English

Zero Order Stochastic Weakly Convex Composite Optimization

Optimization and Control 2020-02-20 v1

Abstract

In this paper we consider stochastic weakly convex composite problems, however without the existence of a stochastic subgradient oracle. We present a derivative free algorithm that uses a two point approximation for computing a gradient estimate of the smoothed function. We prove convergence at a similar rate as state of the art methods, however with a larger constant, and report some numerical results showing the effectiveness of the approach.

Keywords

Cite

@article{arxiv.2002.08083,
  title  = {Zero Order Stochastic Weakly Convex Composite Optimization},
  author = {V. Kungurtsev and F. Rinaldi},
  journal= {arXiv preprint arXiv:2002.08083},
  year   = {2020}
}