Decentralized Proximal Optimization Method with Consensus Procedure

Abstract

Decentralized optimization is well studied for smooth unconstrained problems. However, constrained problems or problems with composite terms are an open direction for research. We study structured (or composite) optimization problems, where the functional is a sum of a convex smooth function and a proper convex proximal-friendly term. Our method builds upon an accelerated proximal gradient descent and makes several consensus iterations between computations. Our result illustrates that a consensus procedure approach works for composite optimization and yields a method with a relatively simple structure and analysis.