Learning Wasserstein Embeddings

@article{Courty2017LearningWE,
  title={Learning Wasserstein Embeddings},
  author={Nicolas Courty and R{\'e}mi Flamary and M{\'e}lanie Ducoffe},
  journal={CoRR},
  year={2017},
  volume={abs/1710.07457}
}
The Wasserstein distance received a lot of attention recently in the community of machine learning, especially for its principled way of comparing distributions. It has found numerous applications in several hard problems, such as domain adaptation, dimensionality reduction or generative models. However, its use is still limited by a heavy computational cost. Our goal is to alleviate this problem by providing an approximation mechanism that allows to break its inherent complexity. It relies on… CONTINUE READING
Recent Discussions
This paper has been referenced on Twitter 135 times over the past 90 days. VIEW TWEETS

References

Publications referenced by this paper.
Showing 1-10 of 42 references

Statistical archetypal analysis

  • C. Wu, E. Tabak
  • arXiv preprint arXiv:1701.08916,
  • 2017
Highly Influential
4 Excerpts

Pot python optimal transport

  • R. Flamary, N. Courty
  • library. 2017
  • 2017
3 Excerpts

Similar Papers

Loading similar papers…