Corpus ID: 201668820

Optimal transport mapping via input convex neural networks

@article{Makkuva2019OptimalTM,
  title={Optimal transport mapping via input convex neural networks},
  author={Ashok Vardhan Makkuva and Amirhossein Taghvaei and Sewoong Oh and Jason D. Lee},
  journal={ArXiv},
  year={2019},
  volume={abs/1908.10962}
}
  • Ashok Vardhan Makkuva, Amirhossein Taghvaei, +1 author Jason D. Lee
  • Published 2019
  • Computer Science, Mathematics
  • ArXiv
  • In this paper, we present a novel and principled approach to learn the optimal transport between two distributions, from samples. Guided by the optimal transport theory, we learn the optimal Kantorovich potential which induces the optimal transport map. This involves learning two convex functions, by solving a novel minimax optimization. Building upon recent advances in the field of input convex neural networks, we propose a new framework where the gradient of one convex function represents the… CONTINUE READING

    Figures and Topics from this paper.

    Explore key concepts

    Links to highly relevant papers for key concepts in this paper:

    Citations

    Publications citing this paper.

    References

    Publications referenced by this paper.
    SHOWING 1-10 OF 40 REFERENCES