2022

Optimal Transport Tools (OTT): A JAX Toolbox for all things Wasserstein

Cuturi, Marco, Meng-Papaxanthos, Laetitia, Tian, Yingtao et al.

Understand

Optimal transport tools (OTT-JAX) is a Python toolbox that can solve optimal transport problems between point clouds and histograms.

  • The toolbox builds on various JAX features, such as automatic and custom reverse mode differentiation, vectorization, just-in-time compilation and accelerators support.
  • The toolbox covers elementary computations, such as the resolution of the regularized OT problem, and more advanced extensions, such as barycenters, Gromov-Wasserstein, low-rank solvers, estimation of convex maps, differentiable generalizations of quantiles and ranks, and approximate OT between Gaussian mixtures.
  • The toolbox code is available at \texttt{https://github.com/ott-jax/ott}

Built on

  • On the transfer of masses (in russian)

    Leonid Kantorovich · 1942

    Earlier work this paper cites.

  • Tres observaciones sobre el algebra lineal

    Garrett Birkhoff · 1946

    Earlier work this paper cites.

  • Network flows

    Ravindra K Ahuja, Thomas L Magnanti, and James B Orlin · 1988

    Earlier work this paper cites.

  • Ranking via sinkhorn propagation

    Original

    Ryan Prescott Adams and Richard S Zemel · 2011

    Earlier work this paper cites.

  • Gromov–Wasserstein distances and the metric approach to object matching

    Facundo Mémoli · 2011

    Earlier work this paper cites.

Similar

  • Sinkhorn distances: lightspeed computation of optimal transport

    Marco Cuturi · 2013

    Cited alongside, same era.

  • On the rate of convergence in Wasserstein distance of the empirical measure

    Nicolas Fournier and Arnaud Guillin · 2015

    Cited alongside, same era.

  • Wasserstein barycentric coordinates: histogram regression using optimal transport

    Nicolas Bonneel, Gabriel Peyré, and Marco Cuturi · 2016

    Cited alongside, same era.

  • Input convex neural networks

    Brandon Amos, Lei Xu, and J Zico Kolter · 2017

    Cited alongside, same era.

  • Differential properties of sinkhorn approximation for learning with wasserstein distance

    Giulia Luise, Alessandro Rudi, Massimiliano Pontil, and Carlo Ciliberto · 2018

    Cited alongside, same era.

  • Low-rank sinkhorn factorization

    Meyer Scetbon, Marco Cuturi, and Gabriel Peyré

    Cited in the paper.

  • Linear-time gromov wasserstein distances using low rank couplings and costs

    Original

    Meyer Scetbon, Gabriel Peyré, and Marco Cuturi

    Cited in the paper.

Then

  • Differentiable ranking and sorting using optimal transport

    Marco Cuturi, Olivier Teboul, and Jean-Philippe Vert · 2019

    Later among the works it cites.

  • Sample complexity of sinkhorn divergences

    Aude Genevay, Lénaic Chizat, Francis Bach, Marco Cuturi, and Gabriel Peyré · 2019

    Later among the works it cites.

  • Statistical bounds for entropic optimal transport: Sample complexity and the central limit theorem

    Gonzalo Mena and Jonathan Niles-Weed · 2019

    Later among the works it cites.

  • Supervised quantile normalization for low rank matrix factorization

    Marco Cuturi, Olivier Teboul, Jonathan Niles-Weed, and Jean-Philippe Vert · 2020

    Later among the works it cites.

  • A wasserstein-type distance in the space of gaussian mixture models

    Julie Delon and Agnes Desolneux · 2020

    Later among the works it cites.

Beyond the bibliography

alphaXiv searches the wider corpus for related work and actual follow-ups.

Open on alphaXiv

alphaXiv is searching for related work…