Distributed, scalable and gossip-free consensus optimization with application to data analysis
arXiv: Optimization and Control, 2017.
Distributed algorithms for solving additive or consensus optimization problems commonly rely on first-order or proximal splitting methods. These algorithms generally come with restrictive assumptions and at best enjoy a linear convergence rate. Hence, they can require many iterations or communications among agents to converge. In many c...More
Full Text (Upload PDF)
PPT (Upload PPT)