“…However, ALM ignores the structure of the problem, so in practice, the performance of ALM is not competitive with specialized algorithms. For example, the alternating directions method of multipliers (ADMM) [18,19], which is based on ALM, is considered the most popular technique, capable of handling multiple blocks of variables in parallel [18,20,21], thereby exhibiting superior implementation efficiency for both convex and nonconvex problems [22][23][24], even for deep neural training [25,26]. However, whether ADMM can be applied to solving the nonlinear block coupled variables for nonconvex problems is still unknown.…”