An inexact ADMM with proximal-indefinite term and larger stepsize

This work is devoted to developing an inexact ADMM for solving a family of multi-block separable convex optimization problems subject to linear equality constraints, where the problem variables are artificially partitioned into two groups. The first grouped subproblems are solved inexactly and and parallelly under relative error criterions, while the second grouped single subproblem (often … Read more

Accelerated Stochastic Peaceman-Rachford Method for Empirical Risk Minimization

This work is devoted to studying an Accelerated Stochastic Peaceman-Rachford Splitting Method (AS-PRSM) for solving a family of structural empirical risk minimization problems. The objective function of this problem is the sum of a possibly nonsmooth convex function and a finite-sum of smooth convex component functions. The smooth subproblem in AS-PRSM is solved by an … Read more