Linear convergence for distributed stochastic optimization with coupled inequality constraints

• Published in: Journal of the Franklin Institute Vol. 362; no. 1; p. 107405
• Main Authors: Du, Kaixin, Meng, Min, Li, Xiuxian
• Format: Journal Article
• Language: English
• Published: Elsevier Inc 01.01.2025
• Subjects: Coupled affine inequality constraints; Distributed stochastic optimization; Linear convergence; Primal–dual algorithm; Variance reduction; Distributed stochastic optimization; Linear convergence; Coupled affine inequality constraints; Primal–dual algorithm; Variance reduction
• ISSN: 0016-0032
• DOI: 10.1016/j.jfranklin.2024.107405

This paper considers the distributed stochastic optimization problem over time-varying networks, in which agents aim to cooperatively minimize the expected value of the sum of their cost functions subject to coupled affine inequalities. Considering various stochastic factors and constraints on decis...