Nonconvex generalization of Alternating Direction Method of Multipliers for nonlinear equality constrained problems

The classic Alternating Direction Method of Multipliers (ADMM) is a popular framework to solve linear-equality constrained problems. In this paper, we extend the ADMM naturally nonlinear equality-constrained problems, called neADMM. difficulty neADMM nonconvex subproblems. We provide globally optimal solutions them in two important applications. Experiments on synthetic and real-world datasets demonstrate excellent performance scalability our proposed over existing state-of-the-start methods.