Convergence of a Stochastic Subgradient Method with Averaging for Nonsmooth Nonconvex Constrained Optimization
Optimization and Control
2019-12-17 v1
Abstract
We prove convergence of a single time-scale stochastic subgradient method with subgradient averaging for constrained problems with a nonsmooth and nonconvex objective function having the property of generalized differentiability. As a tool of our analysis, we also prove a chain rule on a path for such functions.
Cite
@article{arxiv.1912.07580,
title = {Convergence of a Stochastic Subgradient Method with Averaging for Nonsmooth Nonconvex Constrained Optimization},
author = {Andrzej Ruszczynski},
journal= {arXiv preprint arXiv:1912.07580},
year = {2019}
}