We study distributed (strongly convex) optimization problems over a network of agents, with no centralized nodes. The loss functions of the agents are assumed to be \textit{similar}, due to statistical data similarity or otherwise. In order to reduce the number of communications to reach a solution accuracy, we proposed a {\it preconditioned, accelerated} distributed method. An ε-solution is achieved in O~(1−ρβ/μlog1/ε) number of communications steps, where β/μ is the relative condition number between the global and local loss functions, and ρ characterizes the connectivity of the network. This rate matches (up to poly-log factors) lower complexity communication bounds of distributed gossip-algorithms applied to the class of problems of interest. Numerical results show significant communication savings with respect to existing accelerated distributed schemes, especially when solving ill-conditioned problems.
@article{arxiv.2110.12347,
title = {Acceleration in Distributed Optimization under Similarity},
author = {Ye Tian and Gesualdo Scutari and Tianyu Cao and Alexander Gasnikov},
journal= {arXiv preprint arXiv:2110.12347},
year = {2022}
}