Convergence of a Stochastic Subgradient Method with Averaging for Nonsmooth Nonconvex Constrained Optimization

2019/12/16 by Ruszczynski, Andrzej · 1 citation
#90C15 #90C48 #FOS: Mathematics #Optimization and Control (math.OC)

paper · doi:10.48550/arxiv.1912.07580

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.

Cited by

• A Hybrid Subgradient Method for Nonsmooth Nonconvex Bilevel Optimization

Related

• A Stochastic Subgradient Method for Nonsmooth Nonconvex Multi-Level Composition Optimization
• Stochastic Subgradient Methods with Guaranteed Global Stability in Nonsmooth Nonconvex Optimization
• Proximally Guided Stochastic Subgradient Method for Nonsmooth, Nonconvex Problems
• Graphical Convergence of Subgradients in Nonconvex Optimization and\n Learning
• Convergence of Decentralized Stochastic Subgradient-based Methods for Nonsmooth Nonconvex Optimization