Communication-efficient Distributed Solutions to a System of Linear Equations with Laplacian Sparse Structure
Peng Wang, Yuanqi Gao, Nanpeng Yu, Wei Ren, Jianming Jamie Lian, Di Xiao Wu · 2018
Two communication-efficient distributed algorithms are proposed to solve a system of linear equations Ax=b with Laplacian sparse A. A system of linear equations with Laplacian sparse A can be found in many applications, e.g., the power flow problems and other network flow problems. The first algorithm is based on the gradient descent method in optimization and the agents only share two parts of the system state instead of that of the whole system state, which saves significant communication. The two parts shared by every agent through a communication link are the state information of its own and its neighbor connected by the communication link. The second method is obtained from an approximation to the Newton method, which converges faster. It requires twice as much communication as the first one but is still communication-efficient due to the low dimension of each part shared between agents. The convergence at a linear rate of both methods is proved.