A Riemannian gossip approach to decentralized matrix completion

@article{Mishra2016ARG,
  title={A Riemannian gossip approach to decentralized matrix completion},
  author={Bamdev Mishra and Hiroyuki Kasai and Atul Saroop},
  journal={CoRR},
  year={2016},
  volume={abs/1605.06968}
}
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. 

From This Paper

Figures, tables, and topics from this paper.

References

Publications referenced by this paper.
Showing 1-10 of 21 references

A Riemannian gossip approach to decentralized matrix completion

  • B. Mishra, H. Kasai, A Saroop
  • arXiv preprint arXiv:1605.06968,
  • 2016

Konstan . The MovieLens datasets : hi tory and contex

  • A. J.
  • ACM Transactions on Interactive Intelligent…
  • 2015

R 3 MC : A Riemannian threefactor algorithm for low - rank matrix completion

  • W. Yin Z. Wen, Y. Zhang
  • 2014