Achieving Acceleration in Distributed Optimization via Direct Discretization of the Heavy-Ball ODE
Optimization and Control
2018-11-07 v1
Abstract
We develop a distributed algorithm for convex Empirical Risk Minimization, the problem of minimizing large but finite sum of convex functions over networks. The proposed algorithm is derived from directly discretizing the second-order heavy-ball differential equation and results in an accelerated convergence rate, i.e, faster than distributed gradient descent-based methods for strongly convex objectives that may not be smooth. Notably, we achieve acceleration without resorting to the well-known Nesterov's momentum approach. We provide numerical experiments and contrast the proposed method with recently proposed optimal distributed optimization algorithms.
Cite
@article{arxiv.1811.02521,
title = {Achieving Acceleration in Distributed Optimization via Direct Discretization of the Heavy-Ball ODE},
author = {Jingzhao Zhang and César A. Uribe and Aryan Mokhtari and Ali Jadbabaie},
journal= {arXiv preprint arXiv:1811.02521},
year = {2018}
}