Corpus ID: 211068892

On Unbalanced Optimal Transport: An Analysis of Sinkhorn Algorithm

@article{Pham2020OnUO,
  title={On Unbalanced Optimal Transport: An Analysis of Sinkhorn Algorithm},
  author={Khiem Pham and Khang D Le and Nhat Ho and Tung Pham and Hung Hai Bui},
  journal={ArXiv},
  year={2020},
  volume={abs/2002.03293}
}
  • Khiem Pham, Khang D Le, +2 authors Hung Hai Bui
  • Published 2020
  • Mathematics, Computer Science
  • ArXiv
  • We provide a computational complexity analysis for the Sinkhorn algorithm that solves the entropic regularized Unbalanced Optimal Transport (UOT) problem between two measures of possibly different masses with at most $n$ components. We show that the complexity of the Sinkhorn algorithm for finding an $\varepsilon$-approximate solution to the UOT problem is of order $\widetilde{\mathcal{O}}(n^2/ \varepsilon)$, which is near-linear time. To the best of our knowledge, this complexity is better… CONTINUE READING

    References

    Publications referenced by this paper.
    SHOWING 1-10 OF 22 REFERENCES

    Path Finding Methods for Linear Programming: Solving Linear Programs in Õ(vrank) Iterations and Faster Algorithms for Maximum Flow

    • Yin Tat Lee, Aaron Sidford
    • Mathematics, Computer Science
    • 2014 IEEE 55th Annual Symposium on Foundations of Computer Science
    • 2014
    VIEW 1 EXCERPT

    Sinkhorn Distances: Lightspeed Computation of Optimal Transport

    VIEW 5 EXCERPTS
    HIGHLY INFLUENTIAL