Proximal stochastic recursive momentum algorithm for nonsmooth nonconvex optimization problems
Authors:
- 23 August 2022
- journal article
- research article
- Published by Taylor & Francis in Optimization
- Vol. 73 (2) , 481-495
Abstract
In this paper, we mainly consider a class of nonconvex nonsmooth optimization problems, whose objective function is the sum of a smooth function with a Lipschitz continuous gradient and a convex nonsmooth function. We first propose a proximal stochastic recursive momentum algorithm(ProxSTORM) with mini-batch for solving the optimization problems and consider its convergence behaviour. Then, based on the Polyak–Łojasiewicz inequality, we establish the global linear convergence rate of ProxSTORM. Finally, some numerical experiments have been conducted to illustrate the efficiency of our method.Keywords
Funding Information
- National Natural Science Foundation of China (NSFC11801131)
- Natural Science Foundation of Hebei Province (A2019202229)
This publication has 9 references indexed in Scilit:
- A hybrid stochastic optimization framework for composite nonconvex optimizationMathematical Programming, 2021
- Random Gradient Extrapolation for Distributed and Stochastic OptimizationSIAM Journal on Optimization, 2018
- Optimization Methods for Large-Scale Machine LearningSIAM Review, 2018
- Linear Convergence of Gradient and Proximal-Gradient Methods Under the Polyak-Łojasiewicz Condition2016
- Mini-batch stochastic approximation methods for nonconvex stochastic composite optimizationMathematical Programming, 2014
- A Proximal Stochastic Gradient Method with Progressive Variance ReductionSIAM Journal on Optimization, 2014
- Proximal alternating linearized minimization for nonconvex and nonsmooth problemsMathematical Programming, 2013
- A generalized proximal point algorithm for certain non-convex minimization problemsInternational Journal of Systems Science, 1981
- Gradient methods for the minimisation of functionalsUSSR Computational Mathematics and Mathematical Physics, 1963