Proximally Guided Stochastic Subgradient Method for Nonsmooth, Nonconvex Problems

@article{Davis2017ProximallyGS,
  title={Proximally Guided Stochastic Subgradient Method for Nonsmooth, Nonconvex Problems},
  author={Damek Davis and Benjamin Grimmer},
  journal={CoRR},
  year={2017},
  volume={abs/1707.03505}
}
In this paper we introduce a stochastic projected subgradient method for weakly convex (i.e., uniformly prox-regular) nonsmooth, nonconvex functions—a wide class of functions which includes the additive and convex composite classes. At a high-level the method is an inexact proximal point iteration in which the strongly convex proximal subproblems are quickly solved with a specialized stochastic projected subgradient method. The primary contribution of this paper is a simple proof that the… CONTINUE READING
Recent Discussions
This paper has been referenced on Twitter 14 times over the past 90 days. VIEW TWEETS
6 Citations
36 References
Similar Papers

References

Publications referenced by this paper.
Showing 1-10 of 36 references

Stochastic methods for composite optimization problems

  • John Duchi, Feng Ruan
  • arXiv preprint arXiv:1703.08570,
  • 2017
Highly Influential
3 Excerpts

Catalyst acceleration for gradient-based non-convex optimization

  • Courtney Paquette, Hongzhou Lin, Dmitriy Drusvyatskiy, Julien Mairal, Zaid Harchaoui
  • arXiv preprint arXiv:1703.10993,
  • 2017
1 Excerpt

Similar Papers

Loading similar papers…