Distributed Semi-Stochastic Optimization with Quantization Refinement
Optimization and Control
2016-03-22 v1 Systems and Control
Abstract
We consider the problem of regularized regression in a network of communication-constrained devices. Each node has local data and objectives, and the goal is for the nodes to optimize a global objective. We develop a distributed optimization algorithm that is based on recent work on semi-stochastic proximal gradient methods. Our algorithm employs iteratively refined quantization to limit message size. We present theoretical analysis and conditions for the algorithm to achieve a linear convergence rate. Finally, we demonstrate the performance of our algorithm through numerical simulations.
Cite
@article{arxiv.1603.06306,
title = {Distributed Semi-Stochastic Optimization with Quantization Refinement},
author = {Neil McGlohon and Stacy Patterson},
journal= {arXiv preprint arXiv:1603.06306},
year = {2016}
}