A Riemannian gossip approach to decentralized matrix completion
Numerical Analysis
2016-05-24 v1 Machine Learning
Optimization and Control
Abstract
In this paper, we propose novel gossip algorithms for the low-rank decentralized matrix completion problem. The proposed approach is on the Riemannian Grassmann manifold that allows local matrix completion by different agents while achieving asymptotic consensus on the global low-rank factors. The resulting approach is scalable and parallelizable. Our numerical experiments show the good performance of the proposed algorithms on various benchmarks.
Keywords
Cite
@article{arxiv.1605.06968,
title = {A Riemannian gossip approach to decentralized matrix completion},
author = {Bamdev Mishra and Hiroyuki Kasai and Atul Saroop},
journal= {arXiv preprint arXiv:1605.06968},
year = {2016}
}
Comments
Under review