Distributed Memory Approximate Message Passing

TL;DR

This paper introduces D-MAMP, a distributed memory approximate message passing algorithm that overcomes limitations of previous methods, enabling efficient signal recovery in distributed systems with comparable performance to centralized algorithms.

Contribution

The paper proposes D-MAMP, a novel distributed AMP variant that reduces complexity and communication costs while maintaining optimal performance in distributed signal recovery.

Findings

D-MAMP converges to the same MSE as centralized MAMP on acyclic graphs.

D-MAMP reduces communication overhead compared to previous distributed AMP methods.

The algorithm effectively utilizes local observations and message passing for distributed computation.

Abstract

Approximate message passing (AMP) algorithms are iterative methods for signal recovery in noisy linear systems. In some scenarios, AMP algorithms need to operate within a distributed network. To address this challenge, the distributed extensions of AMP (D-AMP, FD-AMP) and orthogonal/vector AMP (D-OAMP/D-VAMP) were proposed, but they still inherit the limitations of centralized algorithms. In this letter, we propose distributed memory AMP (D-MAMP) to overcome the IID matrix limitation of D-AMP/FD-AMP, as well as the high complexity and heavy communication cost of D-OAMP/D-VAMP. We introduce a matrix-by-vector variant of MAMP tailored for distributed computing. Leveraging this variant, D-MAMP enables each node to execute computations utilizing locally available observation vectors and transform matrices. Meanwhile, global summations of locally updated results are conducted through message interaction among nodes. For acyclic graphs, D-MAMP converges to the same mean square error performance as the centralized MAMP.