Dynamical convergence analysis for nonconvex linearized proximal ADMM algorithms (2309.07008v1)

Abstract: The convergence analysis of optimization algorithms using continuous-time dynamical systems has received much attention in recent years. In this paper, we investigate applications of these systems to analyze the convergence of linearized proximal ADMM algorithms for nonconvex composite optimization, whose objective function is the sum of a continuously differentiable function and a composition of a possibly nonconvex function with a linear operator. We first derive a first-order differential inclusion for the linearized proximal ADMM algorithm, LP-ADMM. Both the global convergence and the convergence rates of the generated trajectory are established with the use of Kurdyka-\L{}ojasiewicz (KL) property. Then, a stochastic variant, LP-SADMM, is delved into an investigation for finite-sum nonconvex composite problems. Under mild conditions, we obtain the stochastic differential equation corresponding to LP-SADMM, and demonstrate the almost sure global convergence of the generated trajectory by leveraging the KL property. Based on the almost sure convergence of trajectory, we construct a stochastic process that converges almost surely to an approximate critical point of objective function, and derive the expected convergence rates associated with this stochastic process. Moreover, we propose an accelerated LP-SADMM that incorporates Nesterov's acceleration technique. The continuous-time dynamical system of this algorithm is modeled as a second-order stochastic differential equation. Within the context of KL property, we explore the related almost sure convergence and expected convergence rates.