Stochastic Conditional Gradient Methods: From Convex Minimization to Submodular Maximization

@article{Mokhtari2018StochasticCG,
  title={Stochastic Conditional Gradient Methods: From Convex Minimization to Submodular Maximization},
  author={Aryan Mokhtari and Hamed Hassani and Amin Karbasi},
  journal={CoRR},
  year={2018},
  volume={abs/1804.09554}
}
This paper considers stochastic optimization problems for a large class of objective functions, including convex and continuous submodular. Stochastic proximal gradient methods have been widely used to solve such problems; however, their applicability remains limited when the problem dimension is large and the projection onto a convex set is computationally… CONTINUE READING