This is an early access version, the complete PDF, HTML, and XML versions will be available soon.
Open AccessArticle
A Momentum-Based Adaptive Primal–Dual Stochastic Gradient Method for Non-Convex Programs with Expectation Constraints
by
Rulei Qi
Rulei Qi ,
Dan Xue
Dan Xue * and
Yujia Zhai
Yujia Zhai
School of Mathematics and Statistics, Qingdao University, Qingdao 266071, China
*
Author to whom correspondence should be addressed.
Mathematics 2024, 12(15), 2393; https://doi.org/10.3390/math12152393 (registering DOI)
Submission received: 9 July 2024
/
Revised: 26 July 2024
/
Accepted: 28 July 2024
/
Published: 31 July 2024
Abstract
In this paper, we propose a stochastic primal-dual adaptive method based on an inexact augmented Lagrangian function to solve non-convex programs, referred to as the SPDAM. Different from existing methods, SPDAM incorporates adaptive step size and momentum-based search directions, which improve the convergence rate. At each iteration, an inexact augmented Lagrangian subproblem is solved to update the primal variables. A post-processing step is designed to adjust the primal variables to meet the accuracy requirement, and the adjusted primal variable is used to compute the dual variable. Under appropriate assumptions, we prove that the method converges to the -KKT point of the primal problem, and a complexity result of SPDAM less than is established. This is better than the most famous result. The numerical experimental results validate that this method outperforms several existing methods with fewer iterations and a lower running time.
Share and Cite
MDPI and ACS Style
Qi, R.; Xue, D.; Zhai, Y.
A Momentum-Based Adaptive Primal–Dual Stochastic Gradient Method for Non-Convex Programs with Expectation Constraints. Mathematics 2024, 12, 2393.
https://doi.org/10.3390/math12152393
AMA Style
Qi R, Xue D, Zhai Y.
A Momentum-Based Adaptive Primal–Dual Stochastic Gradient Method for Non-Convex Programs with Expectation Constraints. Mathematics. 2024; 12(15):2393.
https://doi.org/10.3390/math12152393
Chicago/Turabian Style
Qi, Rulei, Dan Xue, and Yujia Zhai.
2024. "A Momentum-Based Adaptive Primal–Dual Stochastic Gradient Method for Non-Convex Programs with Expectation Constraints" Mathematics 12, no. 15: 2393.
https://doi.org/10.3390/math12152393
Note that from the first issue of 2016, this journal uses article numbers instead of page numbers. See further details
here.
Article Metrics
Article Access Statistics
For more information on the journal statistics, click
here.
Multiple requests from the same IP address are counted as one view.