Non-asymptotic convergence bounds for Wasserstein approximation using point clouds - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2021

Non-asymptotic convergence bounds for Wasserstein approximation using point clouds

Résumé

Several issues in machine learning and inverse problems require to generate discrete data, as if sampled from a model probability distribution. A common way to do so relies on the construction of a uniform probability distribution over a set of $N$ points which minimizes the Wasserstein distance to the model distribution. This minimization problem, where the unknowns are the positions of the atoms, is non-convex. Yet, in most cases, a suitably adjusted version of Lloyd's algorithm --- in which Voronoi cells are replaced by Power cells --- leads to configurations with small Wasserstein error. This is surprising because, again, of the non-convex nature of the problem, as well as the existence of spurious critical points. We provide explicit upper bounds for the convergence speed of this Lloyd-type algorithm, starting from a cloud of points sufficiently far from each other. This already works after one step of the iteration procedure, and similar bounds can be deduced, for the corresponding gradient descent. These bounds naturally lead to a modified Poliak-Łojasiewicz inequality for the Wasserstein distance cost, with an error term depending on the distances between Dirac masses in the discrete distribution.
Fichier principal
Vignette du fichier
optquant.pdf (6.26 Mo) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-03256039 , version 1 (14-06-2021)

Identifiants

Citer

Quentin Merigot, Filippo Santambrogio, Clément Sarrazin. Non-asymptotic convergence bounds for Wasserstein approximation using point clouds. 35th Conference on Neural Information Processing Systems (NeurIPS 2021), Dec 2021, Online, France. pp.12810--12821. ⟨hal-03256039⟩
552 Consultations
192 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More