Jun 2026
Large-step symmetric hybrid stochastic Bregman-type ADMM for solving constrained nonconvex and nonsmooth composite optimization under no the KL property
A novel stochastic alternating direction method of multipliers (ADMM) is proposed to solve large-scale linearly constrained nonconvex and nonsmooth composite optimization problems, and establishes global convergence and sublinear convergence rate of the proposed method.
Yi-Xin Yang, Heng-you Lan, Lin-Cheng Jiang
· Positivity (Dordrecht) · 0 citations