A Smoothed Dual Approach for Variational Wasserstein Problems

  title={A Smoothed Dual Approach for Variational Wasserstein Problems},
  author={Marco Cuturi and Gabriel Peyr{\'e}},
  journal={SIAM J. Imaging Sciences},
Variational problems that involve Wasserstein distances have been recently proposed to summarize and learn from probability measures. Despite being conceptually simple, such problems are computationally challenging because they involve minimizing over quantities (Wasserstein distances) that are themselves hard to compute. We show that the dual formulation of Wasserstein variational problems introduced recently by [13] can be regularized using an entropic smoothing, which leads to smooth… CONTINUE READING
Highly Cited
This paper has 52 citations. REVIEW CITATIONS


Publications citing this paper.
Showing 1-10 of 39 extracted citations

53 Citations

Citations per Year
Semantic Scholar estimates that this publication has 53 citations based on the available data.

See our FAQ for additional information.


Publications referenced by this paper.
Showing 1-10 of 38 references

Numerical methods for matching for teams and Wasserstein barycenters

  • G. Carlier, A. Oberman, E. Oudet
  • Preprint hal-00987292, Preprint HAL-00987292,
  • 2014
Highly Influential
10 Excerpts

A generalized model for optimal transport of images including dissipation and density modulation

  • J. Maas, M. Rumpf, C. Schonlieb, S. Simon
  • Arxiv preprint,
  • 2014
1 Excerpt

Similar Papers

Loading similar papers…