point. Then, we propose a PD-PIAG method without extrapolations. The primal-dual gap of the iteration sequence is proved to be sublinearly convergent under strong convexity of ff.

Keywords

Cite

@article{arxiv.1911.05396,
  title  = {On the Convergence of Primal-Dual Proximal Incremental Aggregated Gradient Algorithms},
  author = {Zhou Xianchen and Peng Wei and Wang Hongxia},
  journal= {arXiv preprint arXiv:1911.05396},
  year   = {2019}
}

Comments

17pages