Convergence Analysis of the Relaxed Proximal Point Algorithm

الملخص EN

Recently, a worst-case O(1/t) convergence rate was established for the Douglas-Rachford alternating direction method of multipliers (ADMM) in an ergodic sense.

The relaxed proximal point algorithm (PPA) is a generalization of the original PPA which includes the Douglas-Rachford ADMM as a special case.

In this paper, we provide a simple proof for the same convergence rate of the relaxed PPA in both ergodic and nonergodic senses.