Pith. sign in

REVIEW 7 cited by

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

Not yet reviewed by Pith; the record is open.

Re-run · record.json Download PDF Read on arXiv ↗

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2201.12324 v1 pith:VBG3NLOS submitted 2022-01-28 cs.LG stat.ML

Marco Cuturi , Laetitia Meng-Papaxanthos , Yingtao Tian , Charlotte Bunne , Geoff Davis , Olivier Teboul This is my paper · ORCID
classification cs.LGstat.ML
keywords toolboxoptimaltransportott-jaxtoolsacceleratorsadvancedapproximate
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

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}

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 7 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. Offline Reinforcement Learning with Wasserstein Regularization via Optimal Transport Maps

    cs.LG 2025-07 conditional novelty 7.0 of 10

    Q-DOT uses gradient maps of input-convex neural networks to compute Wasserstein regularization in offline RL, achieving D4RL scores comparable to or better than IQL without adversarial training.

  2. Convergence of empirical subgradients for optimal transport-based objectives

    math.OC 2026-05 unverdicted novelty 6.0 of 10

    Under smooth unit costs and models, empirical subdifferentials of parameterized transport objectives converge graphically almost surely to the population subdifferential, so subgradient methods approach population cri...

  3. Reinforced sequential Monte Carlo for amortised sampling

    cs.LG 2025-10 conditional novelty 6.0 of 10

    A method that trains neural samplers using SMC-collected off-policy samples and an importance-weighted replay buffer improves mode coverage on multi-modal targets.

  4. Flowing Datasets with Wasserstein over Wasserstein Gradient Flows

    cs.LG 2025-06 conditional novelty 6.0 of 10

    A new gradient flow framework on the space of probability distributions over probability distributions is introduced and applied to flowing labeled datasets between domains.

  5. Multivariate Conformal Prediction using Optimal Transport

    stat.ML 2025-02 conditional novelty 6.0 of 10

    Using the norm of an optimal transport map as a conformity score gives distribution-free, finite-sample coverage for multivariate conformal prediction sets.

  6. Towards Adaptive External Communication in Autonomous Vehicles: A Conceptual Design Framework

    cs.HC 2025-08 unverdicted novelty 5.0 of 10

    A three-layer framework (input, processing, output) for adaptive external human-machine interfaces in autonomous vehicles is introduced to systematize design and analysis.

  7. A deep learning approach to multi-marginal optimal transport via Hilbert space embeddings of probability measures

    math.OC 2025-07 conditional novelty 4.0 of 10

    A deep learning penalty method using maximum mean discrepancy enforces marginal constraints in multi-marginal Monge transport, with a convergence theorem for constraint satisfaction only.

Pith tools