Xiaoming Yuan, 香港浸会大学


Block-wise Alternating Direction Method of Multipliers for Multiple-block Convex Programming and Beyond


The alternating direction method of multipliers (ADMM) is a benchmark for solving a linearly constrained convex minimization model with a two-block separable objective function; and it has been shown that its direct extension to a multiple-block case where the objective function is the sum of more than two functions is not necessarily convergent. For the multiple-block case, a natural idea is to artificially group the objective functions and the corresponding variables as two groups and then apply the original ADMM directly – the block-wise ADMM is accordingly named because each of the resulting ADMM subproblems may involve more than one function in its objective. Such a subproblem of the block-wise ADMM may not be easy as it may require minimizing more than one function with coupled variables simultaneously. We discuss how to further decompose the block-wise ADMM’s subproblems and obtain easier subproblems so that the properties of each function in the objective can be individually and thus effectively used, while the convergence can still be ensured. Extensions to the block-wise versions of the generalized ADMM and the ADMM with Gaussian back substitution will also be discussed.

« Back