Corpus ID: 167217585

A Graph Theoretic Additive Approximation of Optimal Transport

@inproceedings{Lahn2019AGT,
  title={A Graph Theoretic Additive Approximation of Optimal Transport},
  author={Nathaniel Lahn and Deepika Mulchandani and Sharath Raghvendra},
  booktitle={NeurIPS},
  year={2019}
}
  • Nathaniel Lahn, Deepika Mulchandani, Sharath Raghvendra
  • Published in NeurIPS 2019
  • Computer Science, Mathematics
  • Transportation cost is an attractive similarity measure between probability distributions due to its many useful theoretical properties. However, solving optimal transport exactly can be prohibitively expensive. Therefore, there has been significant effort towards the design of scalable approximation algorithms. Previous combinatorial results [Sharathkumar, Agarwal STOC '12, Agarwal, Sharathkumar STOC '14] have focused primarily on the design of strongly polynomial multiplicative approximation… CONTINUE READING

    Create an AI-powered research feed to stay up to date with new papers like this posted to ArXiv

    2
    Twitter Mentions

    References

    Publications referenced by this paper.
    SHOWING 1-10 OF 30 REFERENCES

    Preconditioning for the Geometric Transportation Problem

    VIEW 2 EXCERPTS

    Approximating optimal transport with linear programs

    VIEW 2 EXCERPTS

    Wasserstein discriminant analysis

    VIEW 1 EXCERPT