Unbalanced Optimal Transport across Metric Measured Spaces

De Gabriel Peyré

Apparaît dans la collection : 2022 - T3 - WS3 - Measure-theoretic Approaches and Optimal Transportation in Statistics

Optimal transport (OT) has recently gained a lot of interest in machine learning. It is a natural tool to compare in a geometrically faithful way probability distributions. It finds applications in both supervised learning (using geometric loss functions) and unsupervised learning (to perform generative model fitting). OT is however plagued by several issues, and in particular:

(i) the curse of dimensionality, since it might require a number of samples which grows exponentially with the dimension,

(ii) sensitivity to outliers, since it prevents mass creation and destruction during the transport,

(iii) impossibility to transport between two disjoint spaces. In this talk, I will review several recent proposals to address these issues, and showcase how they work hand-in-hand to provide a comprehensive machine learning pipeline.

The three key ingredients are:

(i) entropic regularization which defines computationally efficient loss functions in high dimensions,

(ii) unbalanced OT, which relaxes the mass conservation to make OT robust to missing data and outliers,

(iii) the Gromov-Wasserstein formulation, introduced by Sturm and Memoli, which is a non-convex quadratic optimization problem defining transport between disjoint spaces.

Informations sur la vidéo

Données de citation

  • DOI 10.57987/IHP.2022.T3.WS3.007
  • Citer cette vidéo Peyré Gabriel (22/11/2022). Unbalanced Optimal Transport across Metric Measured Spaces. IHP. Audiovisual resource. DOI: 10.57987/IHP.2022.T3.WS3.007
  • URL https://dx.doi.org/10.57987/IHP.2022.T3.WS3.007

Bibliographie

  • T. Séjourné, F-X. Vialard, G. Peyré / The Unbalanced Gromov Wasserstein Distance: Conic Formulation and Relaxation. In Proc. NeurIPS'21, 2021
  • Gabriel Peyré, Marco Cuturi / Computational Optimal Transport. arXiv:1803.00567

Dernières questions liées sur MathOverflow

Pour poser une question, votre compte Carmin.tv doit être connecté à mathoverflow

Poser une question sur MathOverflow




Inscrivez-vous

  • Mettez des vidéos en favori
  • Ajoutez des vidéos à regarder plus tard &
    conservez votre historique de consultation
  • Commentez avec la communauté
    scientifique
  • Recevez des notifications de mise à jour
    de vos sujets favoris
Donner son avis