F
François-Xavier Vialard
Researcher at University of Marne-la-Vallée
Publications - 88
Citations - 3092
François-Xavier Vialard is an academic researcher from University of Marne-la-Vallée. The author has contributed to research in topics: Geodesic & Metric (mathematics). The author has an hindex of 23, co-authored 87 publications receiving 2344 citations. Previous affiliations of François-Xavier Vialard include École normale supérieure de Cachan & Imperial College London.
Papers
More filters
Posted Content
Interpolating between Optimal Transport and MMD using Sinkhorn Divergences
Jean Feydy,Thibault Séjourné,François-Xavier Vialard,François-Xavier Vialard,Shun-ichi Amari,Alain Trouvé,Gabriel Peyré +6 more
TL;DR: In this article, the Sinkhorn divergences, a family of geometric divergence that interpolates between Maximum Mean Discrepancies (MMD) and Optimal Transport distances (OT), are studied.
Journal ArticleDOI
Scaling algorithms for unbalanced optimal transport problems
Journal ArticleDOI
Diffeomorphic 3D Image Registration via Geodesic Shooting Using an Efficient Adjoint Calculation
TL;DR: The key contribution of this work is to provide an accurate estimation of the so-called initial momentum, which is a scalar function encoding the optimal deformation between two images through the Hamiltonian equations of geodesics.
Journal ArticleDOI
Unbalanced Optimal Transport: Dynamic and Kantorovich Formulations
TL;DR: A new class of distances between arbitrary nonnegative Radon measures inspired by optimal transport is presented, and of particular interest is the Wasserstein–Fisher–Rao metric, which belongs to this class of metrics and hence automatically benefits from a static Kantorovich formulation.
Book ChapterDOI
Geodesic regression for image time-series
TL;DR: A generative model extending least squares linear regression to the space of images by using a second-order dynamic formulation for image registration, which allows for a compact representation of an approximation to the full spatio-temporal trajectory through its initial values.